d3163a5bff
- pgSchema "mesh" with 4 tables isolating the peer mesh domain - Enums: visibility, transport, tier, role - audit_log is metadata-only (E2E encryption enforced at broker/client) - Cascade on mesh delete, soft-delete via archivedAt/revokedAt Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
5.1 KiB
5.1 KiB
title, description, url
| title | description | url |
|---|---|---|
| Eleven Labs | Setup ElevenLabs and learn how to integrate its AI audio capabilities into the starter kit. | /ai/docs/eleven-labs |
Eleven Labs
ElevenLabs stands at the forefront of AI audio innovation, specializing in ultra-realistic Text-to-Speech (TTS), voice cloning, and advanced audio generation. While not a native provider within the AI SDK core, ElevenLabs' powerful services integrate seamlessly with AI applications to deliver exceptional voice experiences.
Setup
Integrating ElevenLabs involves using their purpose-built SDKs (Python, TypeScript/JavaScript) alongside your application logic:
### Generate API KeyVisit the [ElevenLabs website](https://elevenlabs.io/), create an account or sign in, then navigate to your profile settings to generate your unique API key.
Add your API key to your project's `.env` file (e.g., in `apps/web` or the appropriate package):
```bash title=".env"
ELEVENLABS_API_KEY=your-api-key
```
Initialize the ElevenLabs client with your API key:
```typescript title="client.ts"
import { ElevenLabsClient } from "elevenlabs";
import { env } from "../../env";
export const client = new ElevenLabsClient({
apiKey: env.ELEVENLABS_API_KEY,
});
// Now use the client object...
```
For comprehensive implementation details, refer to the [ElevenLabs Quickstart Guide](https://elevenlabs.io/docs/quickstart).
Features
ElevenLabs offers a comprehensive suite of AI audio technologies:
Transform written text into remarkably natural speech across numerous languages, voices, and styles, with flexible options for quality or low-latency delivery. Transcribe spoken audio into text accurately, supporting multiple languages and providing features like speaker diarization. Create stunningly accurate digital replicas of voices from audio samples, with both instant and professional-grade options to suit your needs. Craft entirely new, unique synthetic voices based on descriptive parameters, enabling custom voice creation without requiring sample recordings. Build and deploy end-to-end conversational voice agents, integrating STT, LLMs (like GPT, Claude, Gemini), TTS, and turn-taking logic. Automatically dub audio or video content into different languages while preserving the original voice characteristics. Create custom sound effects and ambient audio from simple text descriptions, adding rich audio elements to your applications. Access an extensive collection of pre-made, ready-to-use voices contributed by the ElevenLabs community.