@henjicc/ai-sdk 0.2.8 → 0.4.0
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 +157 -141
- package/README.md +497 -455
- package/dist/capabilities/embedding/bailian.d.ts +23 -0
- package/dist/capabilities/embedding/bailian.js +10 -0
- package/dist/capabilities/embedding/bigmodel.d.ts +9 -0
- package/dist/capabilities/embedding/bigmodel.js +5 -0
- package/dist/capabilities/embedding/index.d.ts +1 -0
- package/dist/capabilities/embedding/index.js +1 -0
- package/dist/capabilities/embedding/ppio.d.ts +7 -0
- package/dist/capabilities/embedding/ppio.js +5 -0
- package/dist/capabilities/embedding/siliconflow.d.ts +21 -0
- package/dist/capabilities/embedding/siliconflow.js +10 -0
- package/dist/capabilities/embedding/volcengine.d.ts +10 -0
- package/dist/capabilities/embedding/volcengine.js +6 -0
- package/dist/capabilities/rerank/bailian.d.ts +21 -0
- package/dist/capabilities/rerank/bailian.js +14 -0
- package/dist/capabilities/rerank/bigmodel.d.ts +9 -0
- package/dist/capabilities/rerank/bigmodel.js +5 -0
- package/dist/capabilities/rerank/index.d.ts +1 -0
- package/dist/capabilities/rerank/index.js +1 -0
- package/dist/capabilities/rerank/ppio.d.ts +7 -0
- package/dist/capabilities/rerank/ppio.js +5 -0
- package/dist/capabilities/rerank/siliconflow.d.ts +21 -0
- package/dist/capabilities/rerank/siliconflow.js +10 -0
- package/dist/capabilities/retrieval/http.d.ts +3 -0
- package/dist/capabilities/retrieval/http.js +48 -0
- package/dist/capabilities/retrieval/module.d.ts +11 -0
- package/dist/capabilities/retrieval/module.js +110 -0
- package/dist/capabilities/retrieval/types.d.ts +54 -0
- package/dist/capabilities/retrieval/types.js +1 -0
- package/dist/capabilities/retrieval/validation.d.ts +10 -0
- package/dist/capabilities/retrieval/validation.js +65 -0
- package/dist/capabilities/types.d.ts +1 -1
- package/dist/catalog/apimart/gpt-image-2.5.model.d.ts +2 -0
- package/dist/catalog/apimart/gpt-image-2.5.model.js +51 -0
- package/dist/catalog/fal/gpt-image-2.5.model.d.ts +2 -0
- package/dist/catalog/fal/gpt-image-2.5.model.js +53 -0
- package/dist/catalog/fal/ic-light-v2.model.js +9 -13
- package/dist/catalog/grsai/gpt-image-2.5.model.d.ts +2 -0
- package/dist/catalog/grsai/gpt-image-2.5.model.js +54 -0
- package/dist/catalog/grsai/gptImage25Sizes.d.ts +1 -0
- package/dist/catalog/grsai/gptImage25Sizes.js +76 -0
- package/dist/catalog/index.js +112 -104
- package/dist/catalog/kie/gpt-image-2.5.model.d.ts +2 -0
- package/dist/catalog/kie/gpt-image-2.5.model.js +38 -0
- package/dist/catalog/shared/gptImage25.d.ts +16 -0
- package/dist/catalog/shared/gptImage25.js +48 -0
- package/dist/catalog/shared/gptImage25Pricing.d.ts +12 -0
- package/dist/catalog/shared/gptImage25Pricing.js +508 -0
- package/dist/llm/defaults.d.ts +1 -1
- package/dist/llm/defaults.js +1 -1
- package/dist/llm/discovery.d.ts +2 -0
- package/dist/llm/discovery.js +16 -5
- package/dist/llm/modelCatalogEntries.js +32 -0
- package/dist/llm/providerPresets.d.ts +3 -1
- package/dist/llm/providerPresets.js +6 -3
- package/dist/llm/providerReasoningRequest.js +14 -1
- package/dist/llm/siliconflow/index.d.ts +21 -0
- package/dist/llm/siliconflow/index.js +32 -0
- package/dist/llm/siliconflow/preset.d.ts +6 -0
- package/dist/llm/siliconflow/preset.js +33 -0
- package/dist/packs/models/apimart/gpt-image-2.5.d.ts +6 -0
- package/dist/packs/models/apimart/gpt-image-2.5.js +7 -0
- package/dist/packs/models/fal/gpt-image-2.5.d.ts +6 -0
- package/dist/packs/models/fal/gpt-image-2.5.js +7 -0
- package/dist/packs/models/grsai/gpt-image-2.5.d.ts +6 -0
- package/dist/packs/models/grsai/gpt-image-2.5.js +7 -0
- package/dist/packs/models/kie/gpt-image-2.5.d.ts +6 -0
- package/dist/packs/models/kie/gpt-image-2.5.js +7 -0
- package/dist/packs/provider-packs/apimart.d.ts +1 -1
- package/dist/packs/provider-packs/apimart.js +21 -20
- package/dist/packs/provider-packs/fal.d.ts +1 -1
- package/dist/packs/provider-packs/fal.js +37 -36
- package/dist/packs/provider-packs/grsai.d.ts +1 -1
- package/dist/packs/provider-packs/grsai.js +6 -5
- package/dist/packs/provider-packs/kie.d.ts +1 -1
- package/dist/packs/provider-packs/kie.js +28 -27
- package/dist/packs/tool-models/fal/{qwen-image-edit-2509-multiple-angles.d.ts → qwen-image-edit-2511-multiple-angles.d.ts} +1 -1
- package/dist/packs/tool-models/fal/{qwen-image-edit-2509-multiple-angles.js → qwen-image-edit-2511-multiple-angles.js} +1 -1
- package/dist/packs/tool-packs/fal-multi-angle-tools.js +1 -1
- package/dist/tool-packs/fal-multi-angle/models/qwen-image-edit-2511-multiple-angles.model.d.ts +2 -0
- package/dist/tool-packs/fal-multi-angle/models/{qwen-image-edit-2509-multiple-angles.model.js → qwen-image-edit-2511-multiple-angles.model.js} +20 -17
- package/docs/README.md +26 -26
- package/docs/consumers.md +56 -48
