@henjicc/ai-sdk 0.9.0 → 0.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +50 -0
- package/README.md +580 -577
- package/dist/capabilities/speech-recognition/bailian/module.js +12 -13
- package/dist/capabilities/speech-recognition/bailian/parse.js +9 -2
- package/dist/capabilities/speech-recognition/bailian/presets.d.ts +9 -1
- package/dist/capabilities/speech-recognition/bailian/presets.js +7 -2
- package/dist/capabilities/speech-recognition/bailian/realtime/presets.d.ts +2 -1
- package/dist/capabilities/speech-recognition/bailian/realtime/presets.js +2 -0
- package/dist/capabilities/speech-recognition/bailian/upload.js +11 -58
- package/dist/capabilities/speech-recognition/index.d.ts +5 -0
- package/dist/capabilities/speech-recognition/siliconflow/presets.d.ts +2 -3
- package/dist/capabilities/speech-recognition/siliconflow/presets.js +0 -2
- package/dist/capabilities/translation/bailian/types.d.ts +3 -0
- package/dist/capabilities/translation/bailian/types.js +6 -4
- package/dist/catalog/apimart/flux-3-image.model.d.ts +3 -0
- package/dist/catalog/apimart/flux-3-image.model.js +62 -0
- package/dist/catalog/apimart/flux-3-video.model.d.ts +3 -0
- package/dist/catalog/apimart/flux-3-video.model.js +120 -0
- package/dist/catalog/apimart/gemini-omni-1.2-flash.model.d.ts +3 -0
- package/dist/catalog/apimart/gemini-omni-1.2-flash.model.js +175 -0
- package/dist/catalog/apimart/gemini-omni-flash.model.js +27 -23
- package/dist/catalog/apimart/gpt-image-2.5.model.js +1 -1
- package/dist/catalog/apimart/gpt-image-2.6.model.d.ts +3 -0
- package/dist/catalog/apimart/gpt-image-2.6.model.js +103 -0
- package/dist/catalog/apimart/gpt-image-2.model.js +1 -1
- package/dist/catalog/apimart/grok-imagine-2.0.model.js +1 -1
- package/dist/catalog/apimart/grok-imagine-video-1.5.model.d.ts +3 -0
- package/dist/catalog/apimart/grok-imagine-video-1.5.model.js +85 -0
- package/dist/catalog/apimart/happyhorse-1.1.model.d.ts +3 -0
- package/dist/catalog/apimart/happyhorse-1.1.model.js +78 -0
- package/dist/catalog/apimart/kling-3.0-omni.model.js +12 -2
- package/dist/catalog/apimart/kling-3.0-turbo.model.js +5 -2
- package/dist/catalog/apimart/kling-3.0.model.js +1 -1
- package/dist/catalog/apimart/kling-4.0.model.d.ts +3 -0
- package/dist/catalog/apimart/kling-4.0.model.js +149 -0
- package/dist/catalog/apimart/midjourney-video.model.js +31 -32
- package/dist/catalog/apimart/midjourney.model.js +11 -1
- package/dist/catalog/apimart/minimax-h3-max.model.d.ts +3 -0
- package/dist/catalog/apimart/minimax-h3-max.model.js +101 -0
- package/dist/catalog/apimart/minimax-h3.model.js +8 -3
- package/dist/catalog/apimart/nano-banana-2-lite.model.js +1 -1
- package/dist/catalog/apimart/nano-banana-2.1.model.d.ts +2 -0
- package/dist/catalog/apimart/nano-banana-2.1.model.js +49 -0
- package/dist/catalog/apimart/nano-banana-2.model.js +1 -1
- package/dist/catalog/apimart/nano-banana-pro.model.js +1 -1
- package/dist/catalog/apimart/qwen-image-3.0.model.js +1 -1
- package/dist/catalog/apimart/seedance-2.0-fast.model.js +1 -1
- package/dist/catalog/apimart/seedance-2.0-mini.model.js +4 -4
- package/dist/catalog/apimart/seedance-2.0.model.js +1 -1
- package/dist/catalog/apimart/seedance-2.5.model.js +27 -5
- package/dist/catalog/apimart/seedream-5.0-flash.model.d.ts +3 -0
- package/dist/catalog/apimart/seedream-5.0-flash.model.js +52 -0
- package/dist/catalog/apimart/seedream-5.0-lite.model.js +4 -4
- package/dist/catalog/apimart/seedream-5.0-pro.model.js +1 -1
- package/dist/catalog/apimart/veo-3.1.model.d.ts +3 -0
- package/dist/catalog/apimart/veo-3.1.model.js +132 -0
- package/dist/catalog/apimart/wan-2.7-image.model.d.ts +3 -0
- package/dist/catalog/apimart/wan-2.7-image.model.js +80 -0
- package/dist/catalog/apimart/wan-3.0.model.d.ts +3 -0
- package/dist/catalog/apimart/wan-3.0.model.js +101 -0
- package/dist/catalog/apimart/z-image-turbo.model.js +1 -1
- package/dist/catalog/audio/tts-common.d.ts +2 -1
- package/dist/catalog/audio/tts-common.js +5 -1
- package/dist/catalog/bailian/cosyvoice-v3.5.model.js +1 -1
- package/dist/catalog/bailian/minimax-h3.model.d.ts +3 -0
- package/dist/catalog/bailian/minimax-h3.model.js +95 -0
- package/dist/catalog/bailian/minimax-speech-2.8.model.js +1 -1
- package/dist/catalog/bailian/qwen-audio-3.1-tts-flash.model.js +14 -3
- package/dist/catalog/bailian/qwen-audio-3.1-tts-plus.model.d.ts +2 -0
- package/dist/catalog/bailian/qwen-audio-3.1-tts-plus.model.js +44 -0
- package/dist/catalog/bailian/qwen-image-3.0.model.js +1 -1
- package/dist/catalog/bailian/wan-3.0.model.d.ts +3 -0
- package/dist/catalog/bailian/wan-3.0.model.js +104 -0
- package/dist/catalog/bailian/z-image-turbo.model.js +1 -1
- package/dist/catalog/consumer-contract.d.ts +16 -1
- package/dist/catalog/consumer-contract.js +31 -0
- package/dist/catalog/continuation.d.ts +20 -0
- package/dist/catalog/continuation.js +41 -0
- package/dist/catalog/fal/bria-creative-upscale.model.js +1 -1
- package/dist/catalog/fal/eleven-v3-tts.model.js +1 -1
- package/dist/catalog/fal/eleven-v4-tts.model.d.ts +2 -0
- package/dist/catalog/fal/eleven-v4-tts.model.js +38 -0
- package/dist/catalog/fal/flux-3-video.model.d.ts +2 -0
- package/dist/catalog/fal/flux-3-video.model.js +187 -0
- package/dist/catalog/fal/flux-3.model.d.ts +2 -0
- package/dist/catalog/fal/flux-3.model.js +69 -0
- package/dist/catalog/fal/gemini-omni-1.2-flash.model.d.ts +2 -0
- package/dist/catalog/fal/gemini-omni-1.2-flash.model.js +129 -0
- package/dist/catalog/fal/gemini-omni-flash.model.js +1 -1
- package/dist/catalog/fal/gpt-image-2.5.model.js +1 -1
- package/dist/catalog/fal/gpt-image-2.6.model.d.ts +2 -0
- package/dist/catalog/fal/gpt-image-2.6.model.js +97 -0
- package/dist/catalog/fal/gpt-image-2.model.js +1 -1
- package/dist/catalog/fal/grok-imagine-2.0.model.js +1 -1
- package/dist/catalog/fal/grok-imagine-video-1.5.model.d.ts +2 -0
- package/dist/catalog/fal/grok-imagine-video-1.5.model.js +121 -0
- package/dist/catalog/fal/hailuo-02.model.js +8 -4
- package/dist/catalog/fal/hailuo-2.3.model.js +1 -1
- package/dist/catalog/fal/ic-light-v2.model.js +1 -1
- package/dist/catalog/fal/ideogram-upscale.model.js +1 -1
- package/dist/catalog/fal/kling-3.0-omni.model.js +1 -1
- package/dist/catalog/fal/kling-3.0-turbo.model.js +5 -2
- package/dist/catalog/fal/kling-3.0.model.js +4 -1
- package/dist/catalog/fal/kling-4.0-flash.model.d.ts +2 -0
- package/dist/catalog/fal/kling-4.0-flash.model.js +132 -0
- package/dist/catalog/fal/kling-4.0.model.d.ts +2 -0
- package/dist/catalog/fal/kling-4.0.model.js +169 -0
- package/dist/catalog/fal/kling-image-o1.model.js +1 -1
- package/dist/catalog/fal/kling-video-o1.model.js +18 -7
- package/dist/catalog/fal/kling-video-v2.6-pro.model.js +3 -2
- package/dist/catalog/fal/ltx-2.3.model.d.ts +2 -0
- package/dist/catalog/fal/ltx-2.3.model.js +223 -0
- package/dist/catalog/fal/ltx-2.model.js +2 -1
- package/dist/catalog/fal/minimax-h3-max.model.d.ts +2 -0
- package/dist/catalog/fal/minimax-h3-max.model.js +132 -0
- package/dist/catalog/fal/minimax-h3.model.js +3 -4
- package/dist/catalog/fal/minimax-speech-2.8.model.js +1 -1
- package/dist/catalog/fal/nano-banana-2.1.model.d.ts +2 -0
- package/dist/catalog/fal/nano-banana-2.1.model.js +68 -0
- package/dist/catalog/fal/nano-banana-2.model.js +1 -1
- package/dist/catalog/fal/nano-banana-pro.model.js +1 -1
- package/dist/catalog/fal/nano-banana.model.js +1 -1
- package/dist/catalog/fal/pixverse-v5.5.model.js +9 -4
- package/dist/catalog/fal/qwen-image-3.0.model.js +2 -2
- package/dist/catalog/fal/qwen3-tts-1.7b.model.js +4 -3
- package/dist/catalog/fal/seedance-2.0-fast.model.js +1 -1
- package/dist/catalog/fal/seedance-2.0-mini.model.js +1 -1
- package/dist/catalog/fal/seedance-2.0.model.js +1 -1
- package/dist/catalog/fal/seedance-2.5.model.js +5 -2
- package/dist/catalog/fal/seedance.model.js +3 -2
- package/dist/catalog/fal/seedream-5.0-lite.model.js +1 -1
- package/dist/catalog/fal/seedream-5.0-pro.model.js +1 -1
- package/dist/catalog/fal/seedream-v4.5.model.js +1 -1
- package/dist/catalog/fal/seedream-v4.model.js +1 -1
- package/dist/catalog/fal/seedvr2-image-upscale.model.js +1 -1
- package/dist/catalog/fal/topaz-image-upscale.model.js +1 -1
- package/dist/catalog/fal/topaz-transparent-upscale.model.js +1 -1
- package/dist/catalog/fal/utils/klingV4.d.ts +17 -0
- package/dist/catalog/fal/utils/klingV4.js +33 -0
- package/dist/catalog/fal/veo-3.1.model.js +5 -2
- package/dist/catalog/fal/vidu-q2.model.js +20 -8
- package/dist/catalog/fal/wan-2.5-preview.model.js +4 -1
- package/dist/catalog/fal/wan-3.0.model.d.ts +2 -0
- package/dist/catalog/fal/wan-3.0.model.js +135 -0
- package/dist/catalog/fal/z-image-turbo.model.js +10 -9
- package/dist/catalog/grsai/gpt-image-2.5.model.js +13 -31
- package/dist/catalog/grsai/gpt-image-2.6.model.d.ts +2 -0
- package/dist/catalog/grsai/gpt-image-2.6.model.js +37 -0
- package/dist/catalog/grsai/gpt-image-2.model.js +5 -2
- package/dist/catalog/grsai/nano-banana-2-lite.model.js +1 -1
- package/dist/catalog/grsai/nano-banana-2.1.model.d.ts +2 -0
- package/dist/catalog/grsai/nano-banana-2.1.model.js +29 -0
- package/dist/catalog/grsai/nano-banana-2.model.js +1 -1
- package/dist/catalog/grsai/nano-banana-pro.model.js +1 -1
- package/dist/catalog/grsai/wan-3.0.model.d.ts +2 -0
- package/dist/catalog/grsai/wan-3.0.model.js +78 -0
- package/dist/catalog/index.d.ts +1 -0
- package/dist/catalog/index.js +205 -124
- package/dist/catalog/kie/eleven-v3-dialogue.model.js +1 -1
- package/dist/catalog/kie/flux-3-klein.model.d.ts +2 -0
- package/dist/catalog/kie/flux-3-klein.model.js +58 -0
- package/dist/catalog/kie/gemini-3.1-flash-tts.model.js +7 -4
- package/dist/catalog/kie/gemini-3.8-flash-lite-tts.model.d.ts +2 -0
- package/dist/catalog/kie/gemini-3.8-flash-lite-tts.model.js +11 -0
- package/dist/catalog/kie/gemini-3.8-flash-tts.model.d.ts +2 -0
- package/dist/catalog/kie/gemini-3.8-flash-tts.model.js +11 -0
- package/dist/catalog/kie/gemini-omni-video.model.js +3 -4
- package/dist/catalog/kie/gemini38Tts.d.ts +3 -0
- package/dist/catalog/kie/gemini38Tts.js +40 -0
- package/dist/catalog/kie/gpt-image-2.5.model.js +1 -1
- package/dist/catalog/kie/gpt-image-2.6.model.d.ts +2 -0
- package/dist/catalog/kie/gpt-image-2.6.model.js +87 -0
- package/dist/catalog/kie/gpt-image-2.model.js +8 -12
- package/dist/catalog/kie/grok-imagine-2.0.model.js +1 -1
- package/dist/catalog/kie/grok-imagine-video-1.5.model.d.ts +2 -0
- package/dist/catalog/kie/grok-imagine-video-1.5.model.js +52 -0
- package/dist/catalog/kie/grok-imagine-video.model.js +7 -3
- package/dist/catalog/kie/grok-imagine.model.js +4 -2
- package/dist/catalog/kie/hailuo-02.model.js +6 -4
- package/dist/catalog/kie/hailuo-2-3.model.js +1 -1
- package/dist/catalog/kie/happyhorse-1.1.model.js +5 -2
- package/dist/catalog/kie/kling-3.0-omni.model.js +51 -23
- package/dist/catalog/kie/kling-3.0-turbo.model.js +1 -1
- package/dist/catalog/kie/kling-3.0.model.js +1 -8
- package/dist/catalog/kie/kling-4.0-flash.model.d.ts +2 -0
- package/dist/catalog/kie/kling-4.0-flash.model.js +16 -0
- package/dist/catalog/kie/kling-4.0.model.d.ts +2 -0
- package/dist/catalog/kie/kling-4.0.model.js +17 -0
- package/dist/catalog/kie/kling-v2-6.model.js +1 -1
- package/dist/catalog/kie/kling40.d.ts +21 -0
- package/dist/catalog/kie/kling40.js +129 -0
- package/dist/catalog/kie/minimax-h3.model.js +16 -21
- package/dist/catalog/kie/nano-banana-2-lite.model.js +1 -1
- package/dist/catalog/kie/nano-banana-2.1.model.d.ts +2 -0
- package/dist/catalog/kie/nano-banana-2.1.model.js +34 -0
- package/dist/catalog/kie/nano-banana-2.model.js +2 -2
- package/dist/catalog/kie/nano-banana-pro.model.js +1 -1
- package/dist/catalog/kie/qwen-image-3.0.model.js +2 -10
- package/dist/catalog/kie/seedance-1.5-pro.model.js +2 -1
- package/dist/catalog/kie/seedance-2.0-fast.model.js +5 -1
- package/dist/catalog/kie/seedance-2.0-mini.model.js +5 -1
- package/dist/catalog/kie/seedance-2.0.model.js +5 -1
- package/dist/catalog/kie/seedance-2.5.model.js +10 -20
- package/dist/catalog/kie/seedance-v1.model.js +8 -4
- package/dist/catalog/kie/seedream-4.0.model.js +1 -1
- package/dist/catalog/kie/seedream-4.5.model.js +1 -1
- package/dist/catalog/kie/seedream-5.0-lite.model.js +1 -1
- package/dist/catalog/kie/seedream-5.0-pro.model.js +1 -1
- package/dist/catalog/kie/wan-3.0-prime.model.d.ts +2 -0
- package/dist/catalog/kie/wan-3.0-prime.model.js +15 -0
- package/dist/catalog/kie/wan-3.0.model.d.ts +2 -0
- package/dist/catalog/kie/wan-3.0.model.js +15 -0
- package/dist/catalog/kie/wan30.d.ts +10 -0
- package/dist/catalog/kie/wan30.js +78 -0
- package/dist/catalog/kie/z-image.model.js +1 -1
- package/dist/catalog/modelscope/flux-1-krea-dev.model.js +4 -2
- package/dist/catalog/modelscope/majicmix-realistic.model.js +3 -2
- package/dist/catalog/modelscope/modelscope-custom.model.js +3 -2
- package/dist/catalog/modelscope/qwen-image-2512.model.d.ts +5 -0
- package/dist/catalog/modelscope/{qwen-image.model.js → qwen-image-2512.model.js} +11 -8
- package/dist/catalog/modelscope/qwen-image-edit-2511.model.d.ts +5 -0
- package/dist/catalog/modelscope/{qwen-image-edit-2509.model.js → qwen-image-edit-2511.model.js} +9 -7
- package/dist/catalog/modelscope/sdxl-14-ckpt.model.js +3 -2
- package/dist/catalog/modelscope/utils.js +2 -2
- package/dist/catalog/modelscope/z-image-turbo.model.js +3 -2
- package/dist/catalog/ppio/kling-3.0.model.js +4 -1
- package/dist/catalog/ppio/minimax-speech.model.js +2 -1
- package/dist/catalog/shared/mediaPresence.d.ts +8 -1
- package/dist/catalog/shared/mediaPresence.js +21 -1
- package/dist/catalog/shared/nanoBanana21.d.ts +11 -0
- package/dist/catalog/shared/nanoBanana21.js +30 -0
- package/dist/catalog/shared/shotList.d.ts +31 -0
- package/dist/catalog/shared/shotList.js +48 -0
- package/dist/catalog/shared/subjectElements.d.ts +36 -0
- package/dist/catalog/shared/subjectElements.js +93 -0
- package/dist/catalog/siliconflow/moss-ttsd-0.5.model.js +1 -1
- package/dist/catalog/validate.js +14 -1
- package/dist/catalog/volcengine/seedance-2.0-fast.model.d.ts +2 -0
- package/dist/catalog/volcengine/seedance-2.0-fast.model.js +11 -0
- package/dist/catalog/volcengine/seedance-2.0-mini.model.d.ts +2 -0
- package/dist/catalog/volcengine/seedance-2.0-mini.model.js +11 -0
- package/dist/catalog/volcengine/seedance-2.0.model.d.ts +2 -0
- package/dist/catalog/volcengine/seedance-2.0.model.js +11 -0
- package/dist/catalog/volcengine/seedance-2.5.model.d.ts +2 -0
- package/dist/catalog/volcengine/seedance-2.5.model.js +11 -0
- package/dist/catalog/volcengine/seedance.d.ts +17 -0
- package/dist/catalog/volcengine/seedance.js +192 -0
- package/dist/catalog/volcengine/seedream-5.0-lite.model.js +2 -1
- package/dist/catalog/volcengine/seedream-5.0.js +1 -1
- package/dist/catalog/volcengine-speech/seed-icl-2.0.model.js +2 -2
- package/dist/catalog/volcengine-speech/seed-tts-2.0.model.js +2 -2
- package/dist/discovery/index.js +13 -6
- package/dist/index.d.ts +3 -0
- package/dist/index.js +2 -0
- package/dist/llm/bigmodel/preset.js +2 -1
- package/dist/llm/bigmodel/profiles.js +0 -6
- package/dist/llm/chat.d.ts +8 -0
- package/dist/llm/chat.js +18 -2
- package/dist/llm/chatTypes.d.ts +6 -0
- package/dist/llm/defaults.d.ts +2 -2
- package/dist/llm/defaults.js +3 -3
- package/dist/llm/groq/preset.js +18 -2
- package/dist/llm/modelCatalog.d.ts +9 -2
- package/dist/llm/modelCatalog.js +17 -4
- package/dist/llm/modelCatalogEntries.d.ts +2 -0
- package/dist/llm/modelCatalogEntries.js +197 -42
- package/dist/llm/providerPresets.d.ts +3 -0
- package/dist/llm/providerPresets.js +145 -32
- package/dist/llm/providerReasoningRequest.js +28 -11
- package/dist/llm/siliconflow/index.js +1 -1
- package/dist/llm/siliconflow/preset.js +30 -0
- package/dist/llm/types.d.ts +6 -0
- package/dist/packs/models/{ppio/wan-2.5-preview.d.ts → apimart/flux-3-image.d.ts} +1 -1
- package/dist/packs/models/apimart/flux-3-image.js +7 -0
- package/dist/packs/models/apimart/flux-3-video.d.ts +6 -0
- package/dist/packs/models/apimart/flux-3-video.js +7 -0
- package/dist/packs/models/apimart/gemini-omni-1.2-flash.d.ts +6 -0
- package/dist/packs/models/apimart/gemini-omni-1.2-flash.js +7 -0
- package/dist/packs/models/{modelscope/qwen-image.d.ts → apimart/gpt-image-2.6.d.ts} +1 -1
- package/dist/packs/models/apimart/gpt-image-2.6.js +7 -0
- package/dist/packs/models/apimart/grok-imagine-video-1.5.d.ts +6 -0
- package/dist/packs/models/apimart/grok-imagine-video-1.5.js +7 -0
- package/dist/packs/models/apimart/happyhorse-1.1.d.ts +6 -0
- package/dist/packs/models/apimart/happyhorse-1.1.js +7 -0
- package/dist/packs/models/apimart/kling-4.0.d.ts +6 -0
- package/dist/packs/models/apimart/kling-4.0.js +7 -0
- package/dist/packs/models/apimart/minimax-h3-max.d.ts +6 -0
- package/dist/packs/models/apimart/minimax-h3-max.js +7 -0
- package/dist/packs/models/{ppio/minimax-hailuo-2.3.d.ts → apimart/nano-banana-2.1.d.ts} +1 -1
- package/dist/packs/models/{ppio/minimax-hailuo-2.3.js → apimart/nano-banana-2.1.js} +4 -4
- package/dist/packs/models/apimart/seedream-5.0-flash.d.ts +6 -0
- package/dist/packs/models/apimart/seedream-5.0-flash.js +7 -0
- package/dist/packs/models/apimart/veo-3.1.d.ts +6 -0
- package/dist/packs/models/apimart/veo-3.1.js +7 -0
- package/dist/packs/models/apimart/wan-2.7-image.d.ts +6 -0
- package/dist/packs/models/apimart/wan-2.7-image.js +7 -0
- package/dist/packs/models/apimart/wan-3.0.d.ts +6 -0
- package/dist/packs/models/apimart/wan-3.0.js +7 -0
- package/dist/packs/models/bailian/cosyvoice-v3.5.js +1 -1
- package/dist/packs/models/bailian/minimax-h3.d.ts +6 -0
- package/dist/packs/models/bailian/minimax-h3.js +7 -0
- package/dist/packs/models/bailian/minimax-speech-2.8.js +1 -1
- package/dist/packs/models/bailian/qwen-audio-3.1-tts-flash.js +1 -1
- package/dist/packs/models/bailian/qwen-audio-3.1-tts-plus.d.ts +6 -0
- package/dist/packs/models/bailian/qwen-audio-3.1-tts-plus.js +7 -0
- package/dist/packs/models/bailian/qwen-image-3.0.js +1 -1
- package/dist/packs/models/bailian/wan-3.0.d.ts +6 -0
- package/dist/packs/models/bailian/wan-3.0.js +7 -0
- package/dist/packs/models/bailian/z-image-turbo.js +1 -1
- package/dist/packs/models/fal/eleven-v4-tts.d.ts +6 -0
- package/dist/packs/models/{ppio/wan-2.5-preview.js → fal/eleven-v4-tts.js} +4 -4
- package/dist/packs/models/fal/flux-3-video.d.ts +6 -0
- package/dist/packs/models/fal/flux-3-video.js +7 -0
- package/dist/packs/models/{ppio/wan-2.6.d.ts → fal/flux-3.d.ts} +1 -1
- package/dist/packs/models/{ppio/wan-2.6.js → fal/flux-3.js} +4 -4
- package/dist/packs/models/fal/gemini-omni-1.2-flash.d.ts +6 -0
- package/dist/packs/models/fal/gemini-omni-1.2-flash.js +7 -0
- package/dist/packs/models/fal/gpt-image-2.6.d.ts +6 -0
- package/dist/packs/models/fal/gpt-image-2.6.js +7 -0
- package/dist/packs/models/fal/grok-imagine-video-1.5.d.ts +6 -0
- package/dist/packs/models/fal/grok-imagine-video-1.5.js +7 -0
- package/dist/packs/models/fal/kling-4.0-flash.d.ts +6 -0
- package/dist/packs/models/fal/kling-4.0-flash.js +7 -0
- package/dist/packs/models/fal/kling-4.0.d.ts +6 -0
- package/dist/packs/models/{ppio/wan-2.7.js → fal/kling-4.0.js} +4 -4
- package/dist/packs/models/{ppio/wan-2.7.d.ts → fal/ltx-2.3.d.ts} +1 -1
- package/dist/packs/models/fal/ltx-2.3.js +7 -0
- package/dist/packs/models/fal/minimax-h3-max.d.ts +6 -0
- package/dist/packs/models/fal/minimax-h3-max.js +7 -0
