# text-to-speech

text-to-speech gives the agent ready belt commands for speech synthesis: Kokoro, ElevenLabs, Inworld TTS-2 with emotion steering, and a few more models.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 246 installs · ★ 31 repo stars
- Author: 101-skills
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/101-skills/superpowers/tree/HEAD/tools/audio/text-to-speech/SKILL.md
- Updated: 2026-08-31
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/101-skills-text-to-speech

## What it does

The skill hands the agent a set of `belt app run` commands that call inference.sh to synthesize speech. A model table inside lists app IDs: Inworld TTS-2, Inworld TTS 1.5 Max and Mini, ElevenLabs, DIA, Kokoro, Chatterbox, Higgs Audio, VibeVoice. The agent picks whichever fits the job.

Inworld TTS-2 takes direction inline: bracketed tags in the text set emotion, a pause or a laugh, while `STABLE`, `BALANCED` and `CREATIVE` control how far the delivery is pushed. The voice goes in `voice_id`. For dialogue there is TTS 1.5, with Max under 200 ms and Mini around 120 ms. Long podcast scripts go to VibeVoice, a conversational tone to DIA, and ElevenLabs brings 22+ voices across 32 languages.

Nothing runs until the `belt` CLI is installed and `belt login` has been done, because the skill's only allowed tool is `Bash(belt *)`. For talking-head video the notes point to P-Video-Avatar with built-in speech, or to OmniHuman fed an `audio_url` from an earlier step.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill text-to-speech -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/text-to-speech/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/text-to-speech/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill text-to-speech -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/text-to-speech/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill text-to-speech -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/text-to-speech/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install 101-skills/superpowers tools/audio/text-to-speech
```

2. **Manually: put the files in place**
- File: `.github/skills/text-to-speech/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill text-to-speech -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/101-skills/superpowers --path tools/audio/text-to-speech
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/text-to-speech/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add 101-skills/superpowers --skill text-to-speech -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/101-skills/superpowers/tree/HEAD/tools/audio/text-to-speech/SKILL.md

## When to use it
- Narrate a product demo without booking a studio
- Turn a long article into an audio version
- Give a game NPC lines with emotion tags
- Generate a podcast episode from a script
- Build spoken prompts for a phone menu

## Example prompts
- Voice the text in `intro.txt` with the Sarah voice through Inworld TTS-2 in `CREATIVE` mode.
- Generate a two-voice podcast from `script.md` with VibeVoice.
- Run `belt app list --category audio` and pick a voice for a low-latency assistant.

## Similar
- [speech-to-text](https://affpapa.org/en/nevibecode/skills/speech-to-text.md) — skill · 16200 installs
- [Text to Speech — 20+ Languages, MP3 Output](https://affpapa.org/en/nevibecode/mcp/text-to-speech-20-languages-mp3-output.md) — MCP server · 2769 installs
- [azure-text-to-speech](https://affpapa.org/en/nevibecode/skills/azure-text-to-speech.md) — skill · 738 installs
- [venice-audio-speech](https://affpapa.org/en/nevibecode/skills/veniceai-venice-audio-speech.md) — skill · ★ 176 repo stars
- [elevenlabs-tts](https://affpapa.org/en/nevibecode/skills/elevenlabs-tts.md) — skill · 1700 installs
- [pp-elevenlabs](https://affpapa.org/en/nevibecode/skills/pp-elevenlabs.md) — skill · 165 installs

## Other versions with the same name
- [text-to-speech · calesthio](https://affpapa.org/en/nevibecode/skills/calesthio-text-to-speech.md) — 1300 installs
- [text-to-speech · elevenlabs](https://affpapa.org/en/nevibecode/skills/text-to-speech.md) — 22900 installs
- [text-to-speech · martinholovsky](https://affpapa.org/en/nevibecode/skills/martinholovsky-text-to-speech.md) — 237 installs
- [text-to-speech · benchflow-ai](https://affpapa.org/en/nevibecode/skills/benchflow-ai-text-to-speech.md) — 4 installs

From the same set: [101-skills/superpowers](https://affpapa.org/en/nevibecode/by/101-skills/superpowers.md) — 81 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