- package/docs/llm-adaptation/README.md +139 -137
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/DeepSeek.md +103 -91
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/Kimi.md +75 -75
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206/MiniMax.md +84 -84
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//345/260/217/347/261/263MiMo.md +85 -85
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//346/231/272/350/260/261GLM.md +232 -232
- 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 +87 -87
- package/docs/llm-adaptation//344/276/233/345/272/224/345/225/206//347/231/276/347/202/274Qwen.md +84 -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/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/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 +43 -43
- package/docs/model-adaptation/Fun-ASR-Flash-2026-06-15/Fun-ASR-Flash-2026-06-15_/347/231/276/347/202/274.md +41 -41
- package/docs/model-adaptation/Fun-ASR-Realtime/Fun-ASR-Realtime_/347/231/276/347/202/274.md +37 -37
- 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 +207 -207
- 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 +137 -137
- package/docs/model-adaptation/GPT-Image-2/GPT-Image-2_KIE.md +93 -93
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_APIMart.md +66 -0
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_Fal.md +55 -0
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_Grsai.md +53 -0
- package/docs/model-adaptation/GPT-Image-2.5/GPT-Image-2.5_KIE.md +55 -0
- package/docs/model-adaptation/GPT-OSS-20B/GPT-OSS-20B_Groq.md +62 -62
- package/docs/model-adaptation/Gemini-Omni-Flash/Gemini-Omni-Flash_APIMart.md +124 -124
- 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 +129 -129
- package/docs/model-adaptation/Grok-Imagine/Grok-Imagine_KIE.md +36 -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/Hailuo-02/Hailuo-02_Fal.md +93 -93
- package/docs/model-adaptation/Hailuo-02/Hailuo-02_KIE.md +56 -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/Hailuo-2.3/Hailuo-2.3_/346/264/276/346/254/247/344/272/221.md +70 -70
- package/docs/model-adaptation/IC-Light-v2/IC-Light-v2_Fal.md +97 -94
- 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 +89 -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 +119 -119
- package/docs/model-adaptation/Kling-3.0-Omni/Kling-3.0-Omni_APIMart.md +125 -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 +143 -143
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_APIMart.md +85 -85
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_Fal.md +83 -83
- package/docs/model-adaptation/Kling-3.0-Turbo/Kling-3.0-Turbo_KIE.md +84 -84
- package/docs/model-adaptation/Midjourney/Midjourney_APIMart.md +396 -396
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_APIMart.md +234 -234
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_Fal.md +108 -108
- package/docs/model-adaptation/MiniMax-H3/MiniMax-H3_KIE.md +111 -111
- 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 +70 -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-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-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 +84 -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 -0
- package/docs/model-adaptation/Qwen-MT-Flash/Qwen-MT-Flash_/347/231/276/347/202/274.md +47 -47
- package/docs/model-adaptation/Qwen-MT-Lite/Qwen-MT-Lite_/347/231/276/347/202/274.md +39 -39
- package/docs/model-adaptation/Qwen-MT-Plus/Qwen-MT-Plus_/347/231/276/347/202/274.md +39 -39
- package/docs/model-adaptation/Qwen3-ASR-Flash/Qwen3-ASR-Flash_/347/231/276/347/202/274.md +40 -40
- package/docs/model-adaptation/Qwen3-ASR-Flash-2026-02-10/Qwen3-ASR-Flash-2026-02-10_/347/231/276/347/202/274.md +33 -33
- package/docs/model-adaptation/Qwen3-ASR-Flash-Filetrans/Qwen3-ASR-Flash-Filetrans_/347/231/276/347/202/274.md +41 -41
- package/docs/model-adaptation/Qwen3-ASR-Flash-Realtime/Qwen3-ASR-Flash-Realtime_/347/231/276/347/202/274.md +35 -35
- 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 +313 -295
- 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 +143 -143
- 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 +86 -86
- 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 +78 -78
- package/docs/model-adaptation/Seedance-2.0-Mini/Seedance-2.0-Mini_APIMart.md +89 -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 +78 -78
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_APIMart.md +212 -212
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_Fal.md +94 -94
- package/docs/model-adaptation/Seedance-2.5/Seedance-2.5_KIE.md +89 -89
- package/docs/model-adaptation/Seedream-5.0-Lite/Seedream-5.0-Lite_APIMart.md +106 -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 +108 -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 +69 -69
