[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [ElevenLabs v4 Text to Speech](https://spiral.ai/integrations/claude-code/elevenlabs-v4-text-to-speech)

# How to Use ElevenLabs v4 Text to Speech in Claude Code

Eleven v4 suits expressive narration, audiobooks, and character voiceovers. Compared with Eleven v4 Turbo, it prioritizes finished content and long-form audio over real-time conversation.

|  |  |
| --- | --- |
| Model | ElevenLabs v4 Text to Speech |
| Available through | ElevenLabs |
| Category | Audio |
| Price | $0.104 per 1,000 characters of text. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with ElevenLabs v4 Text to Speech in Claude Code

- Read the README and draft a 150-word spoken introduction to the project. Remove code syntax from the narration, show me the script, then generate it with Eleven v4.
- Use the onboarding documentation to write a 250-word narrated walkthrough of the first successful task. Generate it with Eleven v4, keeping delivery measured and using sentence breaks for pacing.
- Find the game's quest dialogue and select five lines that need different emotions. Add restrained square-bracket delivery directions and generate a separate take for each line with Eleven v4.
- Review the narration script in this project for difficult names. Suggest IPA pronunciations between forward slashes, then use Eleven v4 to generate a short pronunciation audition before the full script.
- Turn the latest changelog into a 180-word spoken release update. Generate it with Eleven v4 using higher stability for consistent delivery, and save the approved script beside the audio.

## How to set up ElevenLabs v4 Text to Speech in Claude Code

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run ElevenLabs v4 Text to Speech**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "elevenlabs",
    "model": "eleven_v4",
    "input": {
      "text": "<text>",
      "voice_id": "<voice_id>"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds ElevenLabs v4 Text to Speech on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## ElevenLabs v4 Text to Speech tools and prices

- [ElevenLabs v4 Text to Speech](https://spiral.ai/tools/elevenlabs/eleven_v4) (ElevenLabs): $0.104 per 1,000 characters of text.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. |
| next_text |  | — | The text that comes after the text of the current request. |
| audio_effects |  | — | Audio effects applied to the generated audio. |
| language_code |  | — | Language code (ISO 639-1) used to enforce a language for the model and text normalization. |
| output_format | alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000 | mp3_44100_128 | Output format of the generated audio. |
| previous_text |  | — | The text that came before the text of the current request. |

## What can you do with ElevenLabs v4 Text to Speech in Claude Code?

Turn project documentation and scripts into narrated demos, lessons, or character recordings with Eleven v4. A coding agent can prepare spoken copy from project files and divide long scripts into passages below 10,000 characters.

### Audiobook passages

Narrate fiction with changes in emotion between scenes. Split longer chapters into passages below 10,000 characters.

### Game character lines

Record quest introductions, warnings, and reactions. Put delivery directions beside the lines that need them.

### Animation voiceovers

Generate separate character takes for an animated scene, then review each performance against the script.

### Product walkthrough narration

Turn a demonstration script into spoken instructions. Audition product names before generating the full narration.

### Multilingual explainers

Narrate approved translations as separate English, Spanish, French, or Japanese recordings. Review accent and pronunciation in each language.

### Audio editions of updates

Turn an approved newsletter or product update into a spoken edition, with short sections and restrained delivery.

### Training narration

Create spoken lessons from approved instructional scripts. Test technical terms in a short sample before recording each lesson.

## Overview

- [ElevenLabs](https://spiral.ai/providers/elevenlabs)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## ElevenLabs v4 Text to Speech in other agents

