Tool Integrations
⚙Tool
ElevenLabs
Generate natural-sounding speech from text
ElevenLabs
Generate high-quality, natural-sounding speech from text using ElevenLabs' advanced TTS models. Supports multiple voices, languages, and emotional styles.
Overview
| Property | Value |
|---|---|
| Type | elevenlabs |
| Category | Tool — AI & ML |
| Auth | API Key |
Operations
| Operation | Description |
|---|---|
| Text-to-Speech | Convert text to audio |
| List Voices | Get available voices |
Configuration
| Setting | Type | Description |
|---|---|---|
| API Key | Password | ElevenLabs API key |
| Text | Long text | Text to convert to speech |
| Voice | Dropdown | Select a voice |
| Model | Dropdown | TTS model (multilingual, turbo) |
| Stability | Slider | Voice consistency (0–1) |
| Similarity | Slider | How closely to match voice (0–1) |
Outputs
| Field | Type | Description |
|---|---|---|
audioUrl | string | URL to generated audio |
content | string | Audio data or URL |
Example: Podcast Generator
Workflow:
[Starter: Topic] → [Agent: Write Script] → [ElevenLabs: TTS] → [Response]Agent writes a podcast script on the given topic. ElevenLabs converts it to natural-sounding speech. User gets a playable audio file.
Tips
- Voice cloning — ElevenLabs supports custom voice creation (check their platform)
- Stability — lower = more expressive, higher = more consistent
- Multilingual models handle non-English text better