# Create ElevenLabs Voiceovers

Producing natural narration often requires manual setup across voice, model, and format options. This skill helps Claude, Codex, and Claude Code run ElevenLabs TTS through the inference.sh CLI.

## Install

```bash
npx skillstore add inferen-sh/elevenlabs-tts
```

## Metadata

- Status: approved
- Slug: inferen-sh-elevenlabs-tts
- Skillstore revision: r1
- Version status: missing
- Tree hash: a9d6fdffb6e04331e440e4f4e7a37ab4e282e66b0e0b6d3180021923fc84d839
- Author: inferen-sh
- GitHub username: inferen-sh
- License: MIT
- Repository: https://github.com/inferen-sh/skills/tree/main/tools/audio/elevenlabs-tts/
- Ref: 30c73eac2afe762f6aa9c4553158769369d47351
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network
- Quality score: 78
- Quality tier: bronze
- Public page: https://skillstore.pages.dev/skills/inferen-sh-elevenlabs-tts
- Manifest: https://skillstore.pages.dev/api/skills/inferen-sh-elevenlabs-tts/manifest

## Capabilities

- Generate speech from supplied text with the ElevenLabs TTS app on inference.sh.
- Select named voices such as Aria, George, Bella, Brian, and Daniel.
- Choose multilingual, turbo, or flash ElevenLabs models for quality or latency needs.
- Tune stability, similarity boost, style, and speaker boost settings.
- Request MP3 or PCM output formats for different production workflows.
- Combine generated voiceover output with a documented video generation workflow.

## Use Cases

- Produce Product Demo Narration: Create clear voiceovers for product videos, sales demos, and short launch clips.
- Localize Course Audio: Generate multilingual narration for training modules and learning content.
- Draft Phone System Prompts: Prepare professional IVR greetings, support messages, and status announcements.

## Prompt Templates

### Create a Basic Voiceover

```
Use the elevenlabs-tts skill to generate a short product demo voiceover. Use voice Aria and default settings. Return the audio result location and settings used.
```

### Compare Two Voices

```
Generate the same 30 second script with voices George and Bella. Summarize the tone differences and recommend one for a professional demo.
```

### Tune Expressive Delivery

```
Create an expressive narration using voice Jessica. Adjust stability, similarity boost, and style for a warm but polished delivery.
```

### Build Multilingual Narration

```
Generate English, Spanish, and French versions of this launch script with the multilingual model. Keep voice choice and output format consistent.
```

## Limitations

- Requires the inference.sh CLI, an authenticated account, and network access.
- Sends provided text to an external speech generation service.
- Does not add voice cloning, transcript editing, or content moderation by itself.
- Quality, latency, and language support depend on ElevenLabs and inference.sh availability.

## Best Practices

- Review scripts for secrets, personal data, and unreleased information before generation.
- Choose the model based on quality needs, latency targets, and language requirements.
- Record the voice, model, format, and tuning values used for approved production audio.

## Anti Patterns

- Sending passwords, API keys, private customer details, or confidential drafts as TTS input.
- Using the fastest model for final long-form narration without checking audio quality.
- Changing voices or tuning settings across related assets without a review pass.

## Security Audit

- Audited at: 2026-07-05T15:44:20.55\+00:00
- Summary: No prompt injection or malicious intent was found in SKILL.md. The external command alerts are Markdown inline code or fenced examples, not Ruby or shell backtick execution. The URL alerts are documentation, image, and example URLs that do not execute by themselves.

## Stats

- Views: 181
- Downloads: 17
- Favorites: 0
- Popularity score: 0