# Text to Speech — model skill for voice & voiceover

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Voice any script with Inworld TTS-2, ElevenLabs, Dia, Kokoro or Chatterbox from one CLI.

- **Type:** [Model](https://skills.varg.ai/models.md) · [Voice & voiceover](https://skills.varg.ai/browse/skills/audio.md)
- **Slug:** `inference-sh-text-to-speech`
- **Status:** live
- **Publisher:** inference.sh (vendor, verified)
- **License:** MIT
- **Source:** https://github.com/inference-sh/skills/tree/main/tools/audio/text-to-speech
- **Works in:** Claude Code, Codex, Cursor, Gemini CLI
- **Requires:** inference.sh account, belt CLI (`belt login`)
- **Cost:** Billed by inference.sh
- **Adoption:** 7 installs, 781 GitHub stars (skills.sh, 2026-10-26)

## What it does

A multi-model text-to-speech skill for inference.sh with guidance on picking a voice model. Options include Inworld TTS-2 (100+ languages, emotion steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs, Dia TTS, Kokoro and Chatterbox.

## Use when

- A voiceover from a script
- Speech in many languages
- Low-latency speech for an app

## Install

- Claude Code: `npx skills add inference-sh/skills --skill text-to-speech -a claude-code`
- Codex: `npx skills add inference-sh/skills --skill text-to-speech -a codex`
- Cursor: `npx skills add inference-sh/skills --skill text-to-speech -a cursor`
- Gemini CLI: `npx skills add inference-sh/skills --skill text-to-speech -a gemini-cli`

**Models it drives:** inworld-tts-2, eleven_v3, dia-tts, kokoro, chatterbox

## Example output

https://skills.varg.ai/previews/inference-sh-text-to-speech.mp3 — Kokoro TTS (the skill's quick-start model, falai/kokoro-tts) sample from its model card: 'Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models…' (credit: hexgrad (Kokoro-82M model card sample), https://huggingface.co/hexgrad/Kokoro-82M)

## More voice & voiceover skills

- [ElevenLabs Dubbing](https://skills.varg.ai/skills/elevenlabs-dubbing.md): Dub video and audio into other languages while keeping each original speaker's voice.
- [ElevenLabs Text to Speech](https://skills.varg.ai/skills/elevenlabs-text-to-speech.md): Turn scripts into natural voiceover in 90+ languages with ElevenLabs voices, streaming and stitching.
- [ElevenLabs Voice Changer](https://skills.varg.ai/skills/elevenlabs-voice-changer.md): Re-voice a recording in a different voice while keeping its emotion, timing and delivery.
- [AI Voice Cloning](https://skills.varg.ai/skills/inference-sh-ai-voice-cloning.md): Generate expressive voices in 100+ languages with Inworld TTS-2, ElevenLabs and more, from one CLI.
- [Dialogue Audio](https://skills.varg.ai/skills/inference-sh-dialogue-audio.md): Produce multi-speaker dialogue audio with speaker tags, emotion and pacing for podcasts and explainers.
- [ElevenLabs Dialogue](https://skills.varg.ai/skills/inference-sh-elevenlabs-dialogue.md): Generate a whole multi-voice conversation as one audio file with ElevenLabs, from a script.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt