@mrgoonie/multix 0.0.8 → 0.1.0-beta.1

package/CHANGELOG.md

@@ -5,6 +5,21 @@ 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).
 
+## [0.1.0-beta.1](https://github.com/mrgoonie/multix-cli/compare/v0.1.0-beta...v0.1.0-beta.1) (2026-07-29)
+
+
+### Added
+
+* add Gemini Omni video support ([#28](https://github.com/mrgoonie/multix-cli/issues/28)) ([c8557e6](https://github.com/mrgoonie/multix-cli/commit/c8557e64cfb9bb19b79ae50967664f11d98cb9b8))
+* **gemini:** support Gemini 3.5 Flash text defaults ([#17](https://github.com/mrgoonie/multix-cli/issues/17)) ([e31491e](https://github.com/mrgoonie/multix-cli/commit/e31491ed01f9aeb7ec52421c8cd76d26b797ddf8))
+
+## [0.1.0-beta](https://github.com/mrgoonie/multix-cli/compare/v0.0.8...v0.1.0-beta) (2026-05-19)
+
+
+### Added
+
+* **openai:** add provider media commands ([#9](https://github.com/mrgoonie/multix-cli/issues/9)) ([4622102](https://github.com/mrgoonie/multix-cli/commit/46221029ac98f6da03653397d20e2e604f7f39c1))
+
 ## [0.0.8] - 2026-05-11
 
 ### Fixed

package/README.md

@@ -2,7 +2,7 @@
 
 AI multimodal CLI — generate images/video/speech/music, analyze and transcribe media files, convert documents to Markdown, and optimize media with ffmpeg/ImageMagick.
 
-Supports **Gemini** (analyze, transcribe, generate, Veo video, Flash TTS), **MiniMax** (image, video, speech, music), **OpenRouter** (image generation), **Leonardo.Ai** (image, video, upscale), **BytePlus** (Seedream image, Seedance video, Hyper3D / Hitem3d 3D), and **ElevenLabs** (TTS, voice cloning, STT, voice changer, SFX, music, dubbing, isolation, alignment).
+Supports **OpenAI** (image, image edits, TTS, STT, optional Codex image driver), **Gemini** (analyze, transcribe, generate, Veo video, Flash TTS), **MiniMax** (image, video, speech, music), **OpenRouter** (image generation), **Leonardo.Ai** (image, video, upscale), **BytePlus** (Seedream image, Seedance video, Hyper3D / Hitem3d 3D), and **ElevenLabs** (TTS, voice cloning, STT, voice changer, SFX, music, dubbing, isolation, alignment).
 
