Skip to content

feat: add Whisper-based speech recognition with TTS test audio generation#503

Open
Dantechz wants to merge 1 commit into
open-jarvis:mainfrom
Dantechz:main
Open

feat: add Whisper-based speech recognition with TTS test audio generation#503
Dantechz wants to merge 1 commit into
open-jarvis:mainfrom
Dantechz:main

Conversation

@Dantechz

@Dantechz Dantechz commented Jun 6, 2026

Copy link
Copy Markdown

Summary

  • Added �ackend/speech_recognition.py with OpenAI Whisper for speech-to-text transcription
  • Integrated pyttsx3 for offline TTS test audio generation (run in subprocess to avoid COM/torch conflict)
  • Used built-in winsound for audio playback on Windows, replacing pydub/simpleaudio which caused segfaults

Test plan

  • Run python backend/speech_recognition.py to verify test audio is generated
  • Verify Whisper transcribes the generated audio correctly
  • Confirm audio plays back without errors

?? Generated with Claude Code

…tion

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

2 participants