Dicklesworthstone/franken_whisper

Agent-first Rust ASR orchestration stack: Bayesian backend routing across whisper.cpp/insanely-fast-whisper/whisper-diarization, real-time NDJSON streaming, SQLite persistence, TTY audio transport, conformance harness. 107K lines, 2000+ tests, zero unsafe code.

37
/ 100
Emerging

This tool helps developers integrate advanced speech-to-text capabilities into their applications. It takes various audio or video files as input and produces highly structured, machine-readable text transcripts with speaker identification, suitable for automated processing. Developers creating agent-based systems or data pipelines that need reliable, robust transcription will find this invaluable.

Use this if you are a developer building applications that require consistent, high-quality, and robust speech-to-text transcription with speaker diarization and need a unified way to manage different Whisper backend engines.

Not ideal if you are an end-user simply looking for a desktop app to transcribe a single audio file or if you don't have development expertise.

developer-tool speech-to-text audio-processing AI-pipeline agent-systems
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 11 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Rust

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Dicklesworthstone/franken_whisper"

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