media-processing / library
whisper
Capability: whisper
Use it when
- local speech-to-text transcription offline
- transcribe audio files without cloud STT APIs
What it solves
Not the fit when
- realtime phone carrier stack alone
Install
pip install -U openai-whisper
Invoke
whisper audio.mp3 --model base # STT for call/voice agent pipelines offline
Alternatives
No reviewed alternatives recorded yet.