awvoice(tool, public)
Hear and speak — transcribe audio, synthesize a voice.
Name
awvoice — Hear and speak — transcribe audio, synthesize a voice.
The problem it solves
An agent that can only read text is deaf and mute. Every route to fixing that today is a vendor SDK that wants the audio uploaded, an API key, and a per-minute bill -- which rules it out for exactly the recordings people most want transcribed.
Instead of trusting / you check
- instead of trusting
- that a cloud vendor may hold your audio
- you check
- a transcript and a wav from a service you host
Adopt it alone
Turn speech into text and text into speech, on a service you host.
Install
pip install awvoice
Where it sits in the path
- Not on the path yet — reference only.
Links
Generated 2026-09-14 00:48Z from the ecosystem registry. A field here that is wrong is wrong in the registry — fix it there and this page follows.