- package/dist/packs/models/fal/nano-banana-2.1.d.ts +6 -0
- package/dist/packs/models/fal/nano-banana-2.1.js +7 -0
- package/dist/packs/models/fal/wan-3.0.d.ts +6 -0
- package/dist/packs/models/fal/wan-3.0.js +7 -0
- package/dist/packs/models/grsai/gpt-image-2.6.d.ts +6 -0
- package/dist/packs/models/grsai/gpt-image-2.6.js +7 -0
- package/dist/packs/models/grsai/nano-banana-2.1.d.ts +6 -0
- package/dist/packs/models/grsai/nano-banana-2.1.js +7 -0
- package/dist/packs/models/grsai/wan-3.0.d.ts +6 -0
- package/dist/packs/models/grsai/wan-3.0.js +7 -0
- package/dist/packs/models/kie/flux-3-klein.d.ts +6 -0
- package/dist/packs/models/kie/flux-3-klein.js +7 -0
- package/dist/packs/models/kie/gemini-3.8-flash-lite-tts.d.ts +6 -0
- package/dist/packs/models/kie/gemini-3.8-flash-lite-tts.js +7 -0
- package/dist/packs/models/kie/{eleven-turbo-2.5-tts.d.ts → gemini-3.8-flash-tts.d.ts} +1 -1
- package/dist/packs/models/kie/{eleven-turbo-2.5-tts.js → gemini-3.8-flash-tts.js} +1 -1
- package/dist/packs/models/kie/gpt-image-2.6.d.ts +6 -0
- package/dist/packs/models/kie/gpt-image-2.6.js +7 -0
- package/dist/packs/models/kie/grok-imagine-video-1.5.d.ts +6 -0
- package/dist/packs/models/kie/grok-imagine-video-1.5.js +7 -0
- package/dist/packs/models/kie/kling-4.0-flash.d.ts +6 -0
- package/dist/packs/models/kie/kling-4.0-flash.js +7 -0
- package/dist/packs/models/kie/kling-4.0.d.ts +6 -0
- package/dist/packs/models/kie/kling-4.0.js +7 -0
- package/dist/packs/models/kie/nano-banana-2.1.d.ts +6 -0
- package/dist/packs/models/kie/nano-banana-2.1.js +7 -0
- package/dist/packs/models/kie/wan-3.0-prime.d.ts +6 -0
- package/dist/packs/models/kie/wan-3.0-prime.js +7 -0
- package/dist/packs/models/kie/wan-3.0.d.ts +6 -0
- package/dist/packs/models/kie/wan-3.0.js +7 -0
- package/dist/packs/models/modelscope/flux-1-krea-dev.js +1 -1
- package/dist/packs/models/modelscope/majicmix-realistic.js +1 -1
- package/dist/packs/models/modelscope/modelscope-custom.js +1 -1
- package/dist/packs/models/modelscope/qwen-image-2512.d.ts +6 -0
- package/dist/packs/models/modelscope/{qwen-image.js → qwen-image-2512.js} +2 -2
- package/dist/packs/models/modelscope/{qwen-image-edit-2509.d.ts → qwen-image-edit-2511.d.ts} +1 -1
- package/dist/packs/models/modelscope/{qwen-image-edit-2509.js → qwen-image-edit-2511.js} +2 -2
- package/dist/packs/models/modelscope/sdxl-14-ckpt.js +1 -1
- package/dist/packs/models/modelscope/z-image-turbo.js +1 -1
- package/dist/packs/models/volcengine/seedance-2.0-fast.d.ts +6 -0
- package/dist/packs/models/volcengine/seedance-2.0-fast.js +7 -0
- package/dist/packs/models/volcengine/seedance-2.0-mini.d.ts +6 -0
- package/dist/packs/models/volcengine/seedance-2.0-mini.js +7 -0
- package/dist/packs/models/volcengine/seedance-2.0.d.ts +6 -0
- package/dist/packs/models/volcengine/seedance-2.0.js +7 -0
- package/dist/packs/models/volcengine/seedance-2.5.d.ts +6 -0
- package/dist/packs/models/volcengine/seedance-2.5.js +7 -0
- package/dist/packs/models/volcengine/seedream-5.0-flash.js +1 -1
- package/dist/packs/models/volcengine/seedream-5.0-lite.js +1 -1
- package/dist/packs/models/volcengine/seedream-5.0-pro.js +1 -1
- package/dist/packs/provider-adapters/bailian.js +1 -1
- package/dist/packs/provider-adapters/modelscope.js +1 -1
- package/dist/packs/provider-adapters/volcengine.js +1 -1
- package/dist/packs/provider-packs/apimart.d.ts +1 -1
- package/dist/packs/provider-packs/apimart.js +35 -22
- package/dist/packs/provider-packs/bailian.d.ts +1 -1
- package/dist/packs/provider-packs/bailian.js +8 -5
- package/dist/packs/provider-packs/fal.d.ts +1 -1
- package/dist/packs/provider-packs/fal.js +52 -40
- package/dist/packs/provider-packs/grsai.d.ts +1 -1
- package/dist/packs/provider-packs/grsai.js +8 -5
- package/dist/packs/provider-packs/kie.d.ts +1 -1
- package/dist/packs/provider-packs/kie.js +41 -32
- package/dist/packs/provider-packs/modelscope.js +2 -2
- package/dist/packs/provider-packs/ppio.d.ts +1 -1
- package/dist/packs/provider-packs/ppio.js +2 -6
- package/dist/packs/provider-packs/volcengine.d.ts +1 -1
- package/dist/packs/provider-packs/volcengine.js +8 -4
- package/dist/pricing/index.d.ts +1 -0
- package/dist/pricing/index.js +1 -0
- package/dist/pricing/mediaContext.d.ts +6 -1
- package/dist/pricing/mediaContext.js +12 -5
- package/dist/pricing/tokenPricing.d.ts +36 -0
- package/dist/pricing/tokenPricing.js +26 -0
- package/dist/providers/bailian.d.ts +1 -1
- package/dist/providers/bailian.js +71 -4
- package/dist/providers/fal.js +11 -1
- package/dist/providers/helpers.d.ts +1 -1
- package/dist/providers/helpers.js +17 -5
- package/dist/providers/kie.js +16 -5
- package/dist/providers/metadata.js +2 -2
- package/dist/providers/openai-speech.d.ts +6 -0
- package/dist/providers/openai-speech.js +31 -0
- package/dist/providers/providerAccessErrors.d.ts +3 -0
- package/dist/providers/providerAccessErrors.js +73 -0
- package/dist/providers/siliconflow.js +2 -27
- package/dist/providers/volcengine-speech.js +22 -5
- package/dist/providers/volcengine-voice-clone.js +13 -4
- package/dist/providers/volcengine.d.ts +1 -1
- package/dist/providers/volcengine.js +89 -11
- package/dist/runtime/retry.js +3 -0
- package/dist/tool-packs/fal-erase/models/bria-eraser.model.js +1 -1
- package/dist/tool-packs/fal-erase/models/finegrain-eraser.model.js +1 -1
- package/dist/tool-packs/fal-erase/models/flux-pro-erase.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/control-light.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/outpaint.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/photo-restoration.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/pixelcut-background-removal.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/product-photography.model.js +1 -1
- package/dist/tool-packs/fal-image-utilities/models/relighting.model.js +1 -1
- package/dist/tool-packs/fal-multi-angle/models/flux-2-multiple-angles.model.js +1 -1
- package/dist/tool-packs/fal-multi-angle/models/perspective-change.model.js +1 -1
- package/dist/tool-packs/fal-multi-angle/models/qwen-image-edit-2511-multiple-angles.model.js +1 -1
- package/dist/types/model.d.ts +68 -12
- package/dist/types/model.js +3 -0
- package/dist/types/modelTags.d.ts +142 -0
- package/dist/types/modelTags.js +44 -0
- package/dist/types/speechTimings.d.ts +15 -0
- package/dist/types/speechTimings.js +1 -0
- package/dist/upload/apimart-upload.d.ts +1 -1
- package/dist/upload/apimart-upload.js +37 -15
- package/dist/upload/bailian-oss-upload.d.ts +32 -0
- package/dist/upload/bailian-oss-upload.js +74 -0
- package/dist/upload/{fal-legacy.js → fal-host-fetch.js} +2 -2
- package/dist/upload/fal-transport.d.ts +6 -0
- package/dist/upload/fal-transport.js +2 -1
- package/dist/upload/index.d.ts +2 -2
- package/dist/upload/index.js +4 -7
- package/dist/upload/kie-upload.d.ts +1 -1
- package/dist/upload/kie-upload.js +34 -12
- package/dist/upload/media-fields.js +7 -2
- package/dist/upload/preprocess-core.d.ts +2 -0
- package/dist/upload/preprocess-core.js +2 -0
- package/dist/upload/preprocess.d.ts +1 -1
- package/dist/upload/preprocess.js +12 -3
- package/dist/upload/provider-preprocessors/apimart.d.ts +1 -1
- package/dist/upload/provider-preprocessors/apimart.js +13 -5
- package/dist/upload/provider-preprocessors/bailian.d.ts +8 -0
- package/dist/upload/provider-preprocessors/bailian.js +45 -0
- package/dist/upload/provider-preprocessors/kie.d.ts +1 -1
- package/dist/upload/provider-preprocessors/kie.js +26 -9
- package/dist/upload/provider-preprocessors/ppio.d.ts +1 -2
- package/dist/upload/provider-preprocessors/ppio.js +2 -29
- package/dist/upload/provider-preprocessors/public-host.d.ts +5 -0
- package/dist/upload/provider-preprocessors/public-host.js +7 -0
- package/dist/upload/provider-preprocessors/volcengine.d.ts +5 -0
- package/dist/upload/provider-preprocessors/volcengine.js +10 -0
- package/dist/upload/public-host-upload.d.ts +7 -0
- package/dist/upload/public-host-upload.js +55 -0
- package/dist/upload/upload-response.js +12 -7
- package/docs/README.md +26 -26
- package/docs/consumers.md +156 -148
- package/docs/llm-adaptation/README.md +180 -166
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/DeepSeek.md +108 -104
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/Kimi.md +94 -76
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/MiniMax.md +89 -84
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//345/260/217/347/261/263MiMo.md +126 -126
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//346/231/272/350/260/261GLM.md +238 -234
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//347/201/253/345/261/261/345/274/225/346/223/216.md +131 -87
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//347/231/276/347/202/274Qwen.md +112 -84
- package/docs/llm-adaptation//346/226/207/346/241/243/351/207/207/351/233/206/346/211/213/345/206/214.md +88 -88
- package/docs/model-adaptation/Bria-Eraser/Bria-Eraser_Fal.md +32 -32
- package/docs/model-adaptation/Bria-/345/210/233/346/204/217/346/224/276/345/244/247/Bria-/345/210/233/346/204/217/346/224/276/345/244/247_Fal.md +31 -31
- package/docs/model-adaptation/ControlLight/ControlLight_Fal.md +85 -85
- package/docs/model-adaptation/Eleven-v4/Eleven-v4_Fal.md +49 -0
- package/docs/model-adaptation/FLUX-2-/345/244/232/350/247/222/345/272/246/FLUX-2-/345/244/232/350/247/222/345/272/246_Fal.md +107 -107
- package/docs/model-adaptation/FLUX-3/FLUX-3_APIMart.md +65 -0
- package/docs/model-adaptation/FLUX-3/FLUX-3_Fal.md +48 -0
- package/docs/model-adaptation/FLUX-3-Klein/FLUX-3-Klein_KIE.md +38 -0
- package/docs/model-adaptation/FLUX-3-Video/FLUX-3-Video_APIMart.md +84 -0
- package/docs/model-adaptation/FLUX-3-Video/FLUX-3-Video_Fal.md +80 -0
