@mrgoonie/multix 0.1.0-beta → 0.1.0-beta.1

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.
Files changed (5) hide show
  1. package/CHANGELOG.md +8 -0
  2. package/README.md +23 -5
  3. package/dist/cli.js +409 -192
  4. package/package.json +1 -1
  5. package/skill/SKILL.md +17 -5
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mrgoonie/multix",
3
- "version": "0.1.0-beta",
3
+ "version": "0.1.0-beta.1",
4
4
  "description": "AI multimodal CLI — OpenAI, Gemini, MiniMax, OpenRouter, Leonardo, BytePlus, ElevenLabs, ffmpeg, ImageMagick, doc-to-md",
5
5
  "type": "module",
6
6
  "bin": {
package/skill/SKILL.md CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: multix
3
- description: AI multimodal CLI — generate and edit images (OpenAI, Codex driver, Gemini Nano Banana, Imagen, MiniMax, OpenRouter, Leonardo, BytePlus Seedream), generate video (Veo, Hailuo, Seedance, Leonardo), TTS/STT/music (OpenAI, Gemini Flash TTS, MiniMax, ElevenLabs), 3D models (Hyper3D), analyze/transcribe media, convert documents to Markdown, optimize media via ffmpeg/ImageMagick. Use whenever the user wants to create, edit, or transform images/video/audio/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, ElevenLabs voice cloning, or asks for batch media optimization.
4
- version: 0.1.0-beta # x-release-please-version
3
+ description: AI multimodal CLI — generate and edit images (OpenAI, Codex driver, Gemini Nano Banana, Imagen, MiniMax, OpenRouter, Leonardo, BytePlus Seedream), generate video (Veo, Hailuo, Seedance, Leonardo), TTS/STT/music (OpenAI, Gemini Flash TTS, MiniMax, ElevenLabs), 3D models (Hyper3D), analyze/transcribe/extract media with Gemini 3.5 Flash text-output models, convert documents to Markdown, optimize media via ffmpeg/ImageMagick. Use whenever the user wants to create, edit, or transform images/video/audio/documents from a CLI, mentions any of: OpenAI, Codex image driver, Gemini 3.5 Flash, image-to-image, i2i, image edit, watercolor/cyberpunk style transfer, reference image, OpenRouter, Nano Banana, Flux, Seedream, Veo, Hailuo, ElevenLabs voice cloning, or asks for batch media optimization.
4
+ version: 0.1.0-beta.1 # x-release-please-version
5
5
  ---
6
6
 
7
7
  # multix — AI Multimodal CLI
@@ -45,6 +45,17 @@ npm install -g @mrgoonie/multix
45
45
  multix check [--verbose]
46
46
  ```
47
47
 
48
+ ## Gemini text-output tasks
49
+
50
+ `gemini-3.5-flash` is the default for Gemini analyze, transcribe, extract, and doc conversion. It is text-output only; use Nano Banana/Imagen for images, Veo for video, and Gemini Flash TTS for speech. Override analyze/transcribe/extract with `GEMINI_MODEL` or `MULTIMODAL_MODEL`; override doc conversion with `--model`.
51
+
52
+ ```bash
53
+ multix gemini analyze --files photo.jpg --prompt "Describe this" [--model gemini-3.5-flash]
54
+ multix gemini transcribe --files meeting.mp4 [--model gemini-3.5-flash]
55
+ multix gemini extract --files report.pdf --prompt "Extract tables as JSON" [--model gemini-3.5-flash]
56
+ multix doc convert --input report.pdf [--model gemini-3.5-flash]
57
+ ```
58
+
48
59
  ## Image generation
49
60
 
50
61
  | Provider | Command | Notes |
@@ -176,8 +187,8 @@ multix elevenlabs sfx --text "car engine starting" [--duration-seconds 5]
176
187
  # 3D (BytePlus Hyper3D / Hitem3d)
177
188
  multix byteplus 3d --input-image ./front.png ./side.png --prompt "Generate from these views"
178
189
 
179
- # Docs → Markdown (Gemini)
180
- multix doc convert --input report.pdf [--auto-name] [--output ./out.md]
190
+ # Docs → Markdown (Gemini text-output)
191
+ multix doc convert --input report.pdf [--model gemini-3.5-flash] [--auto-name] [--output ./out.md]
181
192
 
182
193
  # Media optimization (ffmpeg + ImageMagick)
183
194
  multix media optimize --input <file> --output <file> [--target-size <MB>] [--quality 85] [--max-width 1920]
@@ -199,7 +210,8 @@ Files saved under `./multix-output/` by default. Override with `MULTIX_OUTPUT_DI
199
210
  | `OPENROUTER_FALLBACK_MODELS` | CSV; applies to `generate` AND `i2i` |
200
211
  | `OPENROUTER_VIDEO_MODEL` | Default OpenRouter video model (default `google/veo-3.1`) |
201
212
  | `OPENROUTER_SITE_URL` / `OPENROUTER_APP_NAME` | HTTP-Referer / X-Title headers |
202
- | `IMAGE_GEN_MODEL` / `VIDEO_GEN_MODEL` / `MULTIMODAL_MODEL` | Override Gemini model defaults |
213
+ | `GEMINI_MODEL` / `MULTIMODAL_MODEL` | Override Gemini analyze/transcribe/extract default (doc convert uses `--model`) |
214
+ | `IMAGE_GEN_MODEL` / `GEMINI_IMAGE_GEN_MODEL` / `VIDEO_GEN_MODEL` | Override Gemini media-generation model defaults |
203
215
  | `LEONARDO_DEFAULT_MODEL` / `LEONARDO_VIDEO_MODEL` | Leonardo model defaults |
204
216
  | `BYTEPLUS_IMAGE_MODEL` / `BYTEPLUS_VIDEO_MODEL` / `BYTEPLUS_3D_MODEL` | BytePlus model defaults |
205
217
  | `BYTEPLUS_VIDEO_PARAMS_MODE` | `flags` (default) or `structured` |