SkillHub

senseaudio-tts

v1.0.1

Build and debug SenseAudio text-to-speech integrations on `/v1/t2a_v2` and `/ws/v1/t2a_v2`, including sync HTTP, SSE stream, WebSocket event sequencing, hex audio decoding, and voice/audio parameter tuning. Use this whenever user requests TTS generation, low-latency streaming speech, voice selection...

Sourced from ClawHub, Authored by scikkk

Installation

Please help me install the skill `senseaudio-tts` from SkillHub official store. npx skills add scikkk/senseaudio-tts

SenseAudio TTS

Use this skill for all SenseAudio speech synthesis tasks.

Read First

  • references/tts.md

Workflow

  1. Pick protocol:
  2. HTTP sync for simple one-shot generation.
  3. SSE for incremental HTTP audio chunks.

  4. WebSocket for realtime incremental text-to-audio sessions.

  5. Build minimal valid request:

  6. Auth header, model, text, voice_setting.voice_id.

  7. Add optional tuning only if user asks.

  8. Implement output parsing:

  9. Decode data.audio hex to bytes.

  10. Finalize on terminal status/event.

  11. Harden for production:

  12. Handle auth and parameter errors.
  13. Add retry/backoff for transient network failures.
  14. Log session and trace identifiers.