#6767th of 81 in VoiceFor voice, speech and music
whisper-asr-webservice
REST API server for Whisper speech-to-text with three selectable engines
- Stars
- 3.4k
- License
- MIT
- Last commit
- Aug 2026
- Last release
- Aug 2026
- Language
- Python
3,208 on 21 Apr 20263,369 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Wraps OpenAI Whisper, faster-whisper or WhisperX behind a REST API on port 9000, with Swagger UI for trying endpoints. It transcribes and translates audio or video via FFmpeg and returns text, JSON, VTT, SRT or TSV. Engine, model size, device and idle unload timeout are set through environment variables.
Who it is for: Self-hosters who need a transcription API for audio and video files
Strengths
- Switch between openai_whisper, faster_whisper and whisperx with one environment variable
- Outputs text, JSON, VTT, SRT and TSV, with word-level timestamps
- Speaker diarization available through the WhisperX engine
- Models can unload after an idle timeout to free memory
Weaknesses
- Speaker diarization works only with the WhisperX engine
- README documents no authentication or access control for the API
- Separate CPU and GPU image tags; GPU build needs a CUDA-capable host
- Transcription only; no web UI beyond the Swagger docs
What it needs
- GPU optional
- Docker + Compose
- Needs Docker, FFmpeg
- Models: openai/whisper, faster-whisper, whisperX
- port 9000
Quick answers
Is whisper-asr-webservice open source?
Yes. Its code is on GitHub under the MIT license.
Can you run whisper-asr-webservice with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does whisper-asr-webservice need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |