EvilFreelancer/docker-whisper-server

whisper.cpp HTTP transcription server with OpenAI-like API in Docker

42
/ 100
Emerging

This project provides a self-hosted audio transcription service using advanced speech-to-text technology. You feed it audio files in various formats, and it outputs the transcribed text, subtitles (SRT), or JSON with detailed timing. This is ideal for content creators, researchers, journalists, or anyone needing to convert spoken words into written form efficiently.

No commits in the last 6 months.

Use this if you need an on-premise, high-performance solution for transcribing audio into text, especially if you handle sensitive data or large volumes of audio and want to control computing resources.

Not ideal if you don't have access to an NVIDIA GPU or prefer a fully managed, cloud-based transcription service with no setup required.

audio-transcription content-creation research-analysis media-production data-processing
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

29

Forks

9

Language

Python

License

MIT

Last pushed

Aug 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/EvilFreelancer/docker-whisper-server"

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