- package/docs/model-adaptation/TeleSpeechASR/TeleSpeechASR_/347/241/205/345/237/272/346/265/201/345/212/250.md +72 -72
- 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/Wan-2.5-Preview/Wan-2.5-Preview_/346/264/276/346/254/247/344/272/221.md +82 -82
- package/docs/model-adaptation/Wan-2.6/Wan-2.6_/346/264/276/346/254/247/344/272/221.md +84 -84
- package/docs/model-adaptation/Wan-2.7/Wan-2.7_/346/264/276/346/254/247/344/272/221.md +122 -122
- package/docs/model-adaptation/Whisper-Large-v3/Whisper-Large-v3_Groq.md +76 -76
- package/docs/model-adaptation/Whisper-Large-v3-Turbo/Whisper-Large-v3-Turbo_Groq.md +75 -75
- 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 +95 -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 +97 -97
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/APIMart.md +238 -238
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/Fal.md +172 -172
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206/Groq.md +121 -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 +131 -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 +147 -138
- 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 +181 -171
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//347/231/276/347/202/274.md +237 -227
- 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 +140 -75
- package/docs/model-adaptation//344/276/233/345/272/224/345/225/206//351/255/224/346/220/255.md +207 -207
- package/docs/model-adaptation//346/226/207/346/241/243/351/207/207/351/233/206/346/211/213/345/206/214.md +338 -311
- 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 +32 -32
- 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 +255 -195
- package/dist/tool-packs/fal-multi-angle/models/qwen-image-edit-2509-multiple-angles.model.d.ts +0 -2
- package/docs/model-adaptation/Qwen-Image-Edit-2509-/345/244/232/350/247/222/345/272/246/Qwen-Image-Edit-2509-/345/244/232/350/247/222/345/272/246_Fal.md +0 -116
package/docs/model-adaptation/MiniMax-Speech/MiniMax-Speech_/346/264/276/346/254/247/344/272/221.md
CHANGED
|
@@ -1,170 +1,170 @@
|
|
|
1
|
-
# MiniMax Speech · 派欧云 PPIO
|
|
2
|
-
|
|
3
|
-
| 项目 | 内容 |
|
|
4
|
-
|---|---|
|
|
5
|
-
| 最后更新 | 2026-08-30 |
|
|
6
|
-
| 模态 | 音频(语音合成 + 声音克隆) |
|
|
7
|
-
| 供应商 | 派欧云 PPIO |
|
|
8
|
-
| 平台路由 | `/v3/[async/]minimax-speech-2.8-{hd,turbo}`、`/v3/minimax-voice-cloning` |
|
|
9
|
-
| 接口形态 | 同步与异步双版本;声音克隆为同步 |
|
|
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
|
-
供应商公共协议见 [供应商/派欧云.md](../供应商/派欧云.md)。
|
|
14
|
-
|
|
15
|
-
## 1. 能力与价格
|
|
16
|
-
|
|
17
|
-
| 接口 | 路由 | 价格 |
|
|
18
|
-
|---|---|---|
|
|
19
|
-
| Speech 2.8 HD 同步 | `POST /v3/minimax-speech-2.8-hd` | ¥3.5 / 万字符 |
|
|
20
|
-
| Speech 2.8 HD 异步 | `POST /v3/async/minimax-speech-2.8-hd` | ¥3.5 / 万字符 |
|
|
21
|
-
| Speech 2.8 Turbo 同步 | `POST /v3/minimax-speech-2.8-turbo` | ¥2.0 / 万字符 |
|
|
22
|
-
| Speech 2.8 Turbo 异步 | `POST /v3/async/minimax-speech-2.8-turbo` | ¥2.0 / 万字符 |
|
|
23
|
-
| 声音克隆 | `POST /v3/minimax-voice-cloning` | **¥9.9 / 音色**(试听另计) |
|
|
24
|
-
|
|
25
|
-
定价页还列着 `MiniMax speech-2.6-hd` ¥3.5/万字符 与 `speech-2.6-turbo` ¥2/万字符,说明 **2.6 仍在售**,但文档站已不再提供 2.6 的 API 参考页,**路由无法确认**(PPIO 对所有未知路径统一返回 400,无法靠探测区分)。
|
|
26
|
-
|
|
27
|
-
计费字符数以响应里的 `extra_info.usage_characters` 为准。PPIO 公开商品注册表给出的结算表达式为 `(单价 × 字符数 + 999999) / 1000000`,即每次请求按实际字符费**向上取整到人民币分**;不能只做“最低 ¥0.01”而保留分以下的小数。
|
|
28
|
-
|
|
29
|
-
## 2. 声音克隆 `/v3/minimax-voice-cloning`
|
|
30
|
-
|
|
31
|
-
### `model` 字段枚举(已核实)
|
|
32
|
-
|
|
33
|
-
```
|
|
34
|
-
speech-2.6-hd | speech-2.6-turbo | speech-2.8-hd | speech-2.8-turbo
|
|
35
|
-
```
|
|
36
|
-
|
|
37
|
-
> ⚠️ **该文档页底部的 curl 示例里写的是 `"model": "speech-01-hd"`,那是 PPIO 没同步更新的过期示例,不要照抄。** 以正文参数表的枚举为准。曾有一次排查因为参照了含旧示例的过期资料,误判项目代码写错——项目当前的 4 个枚举值是正确的。
|
|
38
|
-
|
|
39
|
-
### 参数
|
|
40
|
-
|
|
41
|
-
| 字段 | 类型 | 必填 | 默认 | 约束 |
|
|
42
|
-
|---|---|---|---|---|
|
|
43
|
-
| `audio_url` | string | ✅ | — | mp3/m4a/wav;时长 10 秒 ~ 5 分钟;≤20MB |
|
|
44
|
-
| `clone_prompt` | object | | — | `{ prompt_audio_url 必填(示例音频 <8s), prompt_text 必填(对应文本,句末需有标点)}`,提升音色相似度与稳定性 |
|
|
45
|
-
| `text` | string | | — | 复刻试听文本,≤2000 字符 |
|
|
46
|
-
| `model` | string | 传 `text` 时必填 | — | 上述 4 个枚举值 |
|
|
47
|
-
| `accuracy` | float | | `0.7` | 文本校验准确率阈值 `[0, 1]` |
|
|
48
|
-
| `need_noise_reduction` | boolean | | `false` | 降噪 |
|
|
49
|
-
| `need_volume_normalization` | boolean | | `false` | 音量归一化 |
|
|
50
|
-
|
|
51
|
-
响应:`{ demo_audio_url, voice_id }`
|
|
52
|
-
|
|
53
|
-
### 两个业务硬约束
|
|
54
|
-
|
|
55
|
-
1. ⚠️ **仅个人认证 / 企业认证用户可调用**(需实名认证)
|
|
56
|
-
2. ⚠️ **复刻出的是临时音色,必须在 168 小时(7 天)内在任意 T2A 合成接口中实际使用一次(试听不算),否则音色被删除**
|
|
57
|
-
|
|
58
|
-
### 计费
|
|
59
|
-
|
|
60
|
-
¥9.9 / 音色。**试听单独计费**——文档明确写「试听将根据字符数正常收取语音合成费用,定价与 T2A 各接口一致」,即传了 `text` 会额外按 HD ¥3.5/万字符或 Turbo ¥2/万字符扣费。试听字符费也按单次请求向上取整到分,再与 ¥9.9 音色费相加;例如 Turbo 60 字符原始金额 ¥0.012,实际计为 ¥0.02,总计 ¥9.92。