 ## Install
 
@@ -14,6 +14,11 @@ npx -p @mrgoonie/multix multix --help
 
 **Requirements:** Node >= 20. For media commands: `ffmpeg` and `magick` (ImageMagick 7+) on PATH.
 
+## Release channels
+
+- `main` uses Release Please for stable releases. It creates release PRs from conventional commits, bumps semver, updates `CHANGELOG.md`, tags `vX.Y.Z`, and publishes npm with dist-tag `latest`.
+- `dev` uses Release Please for beta releases. It creates prerelease PRs like `vX.Y.Z-beta.N` from conventional commits and publishes npm with dist-tag `beta`.
+
 ## Quick start
 
 ```bash
@@ -23,6 +28,9 @@ multix check
 # Generate an image with Gemini
 multix gemini generate --prompt "A sunset over mountains" --aspect-ratio 16:9
 
+# Generate an image with OpenAI
+multix openai generate --prompt "A clean product photo of a glass espresso cup"
+
 # Analyze an image
 multix gemini analyze --files photo.jpg --prompt "Describe this"
 
@@ -40,6 +48,7 @@ Set at least one provider key. Add to `.env` in your project root or `~/.multix/
 | Variable | Required | Purpose |
 |---|---|---|
 | `GEMINI_API_KEY` | For Gemini | [AI Studio](https://aistudio.google.com/apikey) |
+| `OPENAI_API_KEY` | For OpenAI API | [OpenAI](https://platform.openai.com/api-keys) |
 | `OPENROUTER_API_KEY` | For OpenRouter | [OpenRouter](https://openrouter.ai/settings/keys) |
 | `MINIMAX_API_KEY` | For MiniMax | [MiniMax](https://platform.minimax.io/user-center/basic-information/interface-key) |
 | `LEONARDO_API_KEY` | For Leonardo | [Leonardo](https://app.leonardo.ai/settings/api-keys) |
@@ -57,9 +66,12 @@ Set at least one provider key. Add to `.env` in your project root or `~/.multix/
 | `MULTIX_OUTPUT_DIR` | No | Override default output dir (`./multix-output`) |
 | `OPENROUTER_IMAGE_MODEL` | No | Default OpenRouter model |
 | `OPENROUTER_FALLBACK_MODELS` | No | Comma-separated fallback model ids |
-| `IMAGE_GEN_MODEL` | No | Override Gemini image generation model |
+| `OPENAI_IMAGE_MODEL` | No | Default OpenAI image model (default `gpt-image-2`) |
+| `OPENAI_TTS_MODEL` | No | Default OpenAI TTS model (default `gpt-4o-mini-tts`) |
+| `OPENAI_STT_MODEL` | No | Default OpenAI STT model (default `gpt-4o-transcribe`) |
+| `GEMINI_MODEL` / `MULTIMODAL_MODEL` | No | Override Gemini analyze/transcribe/extract model (doc convert uses `--model`; default `gemini-3.5-flash`) |
+| `IMAGE_GEN_MODEL` / `GEMINI_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_TTS_MODEL` / `TTS_MODEL` | No | Override Gemini TTS model (default `gemini-3.1-flash-tts-preview`) |
 
 Priority: `process.env` > `cwd/.env` > `~/.multix/.env`.
@@ -68,13 +80,13 @@ Priority: `process.env` > `cwd/.env` > `~/.multix/.env`.
 
 ### `multix check`
 
-Validate setup: tooling (ffmpeg, magick), API keys, Gemini live ping.
+Validate setup: tooling (ffmpeg, magick), API keys, Gemini live ping, and experimental authenticated Codex image capability. Codex is checked when no API key is configured, or in `--verbose` mode.
 
 ```
 multix check [--verbose]
 ```
 
-Exits 0 if at least one provider key is configured. Exits 1 if no keys found or Gemini auth fails.
+Exits 0 if at least one provider key is configured, or authenticated Codex image capability is available. Exits 1 if no provider is usable or Gemini auth fails.
 
 ### `multix gemini`
 
@@ -100,6 +112,18 @@ multix gemini generate-video --prompt "Ocean waves" [--model veo-3.1-generate-pr
 # Image-to-video with Veo (alias: i2v) [EXPERIMENTAL]
 multix gemini image-to-video <imagePath> --prompt "camera pans left" [--last-frame <path>] [--model veo-3.1-generate-preview] [--resolution 1080p] [--aspect-ratio 16:9] [--output <path>] [-v]
 
+# Generate or edit video with Gemini Omni Flash [PAID PREVIEW]
+# Use either local image guidance or one local video, not both.
+multix gemini omni-video --prompt "A paper airplane flies through a sunlit office" \
+  [--image ./frame.png] [--video ./clip.mp4] [--previous-interaction-id <id>] \
+  [--upload-timeout 300000] [--output ./result.mp4] [-v]
+
+# Chain a Lite-generated image into a Lite edit
+multix gemini generate --model gemini-3.1-flash-lite-image \
+  --prompt "A minimal coffee package on a pale blue background" --size 1K --output package.png
+multix gemini image-to-image --model gemini-3.1-flash-lite-image \
+  --ref package.png --prompt "Add hand-drawn botanical details" --size 1K --output package-botanical.png
+
 # Text-to-speech (Gemini 3.1 Flash TTS — single & multi-speaker)
 multix gemini generate-speech (--text|--prompt) "Say cheerfully: Have a wonderful day!" [--model gemini-3.1-flash-tts-preview] [--voice Kore] [--output-format wav|pcm] [--output <path>] [-v]
 
@@ -109,13 +133,19 @@ multix gemini generate-speech --text "Joe: How's it going? Jane: Not too bad!" \
 ```
 
