How do I install the Voice skill?

Run npx skillmds@latest add octos-org/voice in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Voice skill do?

Batch ASR / OminiX TTS / Model Management It is listed under AI & ML on SkillMD.

Is Voice safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Voice?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Voice free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

octos-org (@octos-org) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Voice by octos-org — Agent Skill

Name: Voice
Author: octos-org

File contents

Batch ASR / OminiX TTS / Model Management

Speech-to-text uses ASR_API_URL when configured (the Octos/OMiniX JSON + base64 batch-transcription contract at POST /v1/audio/transcriptions, such as the local Whisper or Nemotron adapter); otherwise it falls back to Qwen3 ASR through local OminiX. Preset-voice text-to-speech with emotion control and model lifecycle management remain backed by local OminiX (Apple Silicon).

An empty ASR result is a successful no-speech rejection, not an error.

Boundary — when NOT to use this skill

Voice cloning / custom voice profiles → use mofa-fm (fm_tts, fm_voice_save, fm_voice_list, fm_voice_delete). This skill is preset-voice only.
Emotion prompts in fallback mode → not supported. When ominix-api is unreachable, voice_synthesize falls through to the macOS built-in say command, which auto-picks a system voice from the text language and ignores the prompt parameter.

Tools

Tool	Purpose
`voice_transcribe`	ASR — WAV/OGG/MP3/FLAC/M4A → text
`voice_synthesize`	Preset-voice TTS with optional emotion + speed
`list_models`	List loaded + catalog models on the local ominix-api
`download_model`	Pull a catalog model to local disk
`load_model`	Load a downloaded model into GPU memory
`unload_model`	Free a loaded model from GPU memory

Quick recipes

Transcribe a voice message

{"audio_path": "voice.ogg", "language": "Chinese"}

Synthesize plain speech

{"text": "Hello world", "language": "english", "speaker": "ryan"}

Synthesize with emotion

{"text": "我太开心了！", "speaker": "vivian", "prompt": "用兴奋激动的语气说话，充满热情和活力"}

After voice_synthesize returns a file path, deliver the audio with send_file.

Anti-patterns

Calling voice_synthesize with a prompt while ominix-api is down — the fallback (say) silently drops the emotion. Use list_models to confirm Qwen3-TTS is loaded before relying on emotion control.
Passing a non-preset speaker name (e.g. a cloned voice id) — this skill only handles preset voices; route the call to mofa-fm instead.
Skipping download_model + load_model after a fresh install — the catalog model is not loaded until you load it explicitly.

---name: voicedescription: Batch ASR / OminiX TTS / Model Management---# Batch ASR / OminiX TTS / Model ManagementSpeech-to-text uses `ASR_API_URL` when configured (the Octos/OMiniX JSON +base64 batch-transcription contract at `POST /v1/audio/transcriptions`, such asthe local Whisper or Nemotron adapter); otherwise it falls back to Qwen3 ASRthrough local OminiX. Preset-voice text-to-speech with emotion control and modellifecycle management remain backed by local OminiX (Apple Silicon).An empty ASR result is a successful no-speech rejection, not an error.## Boundary — when NOT to use this skill- **Voice cloning / custom voice profiles** → use **mofa-fm** (`fm_tts`, `fm_voice_save`, `fm_voice_list`, `fm_voice_delete`). This skill is **preset-voice only**.- **Emotion prompts in fallback mode** → not supported. When ominix-api is unreachable, `voice_synthesize` falls through to the macOS built-in `say` command, which auto-picks a system voice from the text language and ignores the `prompt` parameter.## Tools| Tool | Purpose ||--------------------|------------------------------------------------------------|| `voice_transcribe` | ASR — WAV/OGG/MP3/FLAC/M4A → text || `voice_synthesize` | Preset-voice TTS with optional emotion + speed || `list_models` | List loaded + catalog models on the local ominix-api || `download_model` | Pull a catalog model to local disk || `load_model` | Load a downloaded model into GPU memory || `unload_model` | Free a loaded model from GPU memory |## Quick recipes### Transcribe a voice message```json{"audio_path": "voice.ogg", "language": "Chinese"}```### Synthesize plain speech```json{"text": "Hello world", "language": "english", "speaker": "ryan"}```### Synthesize with emotion```json{"text": "我太开心了！", "speaker": "vivian", "prompt": "用兴奋激动的语气说话，充满热情和活力"}```After `voice_synthesize` returns a file path, deliver the audio with`send_file`.## Further reading- Emotion / style prompts (Chinese + English) → `docs/emotion-prompts.md`- Server discovery, endpoints, preset speakers, full parameter cheat-sheet → `docs/api-reference.md`## Anti-patterns- Calling `voice_synthesize` with a `prompt` while ominix-api is down — the fallback (`say`) silently drops the emotion. Use `list_models` to confirm Qwen3-TTS is loaded before relying on emotion control.- Passing a non-preset speaker name (e.g. a cloned voice id) — this skill only handles preset voices; route the call to **mofa-fm** instead.- Skipping `download_model` + `load_model` after a fresh install — the catalog model is not loaded until you load it explicitly.

Frequently asked questions

Voice