- package/docs/model-adaptation/Finegrain-Eraser/Finegrain-Eraser_Fal.md +31 -31
- package/docs/model-adaptation/Flux-Pro-Erase/Flux-Pro-Erase_Fal.md +34 -34
- package/docs/model-adaptation/Fun-ASR/Fun-ASR_/347/231/276/347/202/274.md +47 -47
- package/docs/model-adaptation/Fun-ASR-Flash-2026-06-15/Fun-ASR-Flash-2026-06-15_/347/231/276/347/202/274.md +45 -45
- package/docs/model-adaptation/Fun-ASR-Realtime/Fun-ASR-Realtime_/347/231/276/347/202/274.md +57 -57
- package/docs/model-adaptation/Fun-ASR-Realtime-2026-02-28/Fun-ASR-Realtime-2026-02-28_/347/231/276/347/202/274.md +39 -39
- package/docs/model-adaptation/GLM-5.3-Flash/GLM-5.3-Flash_/346/231/272/350/260/261.md +217 -213
- package/docs/model-adaptation/GPT-Image-2/GPT-Image-2_APIMart.md +173 -173
- package/docs/model-adaptation/GPT-Image-2/GPT-Image-2_Fal.md +94 -94
- package/docs/model-adaptation/GPT-Image-2/GPT-Image-2_Grsai.md +138 -137
- package/docs/model-adaptation/GPT-Image-2/GPT-Image-2_KIE.md +97 -93
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_APIMart.md +66 -66
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_Fal.md +55 -55
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_Grsai.md +59 -53
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_KIE.md +55 -55
- package/docs/model-adaptation/GPT-Image-2.6/GPT-Image-2.6_APIMart.md +101 -0
- package/docs/model-adaptation/GPT-Image-2.6/GPT-Image-2.6_Fal.md +55 -0
- package/docs/model-adaptation/GPT-Image-2.6/GPT-Image-2.6_Grsai.md +32 -0
- package/docs/model-adaptation/GPT-Image-2.6/GPT-Image-2.6_KIE.md +51 -0
- package/docs/model-adaptation/GPT-OSS-20B/GPT-OSS-20B_Groq.md +62 -62
- package/docs/model-adaptation/Gemini-3.8-Flash-Lite-TTS/Gemini-3.8-Flash-Lite-TTS_KIE.md +22 -0
- package/docs/model-adaptation/Gemini-3.8-Flash-TTS/Gemini-3.8-Flash-TTS_KIE.md +38 -0
- package/docs/model-adaptation/Gemini-Omni-1.2-Flash/Gemini-Omni-1.2-Flash_APIMart.md +79 -0
- package/docs/model-adaptation/Gemini-Omni-1.2-Flash/Gemini-Omni-1.2-Flash_Fal.md +60 -0
- package/docs/model-adaptation/Gemini-Omni-Flash/Gemini-Omni-Flash_APIMart.md +131 -125
- package/docs/model-adaptation/Gemini-Omni-Flash/Gemini-Omni-Flash_Fal.md +84 -84
- package/docs/model-adaptation/Gemini-Omni-Flash/Gemini-Omni-Flash_KIE.md +132 -130
- package/docs/model-adaptation/Grok-Imagine/Grok-Imagine_KIE.md +38 -36
- package/docs/model-adaptation/Grok-Imagine-2.0/Grok-Imagine-2.0_APIMart.md +250 -250
- package/docs/model-adaptation/Grok-Imagine-2.0/Grok-Imagine-2.0_Fal.md +84 -84
- package/docs/model-adaptation/Grok-Imagine-2.0/Grok-Imagine-2.0_KIE.md +105 -105
- package/docs/model-adaptation/Grok-Imagine-Video-1.5/Grok-Imagine-Video-1.5_APIMart.md +68 -0
- package/docs/model-adaptation/Grok-Imagine-Video-1.5/Grok-Imagine-Video-1.5_Fal.md +47 -0
- package/docs/model-adaptation/Grok-Imagine-Video-1.5/Grok-Imagine-Video-1.5_KIE.md +37 -0
- package/docs/model-adaptation/Hailuo-02/Hailuo-02_Fal.md +95 -93
- package/docs/model-adaptation/Hailuo-02/Hailuo-02_KIE.md +58 -56
- package/docs/model-adaptation/Hailuo-2.3/Hailuo-2.3_Fal.md +88 -88
- package/docs/model-adaptation/Hailuo-2.3/Hailuo-2.3_KIE.md +51 -51
- package/docs/model-adaptation/HappyHorse-1.1/HappyHorse-1.1_APIMart.md +66 -0
- package/docs/model-adaptation/HappyHorse-1.1/HappyHorse-1.1_KIE.md +31 -27
- package/docs/model-adaptation/IC-Light-v2/IC-Light-v2_Fal.md +99 -99
- package/docs/model-adaptation/Ideogram-/345/233/276/347/211/207/346/224/276/345/244/247/Ideogram-/345/233/276/347/211/207/346/224/276/345/244/247_Fal.md +41 -41
- package/docs/model-adaptation/Image-Apps-v2-/345/225/206/345/223/201/346/221/204/345/275/261/Image-Apps-v2-/345/225/206/345/223/201/346/221/204/345/275/261_Fal.md +72 -72
- package/docs/model-adaptation/Image-Apps-v2-/346/211/251/345/233/276/Image-Apps-v2-/346/211/251/345/233/276_Fal.md +93 -93
- package/docs/model-adaptation/Image-Apps-v2-/347/205/247/347/211/207/344/277/256/345/244/215/Image-Apps-v2-/347/205/247/347/211/207/344/277/256/345/244/215_Fal.md +86 -86
- package/docs/model-adaptation/Image-Apps-v2-/351/207/215/346/211/223/345/205/211/Image-Apps-v2-/351/207/215/346/211/223/345/205/211_Fal.md +84 -84
- package/docs/model-adaptation/Kling-3.0/Kling-3.0_APIMart.md +112 -112
- package/docs/model-adaptation/Kling-3.0/Kling-3.0_Fal.md +91 -89
- package/docs/model-adaptation/Kling-3.0/Kling-3.0_KIE.md +106 -106
- package/docs/model-adaptation/Kling-3.0/Kling-3.0_/346/264/276/346/254/247/344/272/221.md +120 -119
- package/docs/model-adaptation/Kling-3.0-Omni/Kling-3.0-Omni_APIMart.md +130 -125
- package/docs/model-adaptation/Kling-3.0-Omni/Kling-3.0-Omni_Fal.md +107 -107
- package/docs/model-adaptation/Kling-3.0-Omni/Kling-3.0-Omni_KIE.md +148 -143
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_APIMart.md +88 -85
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_Fal.md +86 -83
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_KIE.md +84 -84
- package/docs/model-adaptation/Kling-4.0/Kling-4.0_APIMart.md +76 -0
- package/docs/model-adaptation/Kling-4.0/Kling-4.0_Fal.md +115 -0
- package/docs/model-adaptation/Kling-4.0/Kling-4.0_KIE.md +61 -0
- package/docs/model-adaptation/Kling-4.0-Flash/Kling-4.0-Flash_Fal.md +55 -0
- package/docs/model-adaptation/Kling-4.0-Flash/Kling-4.0-Flash_KIE.md +33 -0
- package/docs/model-adaptation/LTX-2.3/LTX-2.3_Fal.md +121 -0
- package/docs/model-adaptation/Midjourney/Midjourney_APIMart.md +402 -396
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_APIMart.md +237 -234
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_Fal.md +112 -108
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_KIE.md +118 -111
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_/347/231/276/347/202/274.md +65 -0
- package/docs/model-adaptation/MiniMax-H3-Max/MiniMax-H3-Max_APIMart.md +78 -0
- package/docs/model-adaptation/MiniMax-H3-Max/MiniMax-H3-Max_Fal.md +62 -0
- package/docs/model-adaptation/MiniMax-Speech/MiniMax-Speech_/346/264/276/346/254/247/344/272/221.md +170 -170
- package/docs/model-adaptation/Nano-Banana-2/Nano-Banana-2_APIMart.md +89 -89
- package/docs/model-adaptation/Nano-Banana-2/Nano-Banana-2_Fal.md +99 -99
- package/docs/model-adaptation/Nano-Banana-2/Nano-Banana-2_Grsai.md +82 -82
- package/docs/model-adaptation/Nano-Banana-2/Nano-Banana-2_KIE.md +72 -70
- package/docs/model-adaptation/Nano-Banana-2-Lite/Nano-Banana-2-Lite_APIMart.md +79 -79
- package/docs/model-adaptation/Nano-Banana-2-Lite/Nano-Banana-2-Lite_Grsai.md +65 -65
- package/docs/model-adaptation/Nano-Banana-2-Lite/Nano-Banana-2-Lite_KIE.md +64 -64
- package/docs/model-adaptation/Nano-Banana-2.1/Nano-Banana-2.1_APIMart.md +35 -0
- package/docs/model-adaptation/Nano-Banana-2.1/Nano-Banana-2.1_Fal.md +37 -0
- package/docs/model-adaptation/Nano-Banana-2.1/Nano-Banana-2.1_Grsai.md +35 -0
- package/docs/model-adaptation/Nano-Banana-2.1/Nano-Banana-2.1_KIE.md +36 -0
- package/docs/model-adaptation/Nano-Banana-Pro/Nano-Banana-Pro_APIMart.md +83 -83
- package/docs/model-adaptation/Nano-Banana-Pro/Nano-Banana-Pro_Fal.md +89 -89
- package/docs/model-adaptation/Nano-Banana-Pro/Nano-Banana-Pro_Grsai.md +82 -82
- package/docs/model-adaptation/Nano-Banana-Pro/Nano-Banana-Pro_KIE.md +64 -64
- package/docs/model-adaptation/Pixelcut-/350/203/214/346/231/257/347/247/273/351/231/244/Pixelcut-/350/203/214/346/231/257/347/247/273/351/231/244_Fal.md +79 -79
- package/docs/model-adaptation/Qwen-Audio-3.1-TTS-Plus/Qwen-Audio-3.1-TTS-Plus_/347/231/276/347/202/274.md +59 -0
- package/docs/model-adaptation/Qwen-Image-3.0/Qwen-Image-3.0_APIMart.md +117 -117
- package/docs/model-adaptation/Qwen-Image-3.0/Qwen-Image-3.0_Fal.md +85 -84
- package/docs/model-adaptation/Qwen-Image-3.0/Qwen-Image-3.0_KIE.md +103 -103
- package/docs/model-adaptation/Qwen-Image-3.0/Qwen-Image-3.0_/347/231/276/347/202/274.md +138 -138
- package/docs/model-adaptation/Qwen-Image-Edit-2511-/345/244/232/350/247/222/345/272/246/Qwen-Image-Edit-2511-/345/244/232/350/247/222/345/272/246_Fal.md +57 -57
- package/docs/model-adaptation/Qwen-MT-Flash/Qwen-MT-Flash_/347/231/276/347/202/274.md +68 -68
- package/docs/model-adaptation/Qwen-MT-Lite/Qwen-MT-Lite_/347/231/276/347/202/274.md +40 -40
- package/docs/model-adaptation/Qwen-MT-Plus/Qwen-MT-Plus_/347/231/276/347/202/274.md +40 -40
- package/docs/model-adaptation/Qwen3-ASR-Flash/Qwen3-ASR-Flash_/347/231/276/347/202/274.md +44 -44
- package/docs/model-adaptation/Qwen3-ASR-Flash-2026-02-10/Qwen3-ASR-Flash-2026-02-10_/347/231/276/347/202/274.md +37 -37
- package/docs/model-adaptation/Qwen3-ASR-Flash-Filetrans/Qwen3-ASR-Flash-Filetrans_/347/231/276/347/202/274.md +45 -45
- package/docs/model-adaptation/Qwen3-ASR-Flash-Realtime/Qwen3-ASR-Flash-Realtime_/347/231/276/347/202/274.md +58 -58
- package/docs/model-adaptation/Qwen3-ASR-Flash-Realtime-2026-02-10/Qwen3-ASR-Flash-Realtime-2026-02-10_/347/231/276/347/202/274.md +37 -37
- package/docs/model-adaptation/README.md +379 -338
- package/docs/model-adaptation/Seed-ICL-2.0/Seed-ICL-2.0_/347/201/253/345/261/261/345/274/225/346/223/216.md +65 -65
- package/docs/model-adaptation/SeedASR-2.0-File/SeedASR-2.0-File_/347/201/253/345/261/261/345/274/225/346/223/216.md +115 -115
- package/docs/model-adaptation/SeedASR-2.0-Realtime/SeedASR-2.0-Realtime_/347/201/253/345/261/261/345/274/225/346/223/216.md +147 -147
- package/docs/model-adaptation/SeedVR2-/345/233/276/347/211/207/346/224/276/345/244/247/SeedVR2-/345/233/276/347/211/207/346/224/276/345/244/247_Fal.md +45 -45
- package/docs/model-adaptation/Seedance-2.0/Seedance-2.0_APIMart.md +121 -121
- package/docs/model-adaptation/Seedance-2.0/Seedance-2.0_Fal.md +97 -97
- package/docs/model-adaptation/Seedance-2.0/Seedance-2.0_KIE.md +87 -86
- package/docs/model-adaptation/Seedance-2.0/Seedance-2.0_/347/201/253/345/261/261/345/274/225/346/223/216.md +101 -0
- package/docs/model-adaptation/Seedance-2.0-Fast/Seedance-2.0-Fast_APIMart.md +89 -89
- package/docs/model-adaptation/Seedance-2.0-Fast/Seedance-2.0-Fast_Fal.md +95 -95
- package/docs/model-adaptation/Seedance-2.0-Fast/Seedance-2.0-Fast_KIE.md +79 -78
- package/docs/model-adaptation/Seedance-2.0-Fast/Seedance-2.0-Fast_/347/201/253/345/261/261/345/274/225/346/223/216.md +98 -0
- package/docs/model-adaptation/Seedance-2.0-Mini/Seedance-2.0-Mini_APIMart.md +93 -89
- package/docs/model-adaptation/Seedance-2.0-Mini/Seedance-2.0-Mini_Fal.md +96 -96
- package/docs/model-adaptation/Seedance-2.0-Mini/Seedance-2.0-Mini_KIE.md +79 -78
- package/docs/model-adaptation/Seedance-2.0-Mini/Seedance-2.0-Mini_/347/201/253/345/261/261/345/274/225/346/223/216.md +98 -0
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_APIMart.md +217 -212
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_Fal.md +98 -94
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_KIE.md +94 -89
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_/347/201/253/345/261/261/345/274/225/346/223/216.md +102 -0
- package/docs/model-adaptation/Seedream-5.0-Flash/Seedream-5.0-Flash_APIMart.md +64 -0
- package/docs/model-adaptation/Seedream-5.0-Flash/Seedream-5.0-Flash_/347/201/253/345/261/261/345/274/225/346/223/216.md +18 -18
- package/docs/model-adaptation/Seedream-5.0-Lite/Seedream-5.0-Lite_APIMart.md +113 -106
- package/docs/model-adaptation/Seedream-5.0-Lite/Seedream-5.0-Lite_Fal.md +91 -91
- package/docs/model-adaptation/Seedream-5.0-Lite/Seedream-5.0-Lite_KIE.md +89 -89
- package/docs/model-adaptation/Seedream-5.0-Lite/Seedream-5.0-Lite_/347/201/253/345/261/261/345/274/225/346/223/216.md +110 -108
- package/docs/model-adaptation/Seedream-5.0-Pro/Seedream-5.0-Pro_APIMart.md +194 -194
- package/docs/model-adaptation/Seedream-5.0-Pro/Seedream-5.0-Pro_Fal.md +100 -100
- package/docs/model-adaptation/Seedream-5.0-Pro/Seedream-5.0-Pro_KIE.md +141 -141
- package/docs/model-adaptation/Seedream-5.0-Pro/Seedream-5.0-Pro_/347/201/253/345/261/261/345/274/225/346/223/216.md +137 -137
- package/docs/model-adaptation/SenseVoiceSmall/SenseVoiceSmall_/347/241/205/345/237/272/346/265/201/345/212/250.md +73 -73
- package/docs/model-adaptation/TTS-/345/244/232/344/276/233/345/272/224/345/225/206-2026-09.md +115 -69
- package/docs/model-adaptation/TTS-/346/227/266/351/227/264/346/210/263-2026-10.md +36 -0
- package/docs/model-adaptation/Topaz-/345/233/276/347/211/207/346/224/276/345/244/247/Topaz-/345/233/276/347/211/207/346/224/276/345/244/247_Fal.md +87 -87
- package/docs/model-adaptation/Topaz-/351/200/217/346/230/216/345/233/276/346/224/276/345/244/247/Topaz-/351/200/217/346/230/216/345/233/276/346/224/276/345/244/247_Fal.md +34 -34
- package/docs/model-adaptation/Veo-3.1/Veo-3.1_APIMart.md +90 -0
- package/docs/model-adaptation/Wan-2.7-Image/Wan-2.7-Image_APIMart.md +81 -0
- package/docs/model-adaptation/Wan-3.0/Wan-3.0_APIMart.md +74 -0
- package/docs/model-adaptation/Wan-3.0/Wan-3.0_Fal.md +60 -0
- package/docs/model-adaptation/Wan-3.0/Wan-3.0_Grsai.md +35 -0
- package/docs/model-adaptation/Wan-3.0/Wan-3.0_KIE.md +38 -0
- package/docs/model-adaptation/Wan-3.0/Wan-3.0_/347/231/276/347/202/274.md +96 -0
- package/docs/model-adaptation/Wan-3.0-Prime/Wan-3.0-Prime_KIE.md +20 -0
- package/docs/model-adaptation/Whisper-Large-v3/Whisper-Large-v3_Groq.md +80 -80
- package/docs/model-adaptation/Whisper-Large-v3-Turbo/Whisper-Large-v3-Turbo_Groq.md +79 -79
- package/docs/model-adaptation/Z-Image-Turbo/Z-Image-Turbo_APIMart.md +88 -88
- package/docs/model-adaptation/Z-Image-Turbo/Z-Image-Turbo_Fal.md +103 -95
- package/docs/model-adaptation/Z-Image-Turbo/Z-Image-Turbo_KIE.md +71 -71
- package/docs/model-adaptation/Z-Image-Turbo/Z-Image-Turbo_/347/231/276/347/202/274.md +122 -122
- package/docs/model-adaptation/Z-Image-Turbo/Z-Image-Turbo_/351/255/224/346/220/255.md +99 -97
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/APIMart.md +240 -240
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/Fal.md +190 -172
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/Groq.md +136 -121
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/Grsai.md +217 -217
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/KIE.md +159 -131
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//345/200/231/351/200/211/344/276/233/345/272/224/345/225/206/350/260/203/347/240/224-/345/233/276/347/211/207/345/267/245/345/205/267.md +151 -151
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//345/277/253/351/200/237/351/200/202/351/205/215/344/276/233/345/272/224/345/225/206.md +65 -65
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//346/264/276/346/254/247/344/272/221.md +170 -147
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//347/201/253/345/261/261/345/274/225/346/223/216.md +191 -183
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//347/231/276/347/202/274.md +339 -288
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//347/241/205/345/237/272/346/265/201/345/212/250.md +180 -153
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//351/255/224/346/220/255.md +205 -207
- package/docs/model-adaptation//346/226/207/346/241/243/351/207/207/351/233/206/346/211/213/345/206/214.md +339 -339
- package/docs/model-adaptation//351/200/217/350/247/206/345/217/230/346/215/242//351/200/217/350/247/206/345/217/230/346/215/242_Fal.md +59 -59
- package/docs//346/216/245/345/205/245/346/214/207/345/215/227/Electron.md +77 -77
- package/docs//346/216/245/345/205/245/346/214/207/345/215/227/Tauri.md +81 -81
- package/docs//346/216/245/345/205/245/346/214/207/345/215/227/UXP.md +169 -169
- package/docs//346/216/245/345/205/245/346/214/207/345/215/227//344/276/233/345/272/224/345/225/206/345/237/237/345/220/215.md +83 -83
- package/docs//346/216/245/345/205/245/346/214/207/345/215/227//351/224/231/350/257/257/345/244/204/347/220/206.md +72 -72
- package/examples/form-renderer/README.md +17 -17
- package/examples/form-renderer/cli.ts +32 -32
- package/examples/form-renderer/index.ts +144 -144
- package/examples/form-renderer/package.json +16 -16
- package/examples/form-renderer/tsconfig.json +14 -14
- package/examples/llm-chat/README.md +38 -38
- package/examples/llm-chat/index.ts +100 -100
- package/examples/llm-chat/package.json +19 -19
- package/examples/llm-chat/tsconfig.json +14 -14
- package/examples/minimal-node/README.md +31 -31
- package/examples/minimal-node/index.ts +138 -138
- package/examples/minimal-node/package.json +17 -17
- package/examples/minimal-node/tsconfig.json +14 -14
- package/package.json +259 -258
- package/dist/catalog/grsai/gptImage25Sizes.d.ts +0 -1
- package/dist/catalog/grsai/gptImage25Sizes.js +0 -76
- package/dist/catalog/kie/eleven-turbo-2.5-tts.model.d.ts +0 -2
- package/dist/catalog/kie/eleven-turbo-2.5-tts.model.js +0 -29
- package/dist/catalog/modelscope/qwen-image-edit-2509.model.d.ts +0 -5
- package/dist/catalog/modelscope/qwen-image.model.d.ts +0 -5
- package/dist/catalog/ppio/minimax-hailuo-2.3.model.d.ts +0 -7
- package/dist/catalog/ppio/minimax-hailuo-2.3.model.js +0 -114
- package/dist/catalog/ppio/wan-2.5-preview.model.d.ts +0 -7
- package/dist/catalog/ppio/wan-2.5-preview.model.js +0 -198
- package/dist/catalog/ppio/wan-2.6.model.d.ts +0 -7
- package/dist/catalog/ppio/wan-2.6.model.js +0 -206
- package/dist/catalog/ppio/wan-2.7.model.d.ts +0 -2
- package/dist/catalog/ppio/wan-2.7.model.js +0 -373
- package/docs/model-adaptation/Hailuo-2.3/Hailuo-2.3_/346/264/276/346/254/247/344/272/221.md +0 -70
- package/docs/model-adaptation/TeleSpeechASR/TeleSpeechASR_/347/241/205/345/237/272/346/265/201/345/212/250.md +0 -76
- package/docs/model-adaptation/Wan-2.5-Preview/Wan-2.5-Preview_/346/264/276/346/254/247/344/272/221.md +0 -82
- package/docs/model-adaptation/Wan-2.6/Wan-2.6_/346/264/276/346/254/247/344/272/221.md +0 -84
- package/docs/model-adaptation/Wan-2.7/Wan-2.7_/346/264/276/346/254/247/344/272/221.md +0 -122
- /package/dist/upload/{fal-legacy.d.ts → fal-host-fetch.d.ts} +0 -0
|
@@ -1,147 +1,147 @@
|
|
|
1
|
-
# SeedASR 2.0 Realtime · 火山引擎
|
|
2
|
-
|
|
3
|
-
| 项目 | 内容 |
|
|
4
|
-
|---|---|
|
|
5
|
-
| 最后更新 | 2026-09-24 |
|
|
6
|
-
| 能力 | 双向实时语音识别(二进制 WebSocket) |
|
|
7
|
-
| SDK `modelId` | `seedasr-2.0-realtime` |
|
|
8
|
-
| 火山请求模型 | `request.model_name="bigmodel"` + 2.0 资源 ID `volc.seedasr.sauc.duration` |
|
|
9
|
-
| P0 音频 | PCM S16LE、16 kHz、16 bit、单声道 |
|
|
10
|
-
| 文档/价格 | 公开;API Key、开通和用量需登录 |
|
|
11
|
-
|
|
12
|
-
## 1. 端点与新版鉴权
|
|
13
|
-
|
|
14
|
-
P0 使用官方双向流式优化端点:
|
|
15
|
-
|
|
16
|
-
```text
|
|
17
|
-
wss://openspeech.bytedance.com/api/v3/sauc/bigmodel_async
|
|
18
|
-
```
|
|
19
|
-
|
|
20
|
-
握手头:
|
|
21
|
-
|
|
22
|
-
```text
|
|
23
|
-
X-Api-Key: <API Key>
|
|
24
|
-
X-Api-Resource-Id: volc.seedasr.sauc.duration
|
|
25
|
-
X-Api-Request-Id: <客户端生成的 UUID>
|
|
26
|
-
X-Api-Sequence: -1
|
|
27
|
-
```
|
|
28
|
-
|
|
29
|
-
只支持新版 `X-Api-Key`。同一官方页面同时列出 1.0 的 `volc.bigasr.sauc.*` 与 2.0 的 `volc.seedasr.sauc.*`;本模型固定 2.0 小时版资源 ID。并发版 `volc.seedasr.sauc.concurrent` 属于另一计费形态,不在 P0 中静默切换。
|
|
30
|
-
|
|
31
|
-
## 2. 首帧与音频规格
|
|
32
|
-
|
|
33
|
-
首帧 JSON 经 UTF-8 + gzip 后装入二进制帧:
|
|
34
|
-
|
|
35
|
-
```json
|
|
36
|
-
{
|
|
37
|
-
"user": { "uid": "<request UUID>" },
|
|
38
|
-
"audio": {
|
|
39
|
-
"format": "pcm",
|
|
40
|
-
"codec": "raw",
|
|
41
|
-
"rate": 16000,
|
|
42
|
-
"bits": 16,
|
|
43
|
-
"channel": 1
|
|
44
|
-
},
|
|
45
|
-
"request": {
|
|
46
|
-
"model_name": "bigmodel",
|
|
47
|
-
"enable_itn": true,
|
|
48
|
-
"enable_punc": true,
|
|
49
|
-
"enable_ddc": false,
|
|
50
|
-
"show_utterances": true,
|
|
51
|
-
"enable_nonstream": false,
|
|
52
|
-
"result_type": "full"
|
|
53
|
-
}
|
|
54