|
|
61
|
-
|
|
62
|
-
## 3. 语音合成(同步)
|
|
63
|
-
|
|
64
|
-
**模型版本在路由里,请求体没有 `model` 字段。**
|
|
65
|
-
|
|
66
|
-
| 字段 | 类型 | 必填 | 默认 | 约束 |
|
|
67
|
-
|---|---|---|---|---|
|
|
68
|
-
| `text` | string | ✅ | — | < 10000 字符(>3000 建议流式);支持换行分段、`<#x#>` 停顿标记、语气词标签 |
|
|
69
|
-
| `stream` | boolean | | `false` | |
|
|
70
|
-
| `output_format` | string | | **`hex`** | `url` / `hex`;仅非流式生效,流式只能 hex;返回的 url 有效期 24 小时 |
|
|
71
|
-
| `voice_setting` | object | | — | 见下 |
|
|
72
|
-
| `audio_setting` | object | | — | 见下 |
|
|
73
|
-
| `voice_modify` | object | | — | `pitch` / `timbre` / `intensity` 各 `[-100, 100]`;`sound_effects` 枚举 `spacious_echo` / `auditorium_echo` / `lofi_telephone` / `robotic`(单次仅一种) |
|
|
74
|
-
| `timber_weights` | object[] | | — | 混合音色 `{ weight 必填 integer, voice_id 必填 string }` |
|
|
75
|
-
| `subtitle_enable` | boolean | | `false` | |
|
|
76
|
-
| `aigc_watermark` | boolean | | `false` | |
|
|
77
|
-
| `language_boost` | string | | `null` | 41 个枚举值(`Chinese`、`Chinese,Yue`、`English`、`Japanese`、…、`auto`) |
|
|
78
|
-
| `pronunciation_dict` | object | | — | `tone` string[],如 `["燕少飞/(yan4)(shao3)(fei1)", "omg/oh my god"]` |
|
|
79
|
-
| `stream_options` | object | | — | `exclude_aggregated_audio` boolean 默认 false |
|
|
80
|
-
|
|
81
|
-
### `voice_setting`
|
|
82
|
-
|
|
83
|
-
| 字段 | 默认 | 约束 |
|
|
84
|
-
|---|---|---|
|
|
85
|
-
| `voice_id` | — | **必填**;系统音色 / 复刻音色 / 文生音色;用混合音色时置空并改用 `timber_weights` |
|
|
86
|
-
| `vol` | `1` | `(0, 10]` |
|
|
87
|
-
| `pitch` | `0` | `[-12, 12]` |
|
|
88
|
-
| `speed` | `1` | `[0.5, 2]` |
|
|
89
|
-
| `emotion` | — | `happy` / `sad` / `angry` / `fearful` / `disgusted` / `surprised` / `calm` / `fluent` / `whisper` |
|
|
90
|
-
| `latex_read` | `false` | |
|
|
91
|
-
| `text_normalization` | `false` | |
|
|
92
|
-
|
|
93
|
-
> ⚠️ **`emotion` 仅对 `speech-2.6-hd/turbo` 与 `speech-01-hd/turbo` 生效,2.8 系列不支持情绪控制**;其中 `fluent` / `whisper` 仅 2.6 系列生效。项目当前只接了 2.8 路由,因此**情绪参数在当前配置下是无效的**,参数面板不应展示。
|
|
94
|
-
|
|
95
|
-
### `audio_setting`
|
|
96
|
-
|
|
97
|
-
| 字段 | 默认 | 约束 |
|
|
98
|
-
|---|---|---|
|
|
99
|
-
| `format` | `mp3` | `mp3` / `pcm` / `flac` / `wav`(wav 仅非流式) |
|
|
100
|
-
| `bitrate` | `128000` | `32000` / `64000` / `128000` / `256000`(仅 mp3 生效) |
|
|
101
|
-
| `channel` | `1` | `1` / `2` |
|
|
102
|
-
| `sample_rate` | `32000` | `8000` / `16000` / `22050` / `24000` / `32000` / `44100` |
|
|
103
|
-
| `force_cbr` | `false` | 仅流式 + mp3 生效 |
|
|
104
|
-
|
|
105
|
-
### 语气词标签(仅 2.8 系列支持)
|
|
106
|
-
|
|
107
|
-
```
|
|
108
|
-
(laughs) (chuckle) (coughs) (clear-throat) (groans) (breath) (pant)
|
|
109
|
-
(inhale) (exhale) (gasps) (sniffs) (sighs) (snorts) (burps)
|
|
110
|
-
(lip-smacking) (humming) (hissing) (emm) (whistles) (sneezes)
|
|
111
|
-
(crying) (applause)
|
|
112
|
-
```
|
|
113
|
-
|
|
114
|
-
### 响应
|
|
115
|
-
|
|
116
|
-
```json
|
|
117
|
-
{
|
|
118
|
-
"data": { "audio": "...", "status": 2, "subtitle_file": "..." },
|
|
119
|
-
"trace_id": "...",
|
|
120
|
-
"base_resp": { "status_code": 0, "status_msg": "success" },
|
|
121
|
-
"extra_info": {
|
|
122
|
-
"usage_characters": 100,
|
|
123
|
-
"audio_length": 1000, "audio_size": 12345, "bitrate": 128000,
|
|
124
|
-
"word_count": 50, "audio_format": "mp3", "audio_channel": 1,
|
|
125
|
-
"audio_sample_rate": 32000, "invisible_character_ratio": 0
|
|
126
|
-
}
|
|
127
|
-
}
|
|
128
|
-
```
|
|
129
|
-
|
|
130
|
-
`extra_info.usage_characters` 是**计费字符数**。
|
|
131
|
-
|
|
132
|
-
## 4. 语音合成(异步)—— 与同步有多处差异
|
|
133
|
-
|
|
134
|
-
本项目走的是异步路由,以下差异必须注意:
|
|
135
|
-
|
|
136
|
-
| 差异点 | 同步 | 异步 |
|
|
137
|
-
|---|---|---|
|
|
138
|
-
| `stream` / `output_format` / `timber_weights` / `subtitle_enable` / `stream_options` | 有 | **没有** |
|
|
139
|
-
| `text` 上限 | < 10000 字符 | **5 万字符** |
|
|
140
|
-
| `text_file_id` | 无 | **有**,与 `text` 二选一必填;txt <100000 字符 或 zip;zip 内 json 支持 `title`/`content`/`extra` 三字段,三者齐全则产出 3 组共 9 个文件 |
|
|
141
|
-
| `voice_setting` | 可选 | **整个 object 必填** |
|
|
142
|
-
| `voice_setting` 内字段 | `latex_read` / `text_normalization` | **`english_normalization`**(默认 false) |
|
|
143
|
-
| 采样率字段名 | `sample_rate` | **`audio_sample_rate`** |
|
|
144
|
-
| `format` 枚举 | mp3/pcm/flac/wav | mp3/pcm/flac/wav/**pcmu_raw**/**pcmu_wav**/**opus** |
|
|
145
|
-
|
|
146
|
-
- `pcmu_*` 为 G.711 μ-law 8kHz
|
|
147
|
-
- `opus` 仅支持采样率 8000/12000/16000/24000/48000,其他值会报错
|
|
148
|
-
- ⚠️ `audio_setting.channel` 文档正文写「可选范围 [1,2],默认值为 1」但 default 标注为 `2`,**文档自相矛盾,建议显式传值**
|
|
149
|
-
|
|
150
|
-
响应:`{ task_id, details: { usage_characters } }`,再走 `/v3/async/task-result` 取 `audios[].audio_url`。
|
|
151
|
-
|
|
152
|
-
## 5. 适配要点
|
|
153
|
-
|
|
154
|
-
- **`emotion` 在 2.8 上不生效**,当前项目只接 2.8 路由,该参数应隐藏或在切到 2.6 时才显示。
|
|
155
|
-
