marcocosta10000 25288d2c0f feat(voice): transcribe Telegram voice notes with SpeechRecognition ...

Add a voice message handler that downloads OGG audio, converts it to
WAV via pydub/ffmpeg, and transcribes it with Google Speech Recognition
(pt-BR) before feeding the text into the normal message pipeline.

Also extract shared text processing into process_text_message, guard
against updates without a text attribute, switch the default AI provider
to openrouter with deepseek-v4-flash, and document the ffmpeg system
requirement in DEPLOY.md.

2026-10-25 17:27:42 -03:00

3.5 KiB

Raw History

View Raw