Voice Synthesis Handler
When to Use
- User says speak response or task matches this capability
- User says text to speech or task matches this capability
- User says voice output or task matches this capability
- User says read aloud or task matches this capability
Workflow
- Format response for spoken delivery (short sentences).
- Strip markdown and code blocks for TTS.
- Invoke TTS; confirm audio output path or stream.
- Offer shorter summary if text exceeds 30 seconds speech.
Integrations
real-time-voice-reasonervoice-think-fast-handler
Error Handling
| Failure | Response |
|---|---|
| TTS unavailable | Return text with speakable formatting note. |
Gotchas
- Never speak secrets or OTP codes aloud.
Example
Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.