- 同步与异步的字段名不同(`sample_rate` vs `audio_sample_rate`、`text_normalization` vs `english_normalization`),不能共用同一个 builder 分支。
|
|
156
|
-
- 声音克隆的 168 小时失效规则需要在产品侧提示用户,否则会出现「克隆成功但过几天音色不见了」。
|
|
157
|
-
- 声音克隆试听会额外产生 TTS 费用,计价展示应体现 ¥9.9 音色费 + 试听字符费两部分。
|
|
158
|
-
- `audio_url` 字段以 `_url` 结尾 → 走 `public-url` 模式,**声音克隆依赖 KIE API Key**。
|
|
159
|
-
|
|
160
|
-
## 6. 原始链接索引
|
|
161
|
-
|
|
162
|
-
| 信息 | 链接 | 是否需登录 |
|
|
163
|
-
|---|---|---|
|
|
164
|
-
| 声音克隆 | https://ppio.com/docs/models/reference-minimax-voice-cloning | 否 |
|
|
165
|
-
| Speech 2.8 HD 同步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-hd | 否 |
|
|
166
|
-
| Speech 2.8 HD 异步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-hd-async | 否 |
|
|
167
|
-
| Speech 2.8 Turbo 同步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-turbo | 否 |
|
|
168
|
-
| Speech 2.8 Turbo 异步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-turbo-async | 否 |
|
|
169
|
-
| 定价页(音频 tab) | https://ppio.com/pricing | 否 |
|
|
170
|
-
| 模型注册表(含计费表达式) | https://api-server.ppio.com/v1/product/multimodal-model/list?returnSchema=true | 否 |
|
|
1
|
+
# MiniMax Speech · 派欧云 PPIO
|
|
2
|
+
|
|
3
|
+
| 项目 | 内容 |
|
|
4
|
+
|---|---|
|
|
5
|
+
| 最后更新 | 2026-08-30 |
|
|
6
|
+
| 模态 | 音频(语音合成 + 声音克隆) |
|
|
7
|
+
| 供应商 | 派欧云 PPIO |
|
|
8
|
+
| 平台路由 | `/v3/[async/]minimax-speech-2.8-{hd,turbo}`、`/v3/minimax-voice-cloning` |
|
|
9
|
+
| 接口形态 | 同步与异步双版本;声音克隆为同步 |
|
|
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
|
+
供应商公共协议见 [供应商/派欧云.md](../供应商/派欧云.md)。
|
|
14
|
+
|
|
15
|
+
## 1. 能力与价格
|
|
16
|
+
|
|
17
|
+
| 接口 | 路由 | 价格 |
|
|
18
|
+
|---|---|---|
|
|
19
|
+
| Speech 2.8 HD 同步 | `POST /v3/minimax-speech-2.8-hd` | ¥3.5 / 万字符 |
|
|
20
|
+
| Speech 2.8 HD 异步 | `POST /v3/async/minimax-speech-2.8-hd` | ¥3.5 / 万字符 |
|
|
21
|
+
| Speech 2.8 Turbo 同步 | `POST /v3/minimax-speech-2.8-turbo` | ¥2.0 / 万字符 |
|
|
22
|
+
| Speech 2.8 Turbo 异步 | `POST /v3/async/minimax-speech-2.8-turbo` | ¥2.0 / 万字符 |
|
|
23
|
+
| 声音克隆 | `POST /v3/minimax-voice-cloning` | **¥9.9 / 音色**(试听另计) |
|
|
24
|
+
|
|
25
|
+
定价页还列着 `MiniMax speech-2.6-hd` ¥3.5/万字符 与 `speech-2.6-turbo` ¥2/万字符,说明 **2.6 仍在售**,但文档站已不再提供 2.6 的 API 参考页,**路由无法确认**(PPIO 对所有未知路径统一返回 400,无法靠探测区分)。
|
|
26
|
+
|
|
27
|
+
计费字符数以响应里的 `extra_info.usage_characters` 为准。PPIO 公开商品注册表给出的结算表达式为 `(单价 × 字符数 + 999999) / 1000000`,即每次请求按实际字符费**向上取整到人民币分**;不能只做“最低 ¥0.01”而保留分以下的小数。
|
|
28
|
+
|
|
29
|
+
## 2. 声音克隆 `/v3/minimax-voice-cloning`
|
|
30
|
+
|
|
31
|
+
### `model` 字段枚举(已核实)
|
|
32
|
+
|
|
33
|
+
```
|
|
34
|
+
speech-2.6-hd | speech-2.6-turbo | speech-2.8-hd | speech-2.8-turbo
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
> ⚠️ **该文档页底部的 curl 示例里写的是 `"model": "speech-01-hd"`,那是 PPIO 没同步更新的过期示例,不要照抄。** 以正文参数表的枚举为准。曾有一次排查因为参照了含旧示例的过期资料,误判项目代码写错——项目当前的 4 个枚举值是正确的。
|
|
38
|
+
|
|
39
|
+
### 参数
|
|
40
|
+
|
|
41
|
+
| 字段 | 类型 | 必填 | 默认 | 约束 |
|
|
42
|
+
|---|---|---|---|---|
|
|
43
|
+
| `audio_url` | string | ✅ | — | mp3/m4a/wav;时长 10 秒 ~ 5 分钟;≤20MB |
|
|
44
|
+
| `clone_prompt` | object | | — | `{ prompt_audio_url 必填(示例音频 <8s), prompt_text 必填(对应文本,句末需有标点)}`,提升音色相似度与稳定性 |
|
|
45
|
+
| `text` | string | | — | 复刻试听文本,≤2000 字符 |
|
|
46
|
+
| `model` | string | 传 `text` 时必填 | — | 上述 4 个枚举值 |
|
|
47
|
+
| `accuracy` | float | | `0.7` | 文本校验准确率阈值 `[0, 1]` |
|
|
48
|
+
| `need_noise_reduction` | boolean | | `false` | 降噪 |
|
|
49
|
+
| `need_volume_normalization` | boolean | | `false` | 音量归一化 |
|
|
50
|
+
|
|
51
|
+
响应:`{ demo_audio_url, voice_id }`
|
|
52
|
+
|
|
53
|
+
### 两个业务硬约束
|
|
54
|
+
|
|
55
|
+
1. ⚠️ **仅个人认证 / 企业认证用户可调用**(需实名认证)
|
|
56
|
+
2. ⚠️ **复刻出的是临时音色,必须在 168 小时(7 天)内在任意 T2A 合成接口中实际使用一次(试听不算),否则音色被删除**
|
|
57
|
+
|
|
58
|
+
### 计费
|
|
59
|
+
|
|
60
|
+
¥9.9 / 音色。**试听单独计费**——文档明确写「试听将根据字符数正常收取语音合成费用,定价与 T2A 各接口一致」,即传了 `text` 会额外按 HD ¥3.5/万字符或 Turbo ¥2/万字符扣费。试听字符费也按单次请求向上取整到分,再与 ¥9.9 音色费相加;例如 Turbo 60 字符原始金额 ¥0.012,实际计为 ¥0.02,总计 ¥9.92。
|
|
61
|
+
|
|
62
|
+
## 3. 语音合成(同步)
|
|
63
|
+
|
|
64
|
+
**模型版本在路由里,请求体没有 `model` 字段。**
|
|
65
|
+
|
|
66
|
+
| 字段 | 类型 | 必填 | 默认 | 约束 |
|
|
67
|
+
|---|---|---|---|---|
|
|
68
|
+
| `text` | string | ✅ | — | < 10000 字符(>3000 建议流式);支持换行分段、`<#x#>` 停顿标记、语气词标签 |
|
|
69
|
+
| `stream` | boolean | | `false` | |
|
|
70
|
+
| `output_format` | string | | **`hex`** | `url` / `hex`;仅非流式生效,流式只能 hex;返回的 url 有效期 24 小时 |
|
|
71
|
+
| `voice_setting` | object | | — | 见下 |
|
|
72
|
+
| `audio_setting` | object | | — | 见下 |
|
|
73
|
+
| `voice_modify` | object | | — | `pitch` / `timbre` / `intensity` 各 `[-100, 100]`;`sound_effects` 枚举 `spacious_echo` / `auditorium_echo` / `lofi_telephone` / `robotic`(单次仅一种) |
|
|
74
|
+
| `timber_weights` | object[] | | — | 混合音色 `{ weight 必填 integer, voice_id 必填 string }` |
|
|
75
|
+
| `subtitle_enable` | boolean | | `false` | |
|
|
76
|
+
| `aigc_watermark` | boolean | | `false` | |
|
|
77
|
+
