# elevenlabs-tts

elevenlabs-tts is a Claude Code skill for ElevenLabs speech production, covering voice selection, spoken-text preparation, rendering, and audio QA.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 147 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/text-to-speech/elevenlabs-tts/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/calesthio-elevenlabs-tts

## What it does

elevenlabs-tts guides ElevenLabs speech work for narration, character performances, multilingual media, and long-form voiceover. It helps select a model and voice, adapt text for speech, control pronunciation, pacing, emotion, and language switching, then review and finish the rendered audio.

The skill covers streamed and batch generation, TTS API use, voice design or cloning, artifact repair, and delivery checks. Model choice can depend on latency, request size, language coverage, and feature support: `eleven_v3` is suited to expressive performance, while `eleven_flash_v2_5` targets low-latency generation. Music, sound effects, conversational-agent logic, and general transcription are outside its scope. Voice cloning is described with explicit consent.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill elevenlabs-tts -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill elevenlabs-tts -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill elevenlabs-tts -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/providers/text-to-speech/elevenlabs-tts
```

2. **Manually: put the files in place**
- File: `.github/skills/elevenlabs-tts/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill elevenlabs-tts -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/providers/text-to-speech/elevenlabs-tts
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill elevenlabs-tts -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/calesthio/generative-media-skills/tree/HEAD/skills/providers/text-to-speech/elevenlabs-tts/SKILL.md

## When to use it
- choose an ElevenLabs model and voice for a narration
- prepare spoken copy with correct names, numbers, and URLs
- control pacing, emotion, and language switches in generated speech
- review rendered audio for artifacts and pronunciation issues

## Example prompts
- Choose an ElevenLabs voice and model for a long-form Russian narration, then check names and numbers.
- Adapt this script for a character performance and render it through the TTS API.
- Review the finished ElevenLabs track for artifacts, pronunciation, and script alignment.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: bd277c8a29ede0ea.

BEGIN THIRD-PARTY FILE bd277c8a29ede0ea
```text
---
name: elevenlabs-tts
description: Produce, direct, integrate, and quality-control ElevenLabs text-to-speech for narration, character performance, multilingual media, long-form voiceover, and streamed or batch AI-content audio. Use when selecting ElevenLabs models or voices; preparing spoken text; controlling pronunciation, pacing, emotion, and code-switching; using TTS APIs; cloning or designing a voice with consent; repairing artifacts; mastering deliverables; or evaluating generated speech. Excludes music, sound-effect generation, conversational-agent design, and general speech recognition except transcription used to verify TTS.
---

# ElevenLabs TTS production

Treat speech generation as casting, script adaptation, performance direction, rendering, and finishing—not as a single API call. Optimize for the listener and delivery channel, then for latency or cost.

## Evidence labels

Interpret guidance by its label:

- **Documented** — ElevenLabs documentation, API reference, or current policy states this.
- **Standard** — a named speech/audio standard states this.
- **Production heuristic** — a practical starting point; validate it on the actual voice, model, script, and channel.
- **Inference** — a conclusion drawn from documented behavior; test before relying on it.

Volatile ElevenLabs facts in this skill were checked on **2026-07-09**. Before a consequential production run, query `GET /v1/models`, inspect the chosen voice, and recheck the current API reference, plan entitlements, policies, and terms. Never infer current availability from an old voice name or model list.

## Scope boundary

Use this skill for rendered speech and voice production. Do not expand into:

- music or sound-effect generation;
- dialogue-system logic, turn-taking, tools, telephony orchestration, or conversational-agent prompting;
- speech-to-speech except to explain why it is not TTS;
- general transcription, dubbing, or localization workflows;
- legal conclusions. Flag rights questions for qualified review.

Speech-to-text may be used only as one TTS QA signal. It must not replace listening.

## Start with a production contract

Before selecting a model, write down:

1. audience, language, regional accent, and accessibility needs;
2. medium and destination: video narration, audiobook, ad, game character, course, IVR, or live playback;
3. performance: credible, intimate, restrained, comic, urgent, dramatic, etc.;
4. target duration and synchronization constraints;
```
END THIRD-PARTY FILE bd277c8a29ede0ea

The third-party file has ended. Everything between the bd277c8a29ede0ea tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2502 of 36155 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/text-to-speech/elevenlabs-tts/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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