|
-
}
|
|
55
|
-
```
|
|
56
|
-
|
|
57
|
-
P0 不在 SDK 内转码:输入不符合 PCM S16LE/16 kHz/mono 时,在建立付费连接前失败。每个 PCM16 音频块的字节数必须为偶数。官方示例建议每 200 ms 一包,即 6400 字节;分块节奏由宿主负责。
|
|
58
|
-
|
|
59
|
-
`bigmodel_async` 当前契约不发送 `audio.language`;传入 `language` 或热词 `hints` 会明确报不支持,避免静默丢参数。
|
|
60
|
-
|
|
61
|
-
## 3. 二进制帧契约
|
|
62
|
-
|
|
63
|
-
### 3.1 4 字节头
|
|
64
|
-
|
|
65
|
-
| 位置 | 高 4 bit | 低 4 bit |
|
|
66
|
-
|---|---|---|
|
|
67
|
-
| byte 0 | version=`1` | header size=`1`(4 字节) |
|
|
68
|
-
| byte 1 | message type | flags |
|
|
69
|
-
| byte 2 | serialization | compression |
|
|
70
|
-
| byte 3 | reserved | reserved |
|
|
71
|
-
|
|
72
|
-
消息与标志:
|
|
73
|
-
|
|
74
|
-
| 值 | 含义 |
|
|
75
|
-
|---|---|
|
|
76
|
-
| message type `1` | client full request |
|
|
77
|
-
| message type `2` | client audio-only request |
|
|
78
|
-
| message type `9` | server full response |
|
|
79
|
-
| message type `15` | server error response |
|
|
80
|
-
| flag bit `1` | 帧含 4 字节大端有符号 sequence |
|
|
81
|
-
| flag bit `2` | 最后一包 |
|
|
82
|
-
| flag bit `4` | 帧含 4 字节大端 event |
|
|
83
|
-
| serialization `0/1` | none / JSON |
|
|
84
|
-
| compression `0/1` | none / gzip |
|
|
85
|
-
|
|
86
|
-
完整响应布局为 `header → [sequence] → [event] → uint32 payload_size → payload`;错误响应为 `header → [sequence] → [event] → uint32 error_code → uint32 payload_size → payload`。解析器要求声明长度与实际剩余字节完全一致,断牙和尾随字节都报 `invalid_response`。服务端 payload 同时接受 `compression=none/gzip`,其他压缩或序列化值拒绝。
|
|
87
|
-
|
|
88
|
-
### 3.2 当前官方附件的客户端帧
|
|
89
|
-
|
|
90
|
-
| 帧 | 头 hex | sequence | payload |
|
|
91
|
-
|---|---|---|---|
|
|
92
|
-
| 首帧 | `11 11 11 00` | `1` | JSON UTF-8 + gzip |
|
|
93
|
-
| 普通音频 | `11 21 11 00` | 正数,从 `2` 递增 | 原始 PCM + gzip |
|
|
94
|
-
| 最后一块真实音频 | `11 23 11 00` | 当前序号取负数 | 原始 PCM + gzip |
|
|
95
|
-
|
|
96
|
-
协议字段表把原始音频描述为 `serialization=none`,但 2026-08-08 当前官方 Python 附件对音频帧实际写入 `serialization=JSON` 标志(第三字节 `0x11`),附件自带成功 `run.log` 也使用这一结构。P0 以可复现的当前官方附件为准锁定 `0x11`;这是已记录的官方资料内部差异,后续若官方修正文档或附件需重新验证,而不是同时猜两套发送协议。
|
|
97
|
-
|
|
98
|
-
SDK 对音频保留一块延迟:收到下一块时才把上一块以正 sequence 发出;`finish()` 把最后一块真实音频以负 sequence 发送。不会制造空终止音频包。无任何真实音频就 `finish()` 会报 `invalid_audio`。
|
|
99
|
-
|
|
100
|
-
## 4. 服务端事件矩阵
|
|
101
|
-
|
|
102
|
-
| 服务端帧/字段 | Capability 事件 | 终态 | 行为 |
|
|
103
|
-
|---|---|---|---|
|
|
104
|
-
| 首个合法 type `9` full response | `started` | 否 | 官方附件该帧 `result.text=""`;SDK 不要求必须为空,也不产生空 partial |
|
|
105
|
-
| type `9`,非空 `result.text` | `partial` | 否 | 文本变化才发,重复内容去重 |
|
|
106
|
-
| `result.utterances[].definite=true` | `final` | 否 | 表示句段已确定,不等于整个连接结束;按时间范围/文本去重 |
|
|
107
|
-
| flag bit `2`(last) | `completed` | 是 | 只有客户端已 `finish()` 后才合法;输出 `result.text/utterances/audio_info.duration` |
|
|
108
|
-
| type `15` | 无 | 是(错误) | 读取 uint32 错误码;错误 payload 可为 JSON 或 UTF-8 文本,默认异常/日志只保留错误码,不带原始 message |
|
|
109
|
-
| 未知 `event` 数字 | 无 | 否 | 只记脱敏 warning,仍按 type/payload 处理 |
|
|
110
|
-
| WebSocket 提前断开 | 无 | 是(错误) | `provider_connection_closed`,不误报完成 |
|
|
111
|
-
| text WebSocket frame | 无 | 是(错误) | 协议要求二进制,报 `invalid_response` |
|
|
112
|
-
|
|
113
|
-
`utterances[].definite=true` 只能判断句段 final,整个会话终态必须看帧头 last 标志。整个终帧仍无有效文本时严格报 `invalid_response`。
|
|
114
|
-
|
|
115
|
-
用户主动取消只关闭连接,不发送负 sequence 终帧,也不把取消伪装成正常完成。full request 默认在 15 秒内必须收到首个服务端响应,可用 `openTimeoutMs` 显式调整;超时会关闭半开连接。`finish()`、连接释放和显式 `close()` 都幂等;发送失败、服务端错误、断线、超时和取消都走同一个释放边界。
|
|
116
|
-
|
|
117
|
-
同一响应帧可能同时产生 partial 与一个或多个 final。每次事件回调后重新检查取消/关闭,避免调用方在 partial 回调取消后,SDK 仍继续发出该帧的 final;该场景使用官方响应 payload 调整 last 标志构造,不代表新的供应商事件类型。
|
|
118
|
-
|
|
119
|
-
2026-09-24 诊断复核:异常 details 保留实际 `modelId=seedasr-2.0-realtime`、`protocol=volcengine-binary-v1`、会话阶段、操作与最后一帧的序号/event/last 标志。原始服务端 message 和宿主异常可能包含识别内容或凭据,不进入默认诊断。握手失败后若关闭也失败,继续报告首个故障,并附 `cleanupFailed=true`。`volcengine-realtime-asr.test.ts` 使用既有官方帧结构、受控敏感文本错误与 Mock close 拒绝验证这些边界;不是额外真实服务实录。
|
|
120
|
-
|
|
121
|
-
## 5. 价格与免费额度
|
|
122
|
-
|
|
123
|
-
| 项目 | 官方公开值 |
|
|
124
|
-
|---|---|
|
|
125
|
-
| 后付费(小时版) | 1 元/小时 |
|
|
126
|
-
| 免费试用 | 20 小时 |
|
|
127
|
-
| 有效期 | 开通后 6 个月 |
|
|
128
|
-
|
|
129
|
-
20 小时为需在豆包语音控制台开通的试用额度,不是每月自动刷新。并发版的资源与计费方式不同,不应把本页小时版单价套到并发版。
|
|
130
|
-
|
|
131
|
-
## 6. Fixture 与验证来源
|
|
132
|
-
|
|
133
|
-
| Fixture | 分类 | 用途 |
|
|
134
|
-
|---|---|---|
|
|
135
|
-
| `asr-seedasr-official.json` | `official-redacted` | 官方附件成功 `run.log` 的握手/空进度/终帧;仅 `log_id` 脱敏 |
|
|
136
|
-
| `asr-seedasr-field-construction.json` | `field-construction` | 按官方当前附件构造三类客户端帧与首帧字段 |
|
|
137
|
-
| `asr-seedasr-synthetic.json` | `synthetic-negative` | 未知 event、错误码、断牙/尾随字节等负例 |
|
|
138
|
-
|
|
139
|
-
## 7. 原始链接索引
|
|
140
|
-
|
|
141
|
-
| 信息 | 链接 | 登录 |
|
|
142
|
-
|---|---|---|
|
|
143
|
-
| 流式 API/二进制协议 | https://docs.volcengine.com/docs/6561/1354869?lang=zh | 否 |
|
|
144
|
-
| 双向流式优化端点与当前附件 | https://docs.volcengine.com/docs/6561/2630027?lang=zh | 否 |
|
|
145
|
-
| 流式调用示例/资源 ID | https://docs.volcengine.com/docs/6561/2628951?lang=zh | 否 |
|
|
146
|
-
| 计费与免费试用 | https://docs.volcengine.com/docs/6561/1359369?lang=zh | 否 |
|
|
147
|
-
| 豆包语音控制台 | https://console.volcengine.com/speech/new/overview | **是** |
|
|
1
|
+
# SeedASR 2.0 Realtime · 火山引擎
|
|
2
|
+
|
|
3
|
+
| 项目 | 内容 |
|
|
4
|
+
|---|---|
|
|
5
|
+
| 最后更新 | 2026-09-24 |
|
|
6
|
+
| 能力 | 双向实时语音识别(二进制 WebSocket) |
|
|
7
|
+
| SDK `modelId` | `seedasr-2.0-realtime` |
|
|
8
|
+
| 火山请求模型 | `request.model_name="bigmodel"` + 2.0 资源 ID `volc.seedasr.sauc.duration` |
|
|
9
|
+
| P0 音频 | PCM S16LE、16 kHz、16 bit、单声道 |
|
|
10
|
+
| 文档/价格 | 公开;API Key、开通和用量需登录 |
|
|
11
|
+
|
|
12
|
+
## 1. 端点与新版鉴权
|
|
13
|
+
|
|
14
|
+
P0 使用官方双向流式优化端点:
|
|
15
|
+
|
|
16
|
+
```text
|
|
17
|
+
wss://openspeech.bytedance.com/api/v3/sauc/bigmodel_async
|
|
18
|
+
```
|
|
19
|
+
|
|
20
|
+
握手头:
|
|
21
|
+
|
|
22
|
+
```text
|
|
23
|
+
X-Api-Key: <API Key>
|
|
24
|
+
X-Api-Resource-Id: volc.seedasr.sauc.duration
|
|
25
|
+
X-Api-Request-Id: <客户端生成的 UUID>
|
|
26
|
+
X-Api-Sequence: -1
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
只支持新版 `X-Api-Key`。同一官方页面同时列出 1.0 的 `volc.bigasr.sauc.*` 与 2.0 的 `volc.seedasr.sauc.*`;本模型固定 2.0 小时版资源 ID。并发版 `volc.seedasr.sauc.concurrent` 属于另一计费形态,不在 P0 中静默切换。
|
|
30
|
+
|
|
31
|
+
## 2. 首帧与音频规格
|
|
32
|
+
|
|
33
|
+
首帧 JSON 经 UTF-8 + gzip 后装入二进制帧:
|
|
34
|
+
|
|
35
|
+
```json
|
|
36
|
+
{
|
|
37
|
+
"user": { "uid": "<request UUID>" },
|
|
38
|
+
"audio": {
|
|
39
|
+
"format": "pcm",
|
|
40
|
+
"codec": "raw",
|
|
41
|
+
"rate": 16000,
|
|
42
|
+
"bits": 16,
|
|
43
|
+
"channel": 1
|
|
44
|
+
},
|
|
45
|
+
"request": {
|
|
46
|
+
"model_name": "bigmodel",
|
|
47
|
+
"enable_itn": true,
|
|
48
|
+
"enable_punc": true,
|
|
49
|
+
"enable_ddc": false,
|
|
50
|
+
"show_utterances": true,
|
|
51
|
+
"enable_nonstream": false,
|
|
52
|
+
"result_type": "full"
|
|
53
|
+
}
|
|
54
|
+
}
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
P0 不在 SDK 内转码:输入不符合 PCM S16LE/16 kHz/mono 时,在建立付费连接前失败。每个 PCM16 音频块的字节数必须为偶数。官方示例建议每 200 ms 一包,即 6400 字节;分块节奏由宿主负责。
|
|
58
|
+
|
|
59
|
+
`bigmodel_async` 当前契约不发送 `audio.language`;传入 `language` 或热词 `hints` 会明确报不支持,避免静默丢参数。
|
|
60
|
+
|
|
61
|
+
## 3. 二进制帧契约
|
|
62
|
+
|
|
63
|
+
### 3.1 4 字节头
|
|
64
|
+
|
|
65
|
+
| 位置 | 高 4 bit | 低 4 bit |
|
|
66
|
+
|---|---|---|
|
|
67
|
+
| byte 0 | version=`1` | header size=`1`(4 字节) |
|
|
68
|
+
| byte 1 | message type | flags |
|
|
69
|
+
| byte 2 | serialization | compression |
|
|
70
|
+
| byte 3 | reserved | reserved |
|
|
71
|
+
|
|
72
|
+
消息与标志:
|
|
73
|
+
|
|
74
|
+
| 值 | 含义 |
|
|
75
|
+
|---|---|
|
|
76
|
+
| message type `1` | client full request |
|
|
77
|
+
| message type `2` | client audio-only request |
|
|
78
|
+
| message type `9` | server full response |
|
|
79
|
+
| message type `15` | server error response |
|
|
80
|
+
| flag bit `1` | 帧含 4 字节大端有符号 sequence |
|
|
81
|
+
| flag bit `2` | 最后一包 |
|
|
82
|
+
| flag bit `4` | 帧含 4 字节大端 event |
|
|
83
|
+
| serialization `0/1` | none / JSON |
|
|
84
|
+
| compression `0/1` | none / gzip |
|
|
85
|
+
|
|
86
|
+
完整响应布局为 `header → [sequence] → [event] → uint32 payload_size → payload`;错误响应为 `header → [sequence] → [event] → uint32 error_code → uint32 payload_size → payload`。解析器要求声明长度与实际剩余字节完全一致,断牙和尾随字节都报 `invalid_response`。服务端 payload 同时接受 `compression=none/gzip`,其他压缩或序列化值拒绝。
|
|
87
|
+
|
|
88
|
+
### 3.2 当前官方附件的客户端帧
|
|
89
|
+
|
|
90
|
+
| 帧 | 头 hex | sequence | payload |
|
|
91
|
+
|---|---|---|---|
|
|
92
|
+
| 首帧 | `11 11 11 00` | `1` | JSON UTF-8 + gzip |
|
|
93
|
+
| 普通音频 | `11 21 11 00` | 正数,从 `2` 递增 | 原始 PCM + gzip |
|
|
94
|
+
| 最后一块真实音频 | `11 23 11 00` | 当前序号取负数 | 原始 PCM + gzip |
|
|
95
|
+
|
|
96
|
+
协议字段表把原始音频描述为 `serialization=none`,但 2026-08-08 当前官方 Python 附件对音频帧实际写入 `serialization=JSON` 标志(第三字节 `0x11`),附件自带成功 `run.log` 也使用这一结构。P0 以可复现的当前官方附件为准锁定 `0x11`;这是已记录的官方资料内部差异,后续若官方修正文档或附件需重新验证,而不是同时猜两套发送协议。
|
|
97
|
+
|
|
98
|
+
SDK 对音频保留一块延迟:收到下一块时才把上一块以正 sequence 发出;`finish()` 把最后一块真实音频以负 sequence 发送。不会制造空终止音频包。无任何真实音频就 `finish()` 会报 `invalid_audio`。
|
|
99
|
+
|
|
100
|
+
## 4. 服务端事件矩阵
|
|
101
|
+
|
|
102
|
+
| 服务端帧/字段 | Capability 事件 | 终态 | 行为 |
|
|
103
|
+
|---|---|---|---|
|
|
104
|
+
| 首个合法 type `9` full response | `started` | 否 | 官方附件该帧 `result.text=""`;SDK 不要求必须为空,也不产生空 partial |
|
|
105
|
+
| type `9`,非空 `result.text` | `partial` | 否 | 文本变化才发,重复内容去重 |
|
|
106
|
+
| `result.utterances[].definite=true` | `final` | 否 | 表示句段已确定,不等于整个连接结束;按时间范围/文本去重 |
|
|
107
|
+
| flag bit `2`(last) | `completed` | 是 | 只有客户端已 `finish()` 后才合法;输出 `result.text/utterances/audio_info.duration` |
|
|
108
|
+
| type `15` | 无 | 是(错误) | 读取 uint32 错误码;错误 payload 可为 JSON 或 UTF-8 文本,默认异常/日志只保留错误码,不带原始 message |
|
|
109
|
+
| 未知 `event` 数字 | 无 | 否 | 只记脱敏 warning,仍按 type/payload 处理 |
|
|
110
|
+
| WebSocket 提前断开 | 无 | 是(错误) | `provider_connection_closed`,不误报完成 |
|
|
111
|
+
| text WebSocket frame | 无 | 是(错误) | 协议要求二进制,报 `invalid_response` |