| `language_boost` | string | | `null` | 41 个枚举值(`Chinese`、`Chinese,Yue`、`English`、`Japanese`、…、`auto`) |
|
|
78
|
+
| `pronunciation_dict` | object | | — | `tone` string[],如 `["燕少飞/(yan4)(shao3)(fei1)", "omg/oh my god"]` |
|
|
79
|
+
| `stream_options` | object | | — | `exclude_aggregated_audio` boolean 默认 false |
|
|
80
|
+
|
|
81
|
+
### `voice_setting`
|
|
82
|
+
|
|
83
|
+
| 字段 | 默认 | 约束 |
|
|
84
|
+
|---|---|---|
|
|
85
|
+
| `voice_id` | — | **必填**;系统音色 / 复刻音色 / 文生音色;用混合音色时置空并改用 `timber_weights` |
|
|
86
|
+
| `vol` | `1` | `(0, 10]` |
|
|
87
|
+
| `pitch` | `0` | `[-12, 12]` |
|
|
88
|
+
| `speed` | `1` | `[0.5, 2]` |
|
|
89
|
+
| `emotion` | — | `happy` / `sad` / `angry` / `fearful` / `disgusted` / `surprised` / `calm` / `fluent` / `whisper` |
|
|
90
|
+
| `latex_read` | `false` | |
|
|
91
|
+
| `text_normalization` | `false` | |
|
|
92
|
+
|
|
93
|
+
> ⚠️ **`emotion` 仅对 `speech-2.6-hd/turbo` 与 `speech-01-hd/turbo` 生效,2.8 系列不支持情绪控制**;其中 `fluent` / `whisper` 仅 2.6 系列生效。项目当前只接了 2.8 路由,因此**情绪参数在当前配置下是无效的**,参数面板不应展示。
|
|
94
|
+
|
|
95
|
+
### `audio_setting`
|
|
96
|
+
|
|
97
|
+
| 字段 | 默认 | 约束 |
|
|
98
|
+
|---|---|---|
|
|
99
|
+
| `format` | `mp3` | `mp3` / `pcm` / `flac` / `wav`(wav 仅非流式) |
|
|
100
|
+
| `bitrate` | `128000` | `32000` / `64000` / `128000` / `256000`(仅 mp3 生效) |
|
|
101
|
+
| `channel` | `1` | `1` / `2` |
|
|
102
|
+
| `sample_rate` | `32000` | `8000` / `16000` / `22050` / `24000` / `32000` / `44100` |
|
|
103
|
+
| `force_cbr` | `false` | 仅流式 + mp3 生效 |
|
|
104
|
+
|
|
105
|
+
### 语气词标签(仅 2.8 系列支持)
|
|
106
|
+
|
|
107
|
+
```
|
|
108
|
+
(laughs) (chuckle) (coughs) (clear-throat) (groans) (breath) (pant)
|
|
109
|
+
(inhale) (exhale) (gasps) (sniffs) (sighs) (snorts) (burps)
|
|
110
|
+
(lip-smacking) (humming) (hissing) (emm) (whistles) (sneezes)
|
|
111
|
+
(crying) (applause)
|
|
112
|
+
```
|
|
113
|
+
|
|
114
|
+
### 响应
|
|
115
|
+
|
|
116
|
+
```json
|
|
117
|
+
{
|
|
118
|
+
"data": { "audio": "...", "status": 2, "subtitle_file": "..." },
|
|
119
|
+
"trace_id": "...",
|
|
120
|
+
"base_resp": { "status_code": 0, "status_msg": "success" },
|
|
121
|
+
"extra_info": {
|
|
122
|
+
"usage_characters": 100,
|
|
123
|
+
"audio_length": 1000, "audio_size": 12345, "bitrate": 128000,
|
|
124
|
+
"word_count": 50, "audio_format": "mp3", "audio_channel": 1,
|
|
125
|
+
"audio_sample_rate": 32000, "invisible_character_ratio": 0
|
|
126
|
+
}
|
|
127
|
+
}
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
`extra_info.usage_characters` 是**计费字符数**。
|
|
131
|
+
|
|
132
|
+
## 4. 语音合成(异步)—— 与同步有多处差异
|
|
133
|
+
|
|
134
|
+
本项目走的是异步路由,以下差异必须注意:
|
|
135
|
+
|
|
136
|
+
| 差异点 | 同步 | 异步 |
|
|
137
|
+
|---|---|---|
|
|
138
|
+
| `stream` / `output_format` / `timber_weights` / `subtitle_enable` / `stream_options` | 有 | **没有** |
|
|
139
|
+
| `text` 上限 | < 10000 字符 | **5 万字符** |
|
|
140
|
+
| `text_file_id` | 无 | **有**,与 `text` 二选一必填;txt <100000 字符 或 zip;zip 内 json 支持 `title`/`content`/`extra` 三字段,三者齐全则产出 3 组共 9 个文件 |
|
|
141
|
+
| `voice_setting` | 可选 | **整个 object 必填** |
|
|
142
|
+
| `voice_setting` 内字段 | `latex_read` / `text_normalization` | **`english_normalization`**(默认 false) |
|
|
143
|
+
| 采样率字段名 | `sample_rate` | **`audio_sample_rate`** |
|
|
144
|
+
| `format` 枚举 | mp3/pcm/flac/wav | mp3/pcm/flac/wav/**pcmu_raw**/**pcmu_wav**/**opus** |
|
|
145
|
+
|
|
146
|
+
- `pcmu_*` 为 G.711 μ-law 8kHz
|
|
147
|
+
- `opus` 仅支持采样率 8000/12000/16000/24000/48000,其他值会报错
|
|
148
|
+
- ⚠️ `audio_setting.channel` 文档正文写「可选范围 [1,2],默认值为 1」但 default 标注为 `2`,**文档自相矛盾,建议显式传值**
|
|
149
|
+
|
|
150
|
+
响应:`{ task_id, details: { usage_characters } }`,再走 `/v3/async/task-result` 取 `audios[].audio_url`。
|
|
151
|
+
|
|
152
|
+
## 5. 适配要点
|
|
153
|
+
|
|
154
|
+
- **`emotion` 在 2.8 上不生效**,当前项目只接 2.8 路由,该参数应隐藏或在切到 2.6 时才显示。
|
|
155
|
+
- 同步与异步的字段名不同(`sample_rate` vs `audio_sample_rate`、`text_normalization` vs `english_normalization`),不能共用同一个 builder 分支。
|
|
156
|
+
- 声音克隆的 168 小时失效规则需要在产品侧提示用户,否则会出现「克隆成功但过几天音色不见了」。
|
|
157
|
+
- 声音克隆试听会额外产生 TTS 费用,计价展示应体现 ¥9.9 音色费 + 试听字符费两部分。
|
|
158
|
+
- `audio_url` 字段以 `_url` 结尾 → 走 `public-url` 模式,**声音克隆依赖 KIE API Key**。
|
|
159
|
+
|
|
160
|
+
## 6. 原始链接索引
|
|
161
|
+
|
|
162
|
+
| 信息 | 链接 | 是否需登录 |
|
|
163
|
+
|---|---|---|
|
|
164
|
+
| 声音克隆 | https://ppio.com/docs/models/reference-minimax-voice-cloning | 否 |
|
|
165
|
+
| Speech 2.8 HD 同步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-hd | 否 |
|
|
166
|
+
| Speech 2.8 HD 异步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-hd-async | 否 |
|
|
167
|
+
| Speech 2.8 Turbo 同步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-turbo | 否 |
|
|
168
|
+
| Speech 2.8 Turbo 异步 | https://ppio.com/docs/models/reference-minimax-speech-2.8-turbo-async | 否 |
|
|
169
|
+
| 定价页(音频 tab) | https://ppio.com/pricing | 否 |
|
|
170
|
+
