About the Speech category

Speech is the AI lane for ASR, TTS, speaker handling, and voice interfaces that depend on speech-specific pipelines.

Use this category for:

  • speech recognition, synthesis, speaker handling, and voice UX
  • ASR, TTS, diarization, and speech pipelines
  • speech systems used in real products or research

Good topics here:

  • voice interaction system design
  • speech model quality and tradeoffs
  • speech pipeline integration in products

If your topic is broader than this subcategory, use AI instead.