 **Gemini models:**
-- Analysis: `gemini-2.5-flash` (default)
-- 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)
+- Text output (analyze, transcribe, extract, doc convert): `gemini-3.5-flash` (default), `gemini-2.5-flash` (manual override)
+- Image gen: `gemini-3.1-flash-image-preview` (Nano Banana 2, fastest), `gemini-3.1-flash-lite-image` (Nano Banana 2 Lite), `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-3.5-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`
 
+**Gemini Omni Flash video:** a paid-tier preview for prompt-to-video and edits, producing 3–10 second 720p videos. It accepts local images or one local video; audio references, multiple videos, video extension/interpolation, and voice editing are unsupported. Uploaded-video editing is unavailable in the EEA, Switzerland, and the UK. Each run prints an interaction ID; use it with `--previous-interaction-id` for a follow-up edit. The CLI keeps no local history: continuation depends on Gemini-stored interactions (`store=true`), retained for up to 55 days on the paid tier and incompatible with `store=false`. The generated MP4 is saved in the standard output directory with an adjacent `.json` sidecar containing its provider, model, prompt, input basenames, timestamp, and interaction ID; `--output` copies the MP4 to the requested path.
+
+**Nano Banana 2 Lite:** use `gemini-3.1-flash-lite-image` with `generate` or `image-to-image`. Output is always 1K—do not request 2K or 4K. Supported aspect ratios are `1:1 3:2 2:3 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.
 
 ### `multix minimax`
@@ -163,6 +193,47 @@ multix openrouter video-models
 
 Fallback models from `OPENROUTER_FALLBACK_MODELS` (CSV) are appended to the chat-image payload automatically — applies to both `generate` and `image-to-image`. Override the default video model with `OPENROUTER_VIDEO_MODEL` (default `google/veo-3.1`).
 
+### `multix openai`
+
+```bash
+# Image generation via OpenAI Images API
+multix openai generate --prompt "A product photo of a titanium travel mug" \
+  [--model gpt-image-2] [--size 1024x1024] [--quality medium] [--format png] [--num-images 1] [--output <path>] [-v]
+
+# Use authenticated Codex CLI as an experimental image driver.
+# Requires manual `codex` login outside multix.
+multix openai generate --prompt "A poster for a midnight jazz club" --driver codex --output poster.png
+
+# Auto chooses OpenAI API when OPENAI_API_KEY exists, otherwise tries authenticated Codex.
+multix openai generate --prompt "Editorial portrait lighting" --driver auto
+
+# Image-to-image edits with one or more local/URL refs
+multix openai image-to-image --prompt "turn this into a watercolor travel sketch" --ref ./photo.jpg [--ref https://...] [--output sketch.png]
+
+# Text-to-speech
+multix openai generate-speech --text "Welcome to multix." [--voice alloy] [--output-format mp3|wav|aac|flac|opus|pcm] [--output speech.mp3]
+
+# Speech-to-text
+multix openai transcribe --input meeting.mp3 [--format text|json|diarized_json] [--language vi]
+
+# Known speaker refs must be paired by name and reference audio path/URL.
+multix openai transcribe --input call.mp3 --format json \
+  --known-speaker-name Alice --known-speaker-reference ./alice.wav \
+  --known-speaker-name Bob --known-speaker-reference ./bob.wav
+```
+
+**OpenAI models:** image `gpt-image-2` (default), TTS `gpt-4o-mini-tts` (default), STT `gpt-4o-transcribe` (default). The Codex driver is experimental and only handles image generation; `multix` does not authenticate Codex for you.
+
+**OpenAI STT format behavior:**
+
+| CLI format | Non-diarize GPT transcription models | Diarize model |
+|---|---|---|
+| `text` | Requests JSON from API, writes returned `text` | Requests JSON from API, writes returned `text` |
+| `json` | Requests JSON | Requests JSON |
+| `diarized_json` | Not supported | Requires `gpt-4o-transcribe-diarize` and defaults `chunking_strategy=auto` |
+
+Known-speaker diarization uses paired `--known-speaker-name` and `--known-speaker-reference` flags; names and references must have the same count.
+
 ### `multix leonardo`
 
 ```bash
@@ -346,7 +417,7 @@ 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-3.5-flash] [--prompt <str>] [-v]
 ```
 
 Converts PDFs, DOCX/XLSX/PPTX, images, and HTML/text files to Markdown via Gemini.