hermes-soniox.yaml 1.1 KB

12345678910111213141516171819202122232425
  1. name: hermes-soniox
  2. repo: https://github.com/XimilalaXiang/hermes-soniox
  3. sha: 79f8d1dec5fcdc75e22ec34e857e5b4e2b8828bf
  4. description: >-
  5. Native BYOK Soniox text-to-speech and asynchronous speech-to-text providers with configurable
  6. languages and voices, automatic STT language detection, and Hermes voice-bubble support.
  7. Disclosure — TTS sends reply text and synthesis settings to tts-rt.soniox.com; STT uploads audio,
  8. optional language hints, and optional prompt context to api.soniox.com, then best-effort deletes
  9. the remote transcription and uploaded file. SONIOX_API_KEY is resolved through Hermes' active-profile
  10. secret scope. No telemetry, shell commands, background processes, or stored credentials.
  11. maintainer: XimilalaXiang
  12. tier: community
  13. version: "0.2.1"
  14. category: voice
  15. requires_hermes: ">=0.22.4"
  16. docs_url: https://github.com/XimilalaXiang/hermes-soniox#readme
  17. platforms: []
  18. known_issues:
  19. - Realtime WebSocket TTS/STT is not implemented; v0.2.1 uses file-based synthesis and asynchronous transcription.
  20. capabilities:
  21. provides_tools: []
  22. provides_hooks: []
  23. provides_middleware: []
  24. requires_env:
  25. - SONIOX_API_KEY