| 模型注册表(含计费表达式) | https://api-server.ppio.com/v1/product/multimodal-model/list?returnSchema=true | 否 |
|
|
@@ -1,89 +1,89 @@
|
|
|
1
|
-
# Nano Banana 2 · APIMart
|
|
2
|
-
|
|
3
|
-
| 项目 | 内容 |
|
|
4
|
-
|---|---|
|
|
5
|
-
| 最后更新 | 2026-08-28 |
|
|
6
|
-
| 模态 | 图片 |
|
|
7
|
-
| 供应商 | APIMart(聚合平台) |
|
|
8
|
-
| 平台模型 ID | 标准版 `gemini-3.1-flash-image-preview`(别名 `nano-banana-2-ext`)<br>官方版 `gemini-3.1-flash-image-preview-official`(别名 `nano-banana-2`) |
|
|
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
|
-
> **Nano Banana 2 Lite 已拆分为独立文档**:[Nano-Banana-2-Lite_APIMart.md](../Nano-Banana-2-Lite/Nano-Banana-2-Lite_APIMart.md)。它在代码里对应独立的 `canonicalModelId: nano-banana-2-lite`([catalog/apimart/nano-banana-2-lite.model.ts](../../../src/catalog/apimart/nano-banana-2-lite.model.ts)),是独立产品模型,不是本模型的渠道或分辨率选项——本文件只覆盖主模型的标准版 / 官方版两条渠道。
|
|
14
|
-
|
|
15
|
-
---
|
|
16
|
-
|
|
17
|
-
## 1. 接入协议
|
|
18
|
-
|
|
19
|
-
- **Base URL**:`https://api.apimart.ai`
|
|
20
|
-
- **鉴权**:`Authorization: Bearer <API_KEY>`
|
|
21
|
-
- **提交**:`POST /v1/images/generations` → `{ code, data: [{ status: "submitted", task_id }] }`
|
|
22
|
-
- **查询**:`GET /v1/tasks/{task_id}`,读 `result.images`
|
|
23
|
-
- **回调**(仅 Lite 文档明确提供):`webhook` 参数传 base 地址,平台回调 `webhook + /callback`(不转发上游),仍建议保留轮询兜底
|
|
24
|
-
|
|
25
|
-
---
|
|
26
|
-
|
|
27
|
-
## 2. 主模型 `gemini-3.1-flash-image-preview` / `-official`
|
|
28
|
-
|
|
29
|
-
### 2.1 能力
|
|
30
|
-
|
|
31
|
-
文生图 / 图生图;最多 **14 张**参考图;最高 **4K**;支持**极端宽高比**(1:4、4:1、1:8、8:1);集成 **Google Search 搜索增强**。
|
|
32
|
-
|
|
33
|
-
### 2.2 请求参数
|
|
34
|
-
|
|
35
|
-
| 字段 | 类型 | 必填 | 默认 | 取值与说明 |
|
|
36
|
-
|---|---|---|---|---|
|
|
37
|
-
| `model` | string | 必填 | `gemini-3.1-flash-image-preview` | 标准版 `gemini-3.1-flash-image-preview`(别名 `nano-banana-2-ext`);官方版 `gemini-3.1-flash-image-preview-official`(别名 `nano-banana-2`) |
|
|
38
|
-
| `prompt` | string | 必填 | — | 图像生成描述 |
|
|
39
|
-
| `size` | string | 可选 | — | `auto`、`1:1`、`3:2`、`2:3`、`4:3`、`3:4`、`16:9`、`9:16`、`5:4`、`4:5`、`21:9`、`1:4`、`4:1`、`1:8`、`8:1`。**`auto` 时文生图默认 `1:1` 或 `16:9`;图生图按上游返回比例为准——建议始终显式指定** |
|
|
40
|
-
| `resolution` | string | 可选 | `1K` | `0.5K`(约 512px)/ `1K`(约 1024px)/ `2K`(约 2048px)/ `4K`(约 4096px)。**不同分辨率计费不同** |
|
|
41
|
-
| `n` | integer | 可选 | `1` | **取值只能是 1**。必须传纯数字 |
|
|
42
|
-
| `image_urls` | array | 可选 | — | 参考图。**最多 14 张**(建议最多 10 张物体参考 + 4 张角色参考);单张 ≤ 10 MB;格式 jpeg/png/webp;支持公网 URL 或完整 Data URI(前缀不能省) |
|
|
43
|
-
| `google_search` | boolean | 可选 | `false` | Google **文字**搜索增强,适合需要真实信息的场景 |
|
|
44
|
-
| `google_image_search` | boolean | 可选 | `false` | Google **图片**搜索增强。**必须配合 `google_search: true`** |
|
|
45
|
-
| `official_fallback` | boolean | 可选 | `false` | 官方渠道兜底。**使用 `-official` 模型时不能带此参数** |
|
|
46
|
-
| `nsfw_check` | boolean | 可选 | `false` | `true` 时用 `omni-moderation-latest` 预审 |
|
|
47
|
-
|
|
48
|
-
### 2.3 价格
|
|
49
|
-
|
|
50
|
-
来源:[APIMart 定价中心](https://apimart.ai/zh/pricing)与[Nano Banana 3 模型页](https://apimart.ai/zh/model/nano-banana-3-api)(2026-08-28,1 Credit ≈ $0.1)。
|
|
51
|
-
|
|
52
|
-
**NANO-BANANA-2-EXT**(按张,5 档)
|
|
53
|
-
|
|
54
|
-
| 规格 | 我们的价格 | 官方价 | 节省 |
|
|
55
|
-
|---|---|---|---|
|
|
56
|
-
| 默认 / 0.5K / 1K | 0.15 Credits/张 ≈ **$0.015/张** | $0.01875 | 20% |
|
|
57
|
-
| 2K | 0.2 Credits/张 ≈ **$0.02/张** | $0.025 | 20% |
|
|
58
|
-
| 4K | 0.25 Credits/张 ≈ **$0.025/张** | $0.03125 | 20% |
|
|
59
|
-
|
|
60
|
-
**NANO-BANANA-2**(官方渠道,按 token)
|
|
61
|
-
|
|
62
|
-
| 计费项 | 我们的价格 | 官方价 |
|
|
63
|
-
|---|---|---|
|
|
64
|
-
| 文本输入 | 4 Credits/M ≈ $0.4/M | $0.5/M |
|
|
65
|
-
| 图片输入 | 4 Credits/M ≈ $0.4/M | $0.5/M |
|
|
66
|
-
| 文本输出 | 24 Credits/M ≈ $2.4/M | $3/M |
|
|
67
|
-
| 图片输出 | 480 Credits/M ≈ **$48/M** | $60/M |
|
|
68
|
-
|
|
69
|
-
SDK 对官方渠道采用模型页给出的当前单张估算:0.5K/1K **$0.0536**、2K **$0.0808**、4K **$0.1208**;实际账单仍按 token 结算。
|
|
70
|
-
|
|
71
|
-
---
|
|
72
|
-
|
|
73
|
-
## 3. 适配要点
|
|
74
|
-
|
|
75
|
-
- 本项目默认**绝对不显示**:`seed`、负面提示词。APIMart 这两个渠道都没有这两个字段。
|
|
76
|
-
- 主模型 `n` 只能是 1;`n` 必须是数字类型。
|
|
77
|
-
- `size: auto` 在文生图与图生图下行为不同,建议永远显式下发比例。
|
|
78
|
-
- `google_image_search` 依赖 `google_search`,两者要做联动。
|
|
79
|
-
- SDK 用首位 `apimartNanoBanana2Channel` 参数表达渠道,默认 `standard` 保持 0.1.5 的 EXT 请求;`official` 只切换为精确官方模型 ID,不发送 `official_fallback`。
|
|
80
|
-
- Lite 版本不要并入本模型:分辨率档位、比例集合、`n` 上限、搜索增强、计费方式都不同,是独立产品,见 [Nano-Banana-2-Lite_APIMart.md](../Nano-Banana-2-Lite/Nano-Banana-2-Lite_APIMart.md)。
|
|
81
|
-
|
|
82
|
-
## 4. 原始链接索引
|
|
83
|
-
|
|
84
|
-
| 信息 | 链接 | 是否需登录 |
|
|
85
|
-
|---|---|---|
|
|
86
|
-
| Nano banana2 图像生成(主模型) | https://docs.apimart.ai/cn/api-reference/images/gemini-3.1-flash/generation | 否 |
|
|
87
|
-
| 获取任务状态 | https://docs.apimart.ai/cn/api-reference/tasks/status | 否 |
|
|
88
|
-
| 定价中心(搜 NANO-BANANA-2-EXT / NANO-BANANA-2) | https://apimart.ai/zh/pricing | 否 |
