Whisper ASR Webservice
Whisper speech-to-text as a REST API in one Docker container.
Quick answer
Whisper ASR Webservice is a whisper speech-to-text as a REST API in one Docker container, listed under Speech & translation. A typical small-business use: a private transcription endpoint that other internal tools or n8n workflows call over HTTP. The project publishes no official RAM figure, so we do not estimate a monthly server cost. License: MIT, which allows internal business use.
Last updated · facts verified against official docs on · sources
Activity data comes from GitHub and was last refreshed Oct 27, 2026.
What is Whisper ASR Webservice?
Whisper ASR Webservice (also called Whisper ASR Box) wraps OpenAI Whisper, Faster Whisper and WhisperX behind a REST API with Swagger docs. It transcribes, translates and detects the language of audio or video files, returns text, JSON, VTT, SRT or TSV, and can add word timestamps, voice activity filtering and speaker diarization (WhisperX). CPU and GPU images are published on Docker Hub.
Where it fits in a 10–200 person business
- A private transcription endpoint that other internal tools or n8n workflows call over HTTP
- Subtitles (SRT/VTT) for training or marketing videos without uploading them to a cloud service
- Transcribe customer calls or interviews with speaker labels using the WhisperX engine
These use cases are our editorial suggestions, not claims made by the project.
Can a business use Whisper ASR Webservice? (license)
| License | MIT |
|---|---|
| Type | Permissive: MIT / Apache-2.0: use, modify and sell with few obligations. |
| Internal business use | Allowed under the license text |
| What to watch | Permissive. Internal and commercial use allowed; keep the license notice. The image bundles FFmpeg libraries under the LGPL-2.1. |
This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.
Data & compliance: does Whisper ASR Webservice phone home?
| Telemetry (usage data sent to the vendor) | Not documented |
|---|---|
| Other calls home by default (updates, marketplaces, default cloud services) | Not documented |
| Single sign-on (OIDC / SAML / LDAP) | Not documented |
| Audit log | Not documented |
| Role-based access control (RBAC) | Not documented |
| Data residency / GDPR notes from the project | Not documented |
Checked against the project's own docs and repository on . "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.
What hardware does Whisper ASR Webservice need?
The project does not publish a minimum CPU/RAM figure, so we leave the official value blank rather than guess.
GPU: Optional (GPU image with --gpus all). A CPU image is available; on CPU the default quantization is int8.
No official RAM or disk figures. Memory use depends on the Whisper model you pick (tiny to large-v3). GPU passthrough does not work in Docker on macOS.
How much does it cost to host Whisper ASR Webservice per month?
The project publishes no RAM figure we could verify, so we do not estimate a cost.
How to deploy Whisper ASR Webservice
Method: Docker
docker run -d -p 9000:9000 \
-e ASR_MODEL=base \
-e ASR_ENGINE=openai_whisper \
onerahmet/openai-whisper-asr-webservice:latestFrom the official instructions: ahmetoner.github.io/whisper-asr-webservice/run/. Always check the source for the current version before you run it.
Known gotchas when self-hosting Whisper ASR Webservice
- The model is downloaded again every time the container starts unless you mount a cache volume; with a persistent cache you no longer receive model updates. source
- Speaker diarization needs the WhisperX engine and a Hugging Face token (HF_TOKEN) to download the diarization model. source
- GPU acceleration in Docker works only on Linux hosts; Docker on macOS cannot pass the GPU through. source
- Distilled models (distil-large-v3 and others) work only with the faster_whisper and whisperx engines, not the default openai_whisper engine. source
Alternatives in Speech & translation
- whisper.cpp Fast C/C++ port of OpenAI Whisper speech recognition with a small HTTP transcription server.
- PDFMathTranslate PDF translator that keeps the original layout, formulas, charts and tables.