alesaccoia/VoiceStreamAI

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

48
/ 100
Emerging

This solution provides near-realtime transcription for live audio streams. It takes live spoken audio, processes it using advanced speech recognition models, and outputs text as people speak. It's designed for anyone who needs to quickly convert spoken words into text during a live conversation or presentation, such as transcribers, journalists, or meeting facilitators.

950 stars. No commits in the last 6 months.

Use this if you need to transcribe live spoken audio directly from a microphone into text with minimal delay, for applications like live captioning or interactive voice assistants.

Not ideal if you primarily need to transcribe pre-recorded audio files or if you require extensive speaker diarization (identifying who spoke when).

live-transcription speech-to-text audio-processing realtime-captioning voice-assistants
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

950

Forks

142

Language

Python

License

MIT

Last pushed

Oct 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/alesaccoia/VoiceStreamAI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.