|
|
112
|
+
|
|
113
|
+
`utterances[].definite=true` 只能判断句段 final,整个会话终态必须看帧头 last 标志。整个终帧仍无有效文本时严格报 `invalid_response`。
|
|
114
|
+
|
|
115
|
+
用户主动取消只关闭连接,不发送负 sequence 终帧,也不把取消伪装成正常完成。full request 默认在 15 秒内必须收到首个服务端响应,可用 `openTimeoutMs` 显式调整;超时会关闭半开连接。`finish()`、连接释放和显式 `close()` 都幂等;发送失败、服务端错误、断线、超时和取消都走同一个释放边界。
|
|
116
|
+
|
|
117
|
+
同一响应帧可能同时产生 partial 与一个或多个 final。每次事件回调后重新检查取消/关闭,避免调用方在 partial 回调取消后,SDK 仍继续发出该帧的 final;该场景使用官方响应 payload 调整 last 标志构造,不代表新的供应商事件类型。
|
|
118
|
+
|
|
119
|
+
2026-09-24 诊断复核:异常 details 保留实际 `modelId=seedasr-2.0-realtime`、`protocol=volcengine-binary-v1`、会话阶段、操作与最后一帧的序号/event/last 标志。原始服务端 message 和宿主异常可能包含识别内容或凭据,不进入默认诊断。握手失败后若关闭也失败,继续报告首个故障,并附 `cleanupFailed=true`。`volcengine-realtime-asr.test.ts` 使用既有官方帧结构、受控敏感文本错误与 Mock close 拒绝验证这些边界;不是额外真实服务实录。
|
|
120
|
+
|
|
121
|
+
## 5. 价格与免费额度
|
|
122
|
+
|
|
123
|
+
| 项目 | 官方公开值 |
|
|
124
|
+
|---|---|
|
|
125
|
+
| 后付费(小时版) | 1 元/小时 |
|
|
126
|
+
| 免费试用 | 20 小时 |
|
|
127
|
+
| 有效期 | 开通后 6 个月 |
|
|
128
|
+
|
|
129
|
+
20 小时为需在豆包语音控制台开通的试用额度,不是每月自动刷新。并发版的资源与计费方式不同,不应把本页小时版单价套到并发版。
|
|
130
|
+
|
|
131
|
+
## 6. Fixture 与验证来源
|
|
132
|
+
|
|
133
|
+
| Fixture | 分类 | 用途 |
|
|
134
|
+
|---|---|---|
|
|
135
|
+
| `asr-seedasr-official.json` | `official-redacted` | 官方附件成功 `run.log` 的握手/空进度/终帧;仅 `log_id` 脱敏 |
|
|
136
|
+
| `asr-seedasr-field-construction.json` | `field-construction` | 按官方当前附件构造三类客户端帧与首帧字段 |
|
|
137
|
+
| `asr-seedasr-synthetic.json` | `synthetic-negative` | 未知 event、错误码、断牙/尾随字节等负例 |
|
|
138
|
+
|
|
139
|
+
## 7. 原始链接索引
|
|
140
|
+
|
|
141
|
+
| 信息 | 链接 | 登录 |
|
|
142
|
+
|---|---|---|
|
|
143
|
+
| 流式 API/二进制协议 | https://docs.volcengine.com/docs/6561/1354869?lang=zh | 否 |
|
|
144
|
+
| 双向流式优化端点与当前附件 | https://docs.volcengine.com/docs/6561/2630027?lang=zh | 否 |
|
|
145
|
+
| 流式调用示例/资源 ID | https://docs.volcengine.com/docs/6561/2628951?lang=zh | 否 |
|
|
146
|
+
| 计费与免费试用 | https://docs.volcengine.com/docs/6561/1359369?lang=zh | 否 |
|
|
147
|
+
| 豆包语音控制台 | https://console.volcengine.com/speech/new/overview | **是** |
|
|
@@ -1,45 +1,45 @@
|
|
|
1
|
-
# SeedVR2 图片放大(Fal)
|
|
2
|
-
|
|
3
|
-
## 契约
|
|
4
|
-
|
|
5
|
-
| 项目 | 内容 |
|
|
6
|
-
|---|---|
|
|
7
|
-
| endpoint ID | `fal-ai/seedvr/upscale/image` |
|
|
8
|
-
| 输入 | `image_url`,应用严格要求 1 张图片 |
|
|
9
|
-
| 官方模式 | `factor` 或 `target`;应用只开放 factor 模式 |
|
|
10
|
-
| 应用参数 | 2×/4×、`noise_scale` 0~1(默认 0.1) |
|
|
11
|
-
| 隐藏字段 | `seed`、`output_format`、`sync_mode`、target resolution |
|
|
12
|
-
| 输出 | `image: File` |
|
|
13
|
-
| 价格 | Fal 标价 `$0.001/MP` |
|
|
14
|
-
| 资料核查 | 2026-08-29;公开,无需登录 |
|
|
15
|
-
|
|
16
|
-
官方价格只标明 megapixels billing unit,没有在公开页明确它指输入还是输出。应用采用“预计输出 MP ×
|
|
17
|
-
$0.001”的保守展示口径,并在价格文案中明确这是估价;SDK 通过 `pricing.mediaContext` 声明源图像素与
|
|
18
|
-
2×/4× 面积倍率,宿主共享价格层统一读取媒体指标。指标未解析成功时不显示伪造兜底价;实际账单仍以
|
|
19
|
-
Fal billing event 为准。
|
|
20
|
-
|
|
21
|
-
## 请求示例
|
|
22
|
-
|
|
23
|
-
```json
|
|
24
|
-
{
|
|
25
|
-
"image_url": "https://example.com/source.jpg",
|
|
26
|
-
"upscale_mode": "factor",
|
|
27
|
-
"upscale_factor": 4,
|
|
28
|
-
"noise_scale": 0.1
|
|
29
|
-
}
|
|
30
|
-
```
|
|
31
|
-
|
|
32
|
-
## 队列与适配
|
|
33
|
-
|
|
34
|
-
使用 `Authorization: Key <FAL_KEY>` 调用 `https://queue.fal.run`,状态为 `IN_QUEUE`、
|
|
35
|
-
`IN_PROGRESS`、`COMPLETED`。canonical ID 为 `seedvr2-image-upscale`,应用模型 ID 为
|
|
36
|
-
`fal-ai-seedvr2-image-upscale`。默认 JPG 输出不保证 alpha,因此画布预检会提示透明图改用专用模型。
|
|
37
|
-
已完成端点、字段钳制、单图限制、2×/4×预检和输出 MP 估价的离线测试;未执行真实付费生成。
|
|
38
|
-
|
|
39
|
-
## 一手资料
|
|
40
|
-
|
|
41
|
-
| 信息 | 链接 | 登录 |
|
|
42
|
-
|---|---|---|
|
|
43
|
-
| API 文档 | https://fal.ai/models/fal-ai/seedvr/upscale/image/api | 否 |
|
|
44
|
-
| OpenAPI | https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/seedvr/upscale/image | 否 |
|
|
45
|
-
| API Key | https://fal.ai/dashboard/keys | 是 |
|
|
1
|
+
# SeedVR2 图片放大(Fal)
|
|
2
|
+
|
|
3
|
+
## 契约
|
|
4
|
+
|
|
5
|
+
| 项目 | 内容 |
|
|
6
|
+
|---|---|
|
|
7
|
+
| endpoint ID | `fal-ai/seedvr/upscale/image` |
|
|
8
|
+
| 输入 | `image_url`,应用严格要求 1 张图片 |
|
|
9
|
+
| 官方模式 | `factor` 或 `target`;应用只开放 factor 模式 |
|
|
10
|
+
| 应用参数 | 2×/4×、`noise_scale` 0~1(默认 0.1) |
|
|
11
|
+
| 隐藏字段 | `seed`、`output_format`、`sync_mode`、target resolution |
|
|
12
|
+
| 输出 | `image: File` |
|
|
13
|
+
| 价格 | Fal 标价 `$0.001/MP` |
|
|
14
|
+
| 资料核查 | 2026-08-29;公开,无需登录 |
|
|
15
|
+
|
|
16
|
+
官方价格只标明 megapixels billing unit,没有在公开页明确它指输入还是输出。应用采用“预计输出 MP ×
|
|
17
|
+
$0.001”的保守展示口径,并在价格文案中明确这是估价;SDK 通过 `pricing.mediaContext` 声明源图像素与
|
|
18
|
+
2×/4× 面积倍率,宿主共享价格层统一读取媒体指标。指标未解析成功时不显示伪造兜底价;实际账单仍以
|
|
19
|
+
Fal billing event 为准。
|
|
20
|
+
|
|
21
|
+
## 请求示例
|
|
22
|
+
|
|
23
|
+
```json
|
|
24
|
+
{
|
|
25
|
+
"image_url": "https://example.com/source.jpg",
|
|
26
|
+
"upscale_mode": "factor",
|
|
27
|
+
"upscale_factor": 4,
|
|
28
|
+
"noise_scale": 0.1
|
|
29
|
+
}
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
## 队列与适配
|
|
33
|
+
|
|
34
|
+
使用 `Authorization: Key <FAL_KEY>` 调用 `https://queue.fal.run`,状态为 `IN_QUEUE`、
|
|
35
|
+
`IN_PROGRESS`、`COMPLETED`。canonical ID 为 `seedvr2-image-upscale`,应用模型 ID 为
|
|
36
|
+
`fal-ai-seedvr2-image-upscale`。默认 JPG 输出不保证 alpha,因此画布预检会提示透明图改用专用模型。
|
|
37
|
+
已完成端点、字段钳制、单图限制、2×/4×预检和输出 MP 估价的离线测试;未执行真实付费生成。
|
|
38
|
+
|
|
39
|
+
## 一手资料
|
|
40
|
+
|
|
41
|
+
| 信息 | 链接 | 登录 |
|
|
42
|
+
|---|---|---|
|
|
43
|
+
| API 文档 | https://fal.ai/models/fal-ai/seedvr/upscale/image/api | 否 |
|
|
44
|
+
| OpenAPI | https://fal.ai/api/openapi/queue/openapi.json?endpoint_id=fal-ai/seedvr/upscale/image | 否 |
|
|
45
|
+
| API Key | https://fal.ai/dashboard/keys | 是 |
|
|
@@ -1,121 +1,121 @@
|
|
|
1
|
-
# Seedance 2.0 · APIMart
|
|
2
|
-
|
|
3
|
-
| 项目 | 内容 |
|
|
4
|
-
|---|---|
|
|
5
|
-
| 最后更新 | 2026-08-30 |
|
|
6
|
-
| 模态 | 视频 |
|
|
7
|
-
| 供应商 | APIMart(聚合平台) |
|
|
8
|
-
| 平台模型 ID | `seedance-2.0`(旧名 `seedance-2-0`) |
|
|
9
|
-
| 接口形态 | **异步任务** |
|
|
10
|
-
| 文档可见性 | 公开,无需登录 |
|
|
11
|
-
| 价格可见性 | 公开,无需登录 |
|
|
12
|
-
|
|
13
|
-
> 同一份 APIMart 文档同时覆盖 `seedance-2.0` / `seedance-2.0-fast` / `seedance-2.0-mini`,参数结构一致,差异集中在**分辨率上限**与**提示词长度**。本文件只讲标准版。
|
|
14
|
-
|
|
15
|
-
## 1. 接入协议
|
|
16
|
-
|
|
17
|
-
- **Base URL**:`https://api.apimart.ai`
|
|
18
|
-
- **鉴权**:`Authorization: Bearer <API_KEY>`
|
|
19
|
-
- **提交**:`POST /v1/videos/generations` → `{ code: 200, data: [{ status: "submitted", task_id }] }`
|
|
20
|
-
- **查询**:`GET /v1/tasks/{task_id}`,状态 `pending` / `processing` / `completed` / `failed`,结果在 `result.videos[]`
|
|
21
|
-
|
|
22
|
-
## 2. 能力清单
|
|
23
|
-
|
|
24
|
-
文生视频、图生视频(首帧)、**首尾帧视频**、**参考视频生视频**、**参考音频**、**有声视频**、**连续视频生成(返回尾帧)**、**联网搜索增强**、**私域虚拟人像素材(Asset URL)**。
|
|
25
|
-
|
|
26
|
-
## 3. 请求参数
|
|
27
|
-
|
|
28
|
-
| 字段 | 类型 | 必填 | 默认 | 取值与说明 |
|
|
29
|
-
|---|---|---|---|---|
|
|
30
|
-
| `model` | string | 必填 | — | `seedance-2.0` |
|
|
31
|
-
| `prompt` | string | 条件 | — | **文生视频必填**;图生视频 / 视频参考生视频可选。限制 4000 字符,**建议 500 字符以内** |
|
|
32
|
-
| `duration` | integer | 可选 | `5` | **4 ~ 15 秒** |
|
|
33
|
-
| `size` | string | 可选 | `16:9` | `16:9`、`9:16`、`1:1`、`4:3`、`3:4`、`21:9`、**`adaptive`**(根据输入图/视频自动匹配)。宽高比须在 0.5–2.5 之间 |
|
|
34
|
-
| `resolution` | string | 可选 | `720p` | `480p` / `720p` / **`1080p`(仅标准版)** / **`4k`(仅标准版)** |
|
|
35
|
-
| `seed` | integer | 可选 | — | 随机种子。**本项目规则:绝对不显示**,不下发 |
|
|
36
|
-
| `generate_audio` | boolean | 可选 | **`true`** | 是否生成配套音频(有声视频) |
|
|
37
|
-
| `return_last_frame` | boolean | 可选 | `false` | `true` 时结果额外返回视频最后一帧的图片 URL,用于连续视频生成 |
|
|
38
|
-
| `tools` | array | 可选 | — | 工具列表,如 `[{"type": "web_search"}]`(联网搜索) |
|
|
39
|
-
| `image_urls` | string[] | 可选 | — | 图生视频参考图。普通 URL 或 `asset://asset_a`。**最多 9 张**。**与 `image_with_roles` 不能同时使用** |
|
|
40
|
-
| `image_with_roles` | array | 可选 | — | 带角色的图片数组,元素为 `{ url, role }`。`role` ∈ `first_frame`(首帧)/ `last_frame`(尾帧)/ `reference_image`(参考人像图,配合 Asset URL)。**与 `image_urls` 不能同时使用** |
|
|
41
|
-
| `video_urls` | string[] | 可选 | — | 参考视频。**最多 3 个,1.8 s < 总时长 < 15.2 s,分辨率需在 480P ~ 720P 之间**。**使用首/尾帧图片时不可用** |
|
|
42
|
-
| `audio_urls` | string[] | 可选 | — | 参考音频。**最多 3 个,总时长 ≤ 15 s**。**必须与参考图片或参考视频一起用**;**使用首/尾帧图片时不可用** |
|
|
43
|
-
| `nsfw_check` | boolean | 可选 | `false` | 见下 |
|
|
44
|
-
|
|
45
|
-
### 互斥与依赖关系(务必在 UI 层做约束)
|
|
46
|
-
|
|
47
|
-
- `image_urls` ⊗ `image_with_roles`(二选一)
|
|
48
|
-
- 使用 `image_with_roles` 的首/尾帧时,`video_urls` 与 `audio_urls` **都不可用**
|
|
49
|
-
- `audio_urls` 必须与参考图片或参考视频一起使用
|
|
50
|
-
|
|
51
|
-
### `nsfw_check` 细节
|
|
52
|
-
|
|
53
|
-
- 审核范围:文本 `prompt`、`negative_prompt`;图片 `image_urls`、`image_with_roles[].url`、`first_frame_image`、`last_frame_image`;`asset://` 图片素材会反查原始公网 URL 后审核;base64 图片转公网地址后审核
|
|
54
|
-
- **`video_urls`、`audio_urls` 以及视频/音频类型的私域素材不会送审**(审核模型不支持视频和音频)
|
|
55
|
-
- 命中审核时**同步返回 HTTP 400(`nsfw_content_detected`)**,不创建任务、不返回 `task_id`、不扣额度
|
|
56
|
-
- 审核服务不可用/超时/响应异常时采用 **fail-open**(继续提交生成请求),因此**不能作为绝对的内容安全保证**
|
|
57
|
-
- 审核调用本身不向发起视频请求的用户计费
|
|
58
|
-
|
|
59
|
-
## 4. 私域虚拟人像素材(Asset URL)
|
|
60
|
-
|
|
61
|
-
**独立端点**:`POST https://api.apimart.ai/v1/seedance2/private-avatar`
|
|
62
|
-
|
|
63
|
-
| 字段 | 类型 | 说明 |
|
|
64
|
-
|---|---|---|
|
|
65
|
-
| `group` | object | 素材组信息 `{ name, description }`。不传 `group_id` 时服务端按此自动创建 `AIGC` 类型素材组。**与 `group_id` 二选一** |
|
|
66
|
-
| `group_id` | string | 已有素材组 ID,传入时跳过素材组创建。**与 `group` 二选一** |
|
|
67
|
-
| `project_name` | string | 项目名称,默认 `default` |
|
|
68
|
-
| `asset_type` | string | `Image`(默认)/ `Video` / `Audio` |
|
|
69
|
-
| `assets` | array | 素材列表,元素为 `{ url, name }`(`url` 需公网可访问)。**单次最多 20 个** |
|
|
70
|
-
| `url` / `name` | string | 单素材兼容写法,与 `assets` 数组二选一 |
|
|
71
|
-
|
|
72
|
-
响应:`data.id`(本地任务 ID)、`data.object = "seedance.avatar.asset.task"`、`data.status = "processing"`、`data.progress`、`data.model`。
|
|
73
|
-
|
|
74
|
-
审核结果同样用 `GET /v1/tasks/{id}` 查询:
