SenseAudio TTS
Use this skill for all SenseAudio speech synthesis tasks.
Read First
references/tts.md
Workflow
- Pick protocol:
- HTTP sync for simple one-shot generation.
- SSE for incremental HTTP audio chunks.
- WebSocket for realtime incremental text-to-audio sessions.
- Build minimal valid request:
- Auth header, model, text,
voice_setting.voice_id. - Add optional tuning only if user asks.
- Implement output parsing:
- Decode
data.audiohex to bytes. - Finalize on terminal status/event.
- Harden for production:
- Handle auth and parameter errors.
- Add retry/backoff for transient network failures.
- Log session and trace identifiers.