|
|
89
|
-
| API Key 管理 | https://apimart.ai/keys | **是** |
|
|
1
|
+
# Nano Banana 2 · APIMart
|
|
2
|
+
|
|
3
|
+
| 项目 | 内容 |
|
|
4
|
+
|---|---|
|
|
5
|
+
| 最后更新 | 2026-08-28 |
|
|
6
|
+
| 模态 | 图片 |
|
|
7
|
+
| 供应商 | APIMart(聚合平台) |
|
|
8
|
+
| 平台模型 ID | 标准版 `gemini-3.1-flash-image-preview`(别名 `nano-banana-2-ext`)<br>官方版 `gemini-3.1-flash-image-preview-official`(别名 `nano-banana-2`) |
|
|
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
|
+
> **Nano Banana 2 Lite 已拆分为独立文档**:[Nano-Banana-2-Lite_APIMart.md](../Nano-Banana-2-Lite/Nano-Banana-2-Lite_APIMart.md)。它在代码里对应独立的 `canonicalModelId: nano-banana-2-lite`([catalog/apimart/nano-banana-2-lite.model.ts](../../../src/catalog/apimart/nano-banana-2-lite.model.ts)),是独立产品模型,不是本模型的渠道或分辨率选项——本文件只覆盖主模型的标准版 / 官方版两条渠道。
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## 1. 接入协议
|
|
18
|
+
|
|
19
|
+
- **Base URL**:`https://api.apimart.ai`
|
|
20
|
+
- **鉴权**:`Authorization: Bearer <API_KEY>`
|
|
21
|
+
- **提交**:`POST /v1/images/generations` → `{ code, data: [{ status: "submitted", task_id }] }`
|
|
22
|
+
- **查询**:`GET /v1/tasks/{task_id}`,读 `result.images`
|
|
23
|
+
- **回调**(仅 Lite 文档明确提供):`webhook` 参数传 base 地址,平台回调 `webhook + /callback`(不转发上游),仍建议保留轮询兜底
|
|
24
|
+
|
|
25
|
+
---
|
|
26
|
+
|
|
27
|
+
## 2. 主模型 `gemini-3.1-flash-image-preview` / `-official`
|
|
28
|
+
|
|
29
|
+
### 2.1 能力
|
|
30
|
+
|
|
31
|
+
文生图 / 图生图;最多 **14 张**参考图;最高 **4K**;支持**极端宽高比**(1:4、4:1、1:8、8:1);集成 **Google Search 搜索增强**。
|
|
32
|
+
|
|
33
|
+
### 2.2 请求参数
|
|
34
|
+
|
|
35
|
+
| 字段 | 类型 | 必填 | 默认 | 取值与说明 |
|
|
36
|
+
|---|---|---|---|---|
|
|
37
|
+
| `model` | string | 必填 | `gemini-3.1-flash-image-preview` | 标准版 `gemini-3.1-flash-image-preview`(别名 `nano-banana-2-ext`);官方版 `gemini-3.1-flash-image-preview-official`(别名 `nano-banana-2`) |
|
|
38
|
+
| `prompt` | string | 必填 | — | 图像生成描述 |
|
|
39
|
+
| `size` | string | 可选 | — | `auto`、`1:1`、`3:2`、`2:3`、`4:3`、`3:4`、`16:9`、`9:16`、`5:4`、`4:5`、`21:9`、`1:4`、`4:1`、`1:8`、`8:1`。**`auto` 时文生图默认 `1:1` 或 `16:9`;图生图按上游返回比例为准——建议始终显式指定** |
|
|
40
|
+
| `resolution` | string | 可选 | `1K` | `0.5K`(约 512px)/ `1K`(约 1024px)/ `2K`(约 2048px)/ `4K`(约 4096px)。**不同分辨率计费不同** |
|
|
41
|
+
| `n` | integer | 可选 | `1` | **取值只能是 1**。必须传纯数字 |
|
|
42
|
+
| `image_urls` | array | 可选 | — | 参考图。**最多 14 张**(建议最多 10 张物体参考 + 4 张角色参考);单张 ≤ 10 MB;格式 jpeg/png/webp;支持公网 URL 或完整 Data URI(前缀不能省) |
|
|
43
|
+
| `google_search` | boolean | 可选 | `false` | Google **文字**搜索增强,适合需要真实信息的场景 |
|
|
44
|
+
| `google_image_search` | boolean | 可选 | `false` | Google **图片**搜索增强。**必须配合 `google_search: true`** |
|
|
45
|
+
| `official_fallback` | boolean | 可选 | `false` | 官方渠道兜底。**使用 `-official` 模型时不能带此参数** |
|
|
46
|
+
| `nsfw_check` | boolean | 可选 | `false` | `true` 时用 `omni-moderation-latest` 预审 |
|
|
47
|
+
|
|
48
|
+
### 2.3 价格
|
|
49
|
+
|
|
50
|
+
来源:[APIMart 定价中心](https://apimart.ai/zh/pricing)与[Nano Banana 3 模型页](https://apimart.ai/zh/model/nano-banana-3-api)(2026-08-28,1 Credit ≈ $0.1)。
|
|
51
|
+
|
|
52
|
+
**NANO-BANANA-2-EXT**(按张,5 档)
|
|
53
|
+
|
|
54
|
+
| 规格 | 我们的价格 | 官方价 | 节省 |
|
|
55
|
+
|---|---|---|---|
|
|
56
|
+
| 默认 / 0.5K / 1K | 0.15 Credits/张 ≈ **$0.015/张** | $0.01875 | 20% |
|
|
57
|
+
| 2K | 0.2 Credits/张 ≈ **$0.02/张** | $0.025 | 20% |
|
|
58
|
+
| 4K | 0.25 Credits/张 ≈ **$0.025/张** | $0.03125 | 20% |
|
|
59
|
+
|
|
60
|
+
**NANO-BANANA-2**(官方渠道,按 token)
|
|
61
|
+
|
|
62
|
+
| 计费项 | 我们的价格 | 官方价 |
|
|
63
|
+
|---|---|---|
|
|
64
|
+
| 文本输入 | 4 Credits/M ≈ $0.4/M | $0.5/M |
|
|
65
|
+
| 图片输入 | 4 Credits/M ≈ $0.4/M | $0.5/M |
|
|
66
|
+
| 文本输出 | 24 Credits/M ≈ $2.4/M | $3/M |
|
|
67
|
+
| 图片输出 | 480 Credits/M ≈ **$48/M** | $60/M |
|
|
68
|
+
|
|
69
|
+
SDK 对官方渠道采用模型页给出的当前单张估算:0.5K/1K **$0.0536**、2K **$0.0808**、4K **$0.1208**;实际账单仍按 token 结算。
|
|
70
|
+
|
|
71
|
+
---
|
|
72
|
+
|
|
73
|
+
## 3. 适配要点
|
|
74
|
+
|
|
75
|
+
- 本项目默认**绝对不显示**:`seed`、负面提示词。APIMart 这两个渠道都没有这两个字段。
|
|
76
|
+
- 主模型 `n` 只能是 1;`n` 必须是数字类型。
|
|
77
|
+
- `size: auto` 在文生图与图生图下行为不同,建议永远显式下发比例。
|
|
78
|
+
- `google_image_search` 依赖 `google_search`,两者要做联动。
|
|
79
|
+
- SDK 用首位 `apimartNanoBanana2Channel` 参数表达渠道,默认 `standard` 保持 0.1.5 的 EXT 请求;`official` 只切换为精确官方模型 ID,不发送 `official_fallback`。
|
|
80
|
+
- Lite 版本不要并入本模型:分辨率档位、比例集合、`n` 上限、搜索增强、计费方式都不同,是独立产品,见 [Nano-Banana-2-Lite_APIMart.md](../Nano-Banana-2-Lite/Nano-Banana-2-Lite_APIMart.md)。
|
|
81
|
+
|
|
82
|
+
## 4. 原始链接索引
|
|
83
|
+
|
|
84
|
+
| 信息 | 链接 | 是否需登录 |
|
|
85
|
+
|---|---|---|
|
|
86
|
+
| Nano banana2 图像生成(主模型) | https://docs.apimart.ai/cn/api-reference/images/gemini-3.1-flash/generation | 否 |
|
|
87
|
+
| 获取任务状态 | https://docs.apimart.ai/cn/api-reference/tasks/status | 否 |
|
|
88
|
+
| 定价中心(搜 NANO-BANANA-2-EXT / NANO-BANANA-2) | https://apimart.ai/zh/pricing | 否 |
|
|
89
|
+
| API Key 管理 | https://apimart.ai/keys | **是** |
|