|
|
75
|
-
- 批量提交时**只要有一个素材审核失败,任务状态就是 `failed`**,但已通过的素材仍可用,出现在 `result.usable_assets`
|
|
76
|
-
- `result.usable_assets[].asset_url` 可直接用于视频生成
|
|
77
|
-
- `result.failed_assets` 中的素材需更换源文件或重新提交
|
|
78
|
-
- 单素材任务也会兼容返回 `result.asset_url`
|
|
79
|
-
|
|
80
|
-
审核通过后把 `asset://...` 传入视频生成接口即可;服务端识别到 `asset://` 前缀后**直接提交官方生成任务,不会再次触发素材审核**。
|
|
81
|
-
|
|
82
|
-
Asset URL 支持全部 Seedance 2.0 模型(`seedance-2.0` / `-fast` / `-mini`)。
|
|
83
|
-
|
|
84
|
-
## 5. 价格
|
|
85
|
-
|
|
86
|
-
来源:[APIMart 定价中心](https://apimart.ai/zh/pricing) → 视频标签页 `SEEDANCE-2.0`(2026-08-30 复核,1 Credit ≈ $0.1)。当前定价中心与模型页的秒价口径一致,未发现新的价格冲突。
|
|
87
|
-
|
|
88
|
-
| 规格 | 我们的价格 |
|
|
89
|
-
|---|---|
|
|
90
|
-
| 480P | 0.66 Credits/秒 ≈ **$0.066/秒** |
|
|
91
|
-
| 480P-input | 0.4 Credits/秒 ≈ **$0.04/秒** |
|
|
92
|
-
| 720P | 1.42 Credits/秒 ≈ **$0.142/秒** |
|
|
93
|
-
| 720P-input | 0.8584 Credits/秒 ≈ **$0.08584/秒** |
|
|
94
|
-
| 1080P | 3.544 Credits/秒 ≈ **$0.3544/秒** |
|
|
95
|
-
| 1080P-input | 2.1568 Credits/秒 ≈ **$0.21568/秒** |
|
|
96
|
-
| 4K | 7.22 Credits/秒 ≈ **$0.722/秒** |
|
|
97
|
-
| 4K-input | 4.4432 Credits/秒 ≈ **$0.44432/秒** |
|
|
98
|
-
|
|
99
|
-
`-input` 档位对应「有参考视频输入」的计费方式(单价更低,但按输入 + 输出总时长计费)。
|
|
100
|
-
|
|
101
|
-
**数字人(私域人像)另有独立价格** `SEEDANCE-2.0-FACE`:480P 0.992 Credits/秒 ≈ $0.0992/秒、480P-input 0.6 ≈ $0.06/秒、720P 2.136 ≈ $0.2136/秒、720P-input 1.288 ≈ $0.1288/秒、1080P 5 ≈ $0.5/秒、1080P-input 3 ≈ $0.3/秒。
|
|
102
|
-
|
|
103
|
-
## 6. 适配要点
|
|
104
|
-
|
|
105
|
-
- 本项目默认**绝对不显示**:`seed`、负面提示词。APIMart 本接口**有 `seed`**(不下发);`negative_prompt` 未在参数表列出,但 `nsfw_check` 的审核范围提到了它,接入时按「不注册、不下发」处理。
|
|
106
|
-
- **参数互斥关系是这个模型最容易踩的坑**:`image_urls` / `image_with_roles` 二选一;首尾帧模式下参考视频与参考音频全部失效。UI 必须做互斥禁用,不能只靠后端报错。
|
|
107
|
-
- `generate_audio` **默认 `true`**(会出有声视频),与多数模型默认关闭相反。
|
|
108
|
-
- `1080p` / `4k` **仅标准版支持**,Fast / Mini 传了会失败。
|
|
109
|
-
- 有参考视频时计费按「输入 + 输出总时长」,成本估算不能只按输出时长算。
|
|
110
|
-
- SDK 从 `uploadedVideoFilePaths` / `videos` / `uploadedVideos` 取非空且数量最完整的一组;空数组不遮蔽其他字段。宿主按顺序提供完整 `__videoDurationSeconds: number[]` 时求真实总和,数组不完整时改用 `__totalVideoDurationSeconds`,最后才兼容 `__firstVideoDurationSeconds × 视频数` 的旧近似估算。
|
|
111
|
-
- Asset URL 是一整套独立的素材上传 + 审核流程,若要做数字人必须先接 `private-avatar` 端点。
|
|
112
|
-
|
|
113
|
-
## 7. 原始链接索引
|
|
114
|
-
|
|
115
|
-
| 信息 | 链接 | 是否需登录 |
|
|
116
|
-
|---|---|---|
|
|
117
|
-
| seedance-2.0 视频生成 | https://docs.apimart.ai/cn/api-reference/videos/seedance-2-0/generation | 否 |
|
|
118
|
-
| 虚拟人像素材(私域 Asset) | https://docs.apimart.ai/cn/api-reference/videos/seedance-2-0/private-avatar | 否 |
|
|
119
|
-
| 获取任务状态 | https://docs.apimart.ai/cn/api-reference/tasks/status | 否 |
|
|
120
|
-
| 定价中心(视频标签页搜 SEEDANCE-2.0 / SEEDANCE-2.0-FACE) | https://apimart.ai/zh/pricing | 否 |
|
|
121
|
-
| API Key 管理 | https://apimart.ai/keys | **是** |
|
|
1
|
+
# Seedance 2.0 · APIMart
|
|
2
|
+
|
|
3
|
+
| 项目 | 内容 |
|
|
4
|
+
|---|---|
|
|
5
|
+
| 最后更新 | 2026-08-30 |
|
|
6
|
+
| 模态 | 视频 |
|
|
7
|
+
| 供应商 | APIMart(聚合平台) |
|
|
8
|
+
| 平台模型 ID | `seedance-2.0`(旧名 `seedance-2-0`) |
|
|
9
|
+
| 接口形态 | **异步任务** |
|
|
10
|
+
| 文档可见性 | 公开,无需登录 |
|
|
11
|
+
| 价格可见性 | 公开,无需登录 |
|
|
12
|
+
|
|
13
|
+
> 同一份 APIMart 文档同时覆盖 `seedance-2.0` / `seedance-2.0-fast` / `seedance-2.0-mini`,参数结构一致,差异集中在**分辨率上限**与**提示词长度**。本文件只讲标准版。
|
|
14
|
+
|
|
15
|
+
## 1. 接入协议
|
|
16
|
+
|
|
17
|
+
- **Base URL**:`https://api.apimart.ai`
|
|
18
|
+
- **鉴权**:`Authorization: Bearer <API_KEY>`
|
|
19
|
+
- **提交**:`POST /v1/videos/generations` → `{ code: 200, data: [{ status: "submitted", task_id }] }`
|
|
20
|
+
- **查询**:`GET /v1/tasks/{task_id}`,状态 `pending` / `processing` / `completed` / `failed`,结果在 `result.videos[]`
|
|
21
|
+
|
|
22
|
+
## 2. 能力清单
|
|
23
|
+
|
|
24
|
+
文生视频、图生视频(首帧)、**首尾帧视频**、**参考视频生视频**、**参考音频**、**有声视频**、**连续视频生成(返回尾帧)**、**联网搜索增强**、**私域虚拟人像素材(Asset URL)**。
|
|
25
|
+
|
|
26
|
+
## 3. 请求参数
|
|
27
|
+
|
|
28
|
+
| 字段 | 类型 | 必填 | 默认 | 取值与说明 |
|
|
29
|
+
|---|---|---|---|---|
|
|
30
|
+
| `model` | string | 必填 | — | `seedance-2.0` |
|
|
31
|
+
| `prompt` | string | 条件 | — | **文生视频必填**;图生视频 / 视频参考生视频可选。限制 4000 字符,**建议 500 字符以内** |
|
|
32
|
+
| `duration` | integer | 可选 | `5` | **4 ~ 15 秒** |
|
|
33
|
+
| `size` | string | 可选 | `16:9` | `16:9`、`9:16`、`1:1`、`4:3`、`3:4`、`21:9`、**`adaptive`**(根据输入图/视频自动匹配)。宽高比须在 0.5–2.5 之间 |
|
|
34
|
+
| `resolution` | string | 可选 | `720p` | `480p` / `720p` / **`1080p`(仅标准版)** / **`4k`(仅标准版)** |
|
|
35
|
+
| `seed` | integer | 可选 | — | 随机种子。**本项目规则:绝对不显示**,不下发 |
|
|
36
|
+
| `generate_audio` | boolean | 可选 | **`true`** | 是否生成配套音频(有声视频) |
|
|
37
|
+
| `return_last_frame` | boolean | 可选 | `false` | `true` 时结果额外返回视频最后一帧的图片 URL,用于连续视频生成 |
|
|
38
|
+
| `tools` | array | 可选 | — | 工具列表,如 `[{"type": "web_search"}]`(联网搜索) |
|
|
39
|
+
| `image_urls` | string[] | 可选 | — | 图生视频参考图。普通 URL 或 `asset://asset_a`。**最多 9 张**。**与 `image_with_roles` 不能同时使用** |
|
|
40
|
+
| `image_with_roles` | array | 可选 | — | 带角色的图片数组,元素为 `{ url, role }`。`role` ∈ `first_frame`(首帧)/ `last_frame`(尾帧)/ `reference_image`(参考人像图,配合 Asset URL)。**与 `image_urls` 不能同时使用** |
|
|
41
|
+
| `video_urls` | string[] | 可选 | — | 参考视频。**最多 3 个,1.8 s < 总时长 < 15.2 s,分辨率需在 480P ~ 720P 之间**。**使用首/尾帧图片时不可用** |
|
|
42
|
+
| `audio_urls` | string[] | 可选 | — | 参考音频。**最多 3 个,总时长 ≤ 15 s**。**必须与参考图片或参考视频一起用**;**使用首/尾帧图片时不可用** |
|
|
43
|
+
| `nsfw_check` | boolean | 可选 | `false` | 见下 |
|
|
44
|
+
|
|
45
|
+
### 互斥与依赖关系(务必在 UI 层做约束)
|
|
46
|
+
|
|
47
|
+
- `image_urls` ⊗ `image_with_roles`(二选一)
|
|
48
|
+
- 使用 `image_with_roles` 的首/尾帧时,`video_urls` 与 `audio_urls` **都不可用**
|
|
49
|
+
- `audio_urls` 必须与参考图片或参考视频一起使用
|
|
50
|
+
|
|
51
|
+
### `nsfw_check` 细节
|
|
52
|
+
|
|
53
|
+
- 审核范围:文本 `prompt`、`negative_prompt`;图片 `image_urls`、`image_with_roles[].url`、`first_frame_image`、`last_frame_image`;`asset://` 图片素材会反查原始公网 URL 后审核;base64 图片转公网地址后审核
|
|
54
|
+
- **`video_urls`、`audio_urls` 以及视频/音频类型的私域素材不会送审**(审核模型不支持视频和音频)
|
|
55
|
+
- 命中审核时**同步返回 HTTP 400(`nsfw_content_detected`)**,不创建任务、不返回 `task_id`、不扣额度
|
|
56
|
+
- 审核服务不可用/超时/响应异常时采用 **fail-open**(继续提交生成请求),因此**不能作为绝对的内容安全保证**
|
|
57
|
+
- 审核调用本身不向发起视频请求的用户计费
|
|
58
|
+
|
|
59
|
+
## 4. 私域虚拟人像素材(Asset URL)
|
|
60
|
+
|
|
61
|
+
**独立端点**:`POST https://api.apimart.ai/v1/seedance2/private-avatar`
|
|
62
|
+
|
|
63
|
+
| 字段 | 类型 | 说明 |
|
|
64
|
+
|---|---|---|
|
|
65
|
+
| `group` | object | 素材组信息 `{ name, description }`。不传 `group_id` 时服务端按此自动创建 `AIGC` 类型素材组。**与 `group_id` 二选一** |
|
|
66
|
+
| `group_id` | string | 已有素材组 ID,传入时跳过素材组创建。**与 `group` 二选一** |
|
|
67
|
+
| `project_name` | string | 项目名称,默认 `default` |
|
|
68
|
+
| `asset_type` | string | `Image`(默认)/ `Video` / `Audio` |
|
|
69
|
+
| `assets` | array | 素材列表,元素为 `{ url, name }`(`url` 需公网可访问)。**单次最多 20 个** |
|
|
70
|
+
| `url` / `name` | string | 单素材兼容写法,与 `assets` 数组二选一 |
|
|
71
|
+
|
|
72
|
+
响应:`data.id`(本地任务 ID)、`data.object = "seedance.avatar.asset.task"`、`data.status = "processing"`、`data.progress`、`data.model`。
|
|
73
|
+
|
|
74
|
+
审核结果同样用 `GET /v1/tasks/{id}` 查询:
|
|
75
|
+
- 批量提交时**只要有一个素材审核失败,任务状态就是 `failed`**,但已通过的素材仍可用,出现在 `result.usable_assets`
|
|
76
|
+
- `result.usable_assets[].asset_url` 可直接用于视频生成
|
|
77
|
+
- `result.failed_assets` 中的素材需更换源文件或重新提交
|
|
78
|
+
- 单素材任务也会兼容返回 `result.asset_url`
|
|
79
|
+
|
|
80
|
+
审核通过后把 `asset://...` 传入视频生成接口即可;服务端识别到 `asset://` 前缀后**直接提交官方生成任务,不会再次触发素材审核**。
|
|
81
|
+
|
|
82
|
+
Asset URL 支持全部 Seedance 2.0 模型(`seedance-2.0` / `-fast` / `-mini`)。
|
|
83
|
+
|
|
84
|
+
## 5. 价格
|
|
85
|
+
|
|
86
|
+
来源:[APIMart 定价中心](https://apimart.ai/zh/pricing) → 视频标签页 `SEEDANCE-2.0`(2026-08-30 复核,1 Credit ≈ $0.1)。当前定价中心与模型页的秒价口径一致,未发现新的价格冲突。
|
|
87
|
+
|
|
88
|
+
| 规格 | 我们的价格 |
|
|
89
|
+
|---|---|
|
|
90
|
+
| 480P | 0.66 Credits/秒 ≈ **$0.066/秒** |
|
|
91
|
+
| 480P-input | 0.4 Credits/秒 ≈ **$0.04/秒** |
|
|
92
|
+
| 720P | 1.42 Credits/秒 ≈ **$0.142/秒** |
|
|
93
|
+
| 720P-input | 0.8584 Credits/秒 ≈ **$0.08584/秒** |
|
|
94
|
+
| 1080P | 3.544 Credits/秒 ≈ **$0.3544/秒** |
|
|
95
|
+
| 1080P-input | 2.1568 Credits/秒 ≈ **$0.21568/秒** |
|
|
96
|
+
| 4K | 7.22 Credits/秒 ≈ **$0.722/秒** |
|
|
97
|
+
| 4K-input | 4.4432 Credits/秒 ≈ **$0.44432/秒** |
|
|
98
|
+
|
|
99
|
+
`-input` 档位对应「有参考视频输入」的计费方式(单价更低,但按输入 + 输出总时长计费)。
|
|
100
|
+
|
|
101
|
+
**数字人(私域人像)另有独立价格** `SEEDANCE-2.0-FACE`:480P 0.992 Credits/秒 ≈ $0.0992/秒、480P-input 0.6 ≈ $0.06/秒、720P 2.136 ≈ $0.2136/秒、720P-input 1.288 ≈ $0.1288/秒、1080P 5 ≈ $0.5/秒、1080P-input 3 ≈ $0.3/秒。
|
|
102
|
+
|
|
103
|
+
## 6. 适配要点
|
|
104
|
+
|
|
105
|
+
- 本项目默认**绝对不显示**:`seed`、负面提示词。APIMart 本接口**有 `seed`**(不下发);`negative_prompt` 未在参数表列出,但 `nsfw_check` 的审核范围提到了它,接入时按「不注册、不下发」处理。
|
|
106
|
+
- **参数互斥关系是这个模型最容易踩的坑**:`image_urls` / `image_with_roles` 二选一;首尾帧模式下参考视频与参考音频全部失效。UI 必须做互斥禁用,不能只靠后端报错。
|
|
107
|
+
- `generate_audio` **默认 `true`**(会出有声视频),与多数模型默认关闭相反。
|
|
108
|
+
- `1080p` / `4k` **仅标准版支持**,Fast / Mini 传了会失败。
|
|
109
|
+
- 有参考视频时计费按「输入 + 输出总时长」,成本估算不能只按输出时长算。
|
|
110
|
+
- SDK 从 `uploadedVideoFilePaths` / `videos` / `uploadedVideos` 取非空且数量最完整的一组;空数组不遮蔽其他字段。宿主按顺序提供完整 `__videoDurationSeconds: number[]` 时求真实总和,数组不完整时改用 `__totalVideoDurationSeconds`,最后才兼容 `__firstVideoDurationSeconds × 视频数` 的旧近似估算。
|
|
111
|
+
- Asset URL 是一整套独立的素材上传 + 审核流程,若要做数字人必须先接 `private-avatar` 端点。
|
|
112
|
+
|
|
113
|
+
## 7. 原始链接索引
|
|
114
|
+
|
|
115
|
+
| 信息 | 链接 | 是否需登录 |
|
|
116
|
+
|---|---|---|
|
|
117
|
+
| seedance-2.0 视频生成 | https://docs.apimart.ai/cn/api-reference/videos/seedance-2-0/generation | 否 |
|
|
118
|
+
| 虚拟人像素材(私域 Asset) | https://docs.apimart.ai/cn/api-reference/videos/seedance-2-0/private-avatar | 否 |
|
|
119
|
+
| 获取任务状态 | https://docs.apimart.ai/cn/api-reference/tasks/status | 否 |
|
|
120
|
+
| 定价中心(视频标签页搜 SEEDANCE-2.0 / SEEDANCE-2.0-FACE) | https://apimart.ai/zh/pricing | 否 |
|
|
121
|
+
| API Key 管理 | https://apimart.ai/keys | **是** |
|