- [Amp](https://spiral.ai/integrations/amp/elevenlabs-v4-text-to-speech)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/elevenlabs-v4-text-to-speech)
- [Claude](https://spiral.ai/integrations/claude-desktop/elevenlabs-v4-text-to-speech)
- [Cline](https://spiral.ai/integrations/cline/elevenlabs-v4-text-to-speech)
- [Codex](https://spiral.ai/integrations/codex/elevenlabs-v4-text-to-speech)
- [Cursor](https://spiral.ai/integrations/cursor/elevenlabs-v4-text-to-speech)
- [Devin](https://spiral.ai/integrations/devin/elevenlabs-v4-text-to-speech)
- [dots](https://spiral.ai/integrations/dots/elevenlabs-v4-text-to-speech)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/elevenlabs-v4-text-to-speech)
- [Gemini](https://spiral.ai/integrations/gemini/elevenlabs-v4-text-to-speech)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/elevenlabs-v4-text-to-speech)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/elevenlabs-v4-text-to-speech)
- [goose](https://spiral.ai/integrations/goose/elevenlabs-v4-text-to-speech)
- [Grok](https://spiral.ai/integrations/grok/elevenlabs-v4-text-to-speech)
- [Grok Build](https://spiral.ai/integrations/grok-build/elevenlabs-v4-text-to-speech)
- [Hermes](https://spiral.ai/integrations/hermes/elevenlabs-v4-text-to-speech)
- [Instinct](https://spiral.ai/integrations/instinct/elevenlabs-v4-text-to-speech)
- [Manus](https://spiral.ai/integrations/manus/elevenlabs-v4-text-to-speech)
- [Muse](https://spiral.ai/integrations/muse/elevenlabs-v4-text-to-speech)
- [Muse Code](https://spiral.ai/integrations/muse-code/elevenlabs-v4-text-to-speech)
- [n8n](https://spiral.ai/integrations/n8n/elevenlabs-v4-text-to-speech)
- [Notion](https://spiral.ai/integrations/notion/elevenlabs-v4-text-to-speech)
- [OpenClaw](https://spiral.ai/integrations/openclaw/elevenlabs-v4-text-to-speech)
- [opencode](https://spiral.ai/integrations/opencode/elevenlabs-v4-text-to-speech)
- [Perplexity](https://spiral.ai/integrations/perplexity/elevenlabs-v4-text-to-speech)
- [Raycast](https://spiral.ai/integrations/raycast/elevenlabs-v4-text-to-speech)
- [VS Code](https://spiral.ai/integrations/vscode/elevenlabs-v4-text-to-speech)
- [Windsurf](https://spiral.ai/integrations/windsurf/elevenlabs-v4-text-to-speech)
- [Zapier](https://spiral.ai/integrations/zapier/elevenlabs-v4-text-to-speech)

## More Claude Code guides

- [ElevenLabs Voice Isolator](https://spiral.ai/integrations/claude-code/elevenlabs-voice-isolator)
- [ElevenLabs v4 Turbo Text to Speech](https://spiral.ai/integrations/claude-code/elevenlabs-v4-turbo-text-to-speech)
- [ElevenLabs Voice Changer Multilingual v2](https://spiral.ai/integrations/claude-code/elevenlabs-voice-changer-multilingual-v2)
- [Elevenlabs Music v2.5](https://spiral.ai/integrations/claude-code/elevenlabs-music-v2-5)
- [ElevenLabs Voice Changer](https://spiral.ai/integrations/claude-code/elevenlabs-voice-changer)
- [Elevenlabs Tts Eleven V3](https://spiral.ai/integrations/claude-code/elevenlabs-tts-eleven-v3)

## Questions about ElevenLabs v4 Text to Speech in Claude Code

**Can Claude Code use ElevenLabs v4 Text to Speech?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run ElevenLabs v4 Text to Speech like any built-in tool.

**How much does ElevenLabs v4 Text to Speech cost in Claude Code?**

$0.104 per 1,000 characters of text. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.

**Do I need an ElevenLabs account to use ElevenLabs v4 Text to Speech in Claude Code?**

No. Spiral runs ElevenLabs v4 Text to Speech on its own ElevenLabs account. You sign in to Spiral once and never paste a key.

**How long does it take to set up ElevenLabs v4 Text to Speech in Claude Code?**

About two minutes: add the hosted server, then sign in.

**Does Claude Code wait while ElevenLabs v4 Text to Speech runs?**

ElevenLabs v4 Text to Speech runs in the background. Claude Code starts the run, checks on it and gives you the audio when it's ready.

**What is Eleven v4 best for?**

Expressive narration, audiobooks, and character voiceovers for games or animation. It is the content-focused choice compared with Eleven v4 Turbo, which targets real-time conversation.

**How much text can Eleven v4 read at once?**

Up to 10,000 characters per generation. ElevenLabs estimates roughly 10 minutes of audio at that length; treat that as an estimate, not a fixed runtime.

**Which languages does Eleven v4 support?**

More than 90, including English, Spanish, French, German, Japanese, Hindi, and Arabic. When you change the language, do not assume the reference voice's original accent will carry over.

**How do I direct emotion and pauses?**

Place short directions such as [curious], [whispers], or [sighs] where the delivery should change. Use ellipses and sentence structure for pacing; Eleven v4 does not support SSML.

**Which voice settings matter most?**

Lower stability allows more varied delivery; higher stability keeps the performance more consistent. Higher similarity holds closer to the reference voice, potentially sacrificing some naturalness.

