@mrgoonie/multix 0.8.0 → 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 +14 -0
- package/README.md +4 -1
- package/dist/cli.js +540 -256
- package/package.json +1 -1
- package/skill/SKILL.md +5 -3
package/package.json
CHANGED
package/skill/SKILL.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: multix
|
|
3
3
|
description: AI multimodal CLI — generate and edit images (OpenAI, Codex driver, Gemini Nano Banana, Imagen, MiniMax, OpenRouter, Leonardo, BytePlus Seedream, Cloudflare Workers AI FLUX.1 Schnell, fal.ai FLUX), generate video (Gemini Veo, MiniMax Hailuo, OpenRouter via Veo/Seedance/Kling, Leonardo via Motion/Veo/Kling/Hailuo/Seedance/LTX, BytePlus Seedance, Cloudflare AI Gateway via Replicate, fal.ai queue models), TTS/STT/music (OpenAI, Gemini Flash TTS incl. Gemini 3.8 with delivery-style control, MiniMax, Cloudflare Workers AI MeloTTS, ElevenLabs), 3D models (BytePlus Hyper3D/Hitem3d), analyze/transcribe media, convert documents to Markdown, optimize media via ffmpeg/ImageMagick, and self-update the CLI. Use whenever the user wants to create, edit, or transform images/video/audio/3D/documents from a CLI, mentions any of: OpenAI, Codex image driver, image-to-image, i2i, image edit, watercolor/cyberpunk style transfer, reference image, OpenRouter, Nano Banana, Flux, Seedream, Veo, Hailuo, Seedance, Kling, Cloudflare Workers AI, AI Gateway, fal.ai, video generation, text-to-video, image-to-video, i2v, ElevenLabs voice cloning, updating/upgrading multix, or asks for batch media optimization.
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.10.0 # x-release-please-version
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# multix — AI Multimodal CLI
|
|
@@ -48,7 +48,7 @@ CLOUDFLARE_API_TOKEN # Cloudflare Workers AI / AI Gateway token
|
|
|
48
48
|
# Video additionally requires CLOUDFLARE_AI_GATEWAY_ID and REPLICATE_API_TOKEN.
|
|
49
49
|
```
|
|
50
50
|
|
|
51
|
-
Priority: `process.env` > `cwd/.env` > `~/.multix/.env`.
|
|
51
|
+
Priority: `process.env` > `cwd/.env` > `~/.multix/.env`. Set `MULTIX_LEGACY_CLAUDE_ENV=1` to also read legacy AgentKit `.claude` env files (credential names only, lowest priority); `multix check -v` lists loaded env files.
|
|
52
52
|
|
|
53
53
|
## Gemini text-output tasks
|
|
54
54
|
|
|
@@ -323,7 +323,8 @@ Requires `cwebp` (libwebp: `brew install webp`, `apt install webp`) on `PATH`.
|
|
|
323
323
|
| `CLOUDFLARE_AI_GATEWAY_COLLECT_LOG_PAYLOAD` | Set `true` to explicitly opt in to AI Gateway request-payload collection; defaults to `false` |
|
|
324
324
|
| `REPLICATE_API_TOKEN` | Required for Cloudflare AI Gateway video |
|
|
325
325
|
| `CLOUDFLARE_AI_IMAGE_MODEL` / `CLOUDFLARE_AI_TTS_MODEL` | Fixed-model settings: only `@cf/black-forest-labs/flux-1-schnell` and `@cf/myshell-ai/melotts` respectively are accepted |
|
|
326
|
-
| `MULTIX_DISABLE_HOME_ENV` | `1` to skip `~/.multix/.env
|
|
326
|
+
| `MULTIX_DISABLE_HOME_ENV` | `1` to skip every home-directory env file (`~/.multix/.env`, `~/.claude/...`) |
|
|
327
|
+
| `MULTIX_LEGACY_CLAUDE_ENV` | `1` to also read legacy `.claude` env files (credential names only) |
|
|
327
328
|
|
|
328
329
|
## Quick examples for agents
|
|
329
330
|
|
|
@@ -350,6 +351,7 @@ multix byteplus i2v ./photo.jpg --prompt "camera slowly pans left"
|
|
|
350
351
|
# Transcribe / analyze media
|
|
351
352
|
multix gemini analyze --files ./video.mp4 --prompt "Summarize this video"
|
|
352
353
|
multix gemini transcribe --files ./audio.mp3
|
|
354
|
+
cat ./shot.png | multix gemini analyze --files - --prompt "Describe" # "-" reads stdin; --stdin-ext <ext> if undetected
|
|
353
355
|
multix elevenlabs transcribe --input ./audio.mp3 --diarize
|
|
354
356
|
|
|
355
357
|
# Compress / split media
|