faster-whisper-server

by fedirz

OpenAI-compatible /v1/audio/transcriptions endpoint over faster-whisper.

TL;DR

OpenAI-compatible /v1/audio/transcriptions endpoint over faster-whisper.

Best for drop-in replacement for OpenAI's Whisper API on your own GPU. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Docker

What it is

A FastAPI server that exposes the OpenAI Audio API on top of faster-whisper. Supports SSE streaming, language detection, model hot-swap. MIT.

Best for: Drop-in replacement for OpenAI's Whisper API on your own GPU.
Watch out for: Repo has been renamed/forked; single-tenant; no auth out of box.

Install / use

docker run fedirz/faster-whisper-server

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

faster-whisper-server vs Whipscribe

Featurefaster-whisper-serverWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, DockerWeb, API, MCP

Alternatives to faster-whisper-server

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.