@mrgoonie/multix 0.4.0 → 0.5.0

package/CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.5.0](https://github.com/mrgoonie/multix-cli/compare/v0.4.0...v0.5.0) (2026-07-30)
+
+
+### Added
+
+* **gemini:** default text tasks to 3.6 Flash ([#36](https://github.com/mrgoonie/multix-cli/issues/36)) ([ec1e019](https://github.com/mrgoonie/multix-cli/commit/ec1e0193dc9f8e0570ffc0f57901d5846b44c91f))
+
 ## [0.4.0](https://github.com/mrgoonie/multix-cli/compare/v0.3.0...v0.4.0) (2026-07-30)
 
 

package/README.md

@@ -84,7 +84,7 @@ Set at least one provider key. Add to `.env` in your project root or `~/.multix/
 | `OPENAI_STT_MODEL` | No | Default OpenAI STT model (default `gpt-4o-transcribe`) |
 | `IMAGE_GEN_MODEL` | No | Override Gemini image generation model |
 | `VIDEO_GEN_MODEL` | No | Override Gemini video generation model |
-| `MULTIMODAL_MODEL` | No | Override Gemini analysis model |
+| `GEMINI_MODEL` / `MULTIMODAL_MODEL` | No | Override Gemini analyze/transcribe/extract model (doc convert uses `--model`; default `gemini-3.6-flash`) |
 | `GEMINI_TTS_MODEL` / `TTS_MODEL` | No | Override Gemini TTS model (default `gemini-3.1-flash-tts-preview`) |
 
 Priority: `process.env` > `cwd/.env` > `~/.multix/.env`.
@@ -134,11 +134,13 @@ multix gemini generate-speech --text "Joe: How's it going? Jane: Not too bad!" \
 ```
 
 **Gemini models:**
-- Analysis: `gemini-2.5-flash` (default)
+- Text output (analyze, transcribe, extract, doc convert): `gemini-3.6-flash` (default), `gemini-3.5-flash` (manual override)
 - Image gen: `gemini-3.1-flash-image-preview` (Nano Banana 2, fastest), `gemini-3-pro-image-preview` (4K text), `imagen-4.0-generate-001` (production)
 - Video: `veo-3.1-generate-preview` (requires billing)
 - TTS: `gemini-3.1-flash-tts-preview` (default), `gemini-2.5-flash-preview-tts`, `gemini-2.5-pro-preview-tts`
 
+`gemini-3.6-flash` is a text-output model. Use Nano Banana/Imagen for images, Veo for video, and Gemini Flash TTS for speech.
+
 **Aspect ratios:** `1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9`
 
 **TTS voices (30 prebuilt):** Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima, Achird, Zubenelgenubi, Vindemiatrix, Sadachbia, Sadaltager, Sulafat. Audio is PCM s16le @ 24 kHz mono — saved as WAV (default) or raw PCM. Style is controlled via natural language in the prompt (`[whispers]`, `Say excitedly:`, etc.). No streaming; max 2 speakers; ~32k token context.
@@ -441,7 +443,7 @@ multix media batch --input-dir <dir> --output-dir <dir> [--quality 85] [--max-wi
 ### `multix doc`
 
 ```bash
-multix doc convert --input <files...> [--output <path>] [--auto-name] [--model gemini-2.5-flash] [--prompt <str>] [-v]
+multix doc convert --input <files...> [--output <path>] [--auto-name] [--model gemini-3.6-flash] [--prompt <str>] [-v]
 ```
 
 Converts PDFs, DOCX/XLSX/PPTX, images, and HTML/text files to Markdown via Gemini.

package/dist/cli.js

@@ -2563,9 +2563,10 @@ function sleep(ms) {
 var IMAGE_MODEL_DEFAULT = "gemini-3.1-flash-image-preview";
 var IMAGE_MODEL_FALLBACK = "gemini-2.5-flash-image";
 var VIDEO_MODEL_DEFAULT = "veo-3.1-generate-preview";
-var ANALYSIS_MODEL_DEFAULT = "gemini-2.5-flash";
+var TEXT_MODEL_DEFAULT = "gemini-3.6-flash";
+var ANALYSIS_MODEL_DEFAULT = TEXT_MODEL_DEFAULT;
 var TTS_MODEL_DEFAULT = "gemini-3.1-flash-tts-preview";
-var DOC_MODEL_DEFAULT = "gemini-2.5-flash";
+var DOC_MODEL_DEFAULT = TEXT_MODEL_DEFAULT;
 var IMAGEN_MODELS = /* @__PURE__ */ new Set([
   "imagen-4.0-generate-001",
   "imagen-4.0-ultra-generate-001",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mrgoonie/multix",
-  "version": "0.4.0",
+  "version": "0.5.0",
   "description": "AI multimodal CLI — OpenAI, Gemini, MiniMax, OpenRouter, Leonardo, BytePlus, ElevenLabs, ffmpeg, ImageMagick, doc-to-md",
   "type": "module",
   "bin": {

package/skill/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: multix
 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), 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), TTS/STT/music (OpenAI, Gemini Flash TTS, MiniMax, Cloudflare Workers AI MeloTTS, ElevenLabs), 3D models (BytePlus Hyper3D/Hitem3d), 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/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, video generation, text-to-video, image-to-video, i2v, ElevenLabs voice cloning, or asks for batch media optimization.
-version: 0.4.0 # x-release-please-version
+version: 0.5.0 # x-release-please-version
 ---
 
 # multix — AI Multimodal CLI
@@ -39,6 +39,10 @@ CLOUDFLARE_API_TOKEN  # Cloudflare Workers AI / AI Gateway token
 
 Priority: `process.env` > `cwd/.env` > `~/.multix/.env`.
 
+## Gemini text-output tasks
+
+`gemini-3.6-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`.
+
 Codex CLI can be used as an experimental OpenAI image driver after manual `codex login`:
 
 ```bash
@@ -257,7 +261,8 @@ Files saved under `./multix-output/` by default. Override with `MULTIX_OUTPUT_DI
 | `OPENROUTER_FALLBACK_MODELS` | CSV; applies to `generate` AND `i2i` |
 | `OPENROUTER_VIDEO_MODEL` | Default OpenRouter video model (default `google/veo-3.1`) |
 | `OPENROUTER_SITE_URL` / `OPENROUTER_APP_NAME` | HTTP-Referer / X-Title headers |
-| `IMAGE_GEN_MODEL` / `VIDEO_GEN_MODEL` / `MULTIMODAL_MODEL` | Override Gemini model defaults |
+| `GEMINI_MODEL` / `MULTIMODAL_MODEL` | Override Gemini analyze/transcribe/extract defaults (doc convert uses `--model`; default `gemini-3.6-flash`) |
+| `IMAGE_GEN_MODEL` / `VIDEO_GEN_MODEL` | Override Gemini media-generation defaults |
 | `LEONARDO_DEFAULT_MODEL` / `LEONARDO_VIDEO_MODEL` | Leonardo model defaults |
 | `BYTEPLUS_IMAGE_MODEL` / `BYTEPLUS_VIDEO_MODEL` / `BYTEPLUS_3D_MODEL` | BytePlus model defaults |
 | `BYTEPLUS_VIDEO_PARAMS_MODE` | `flags` (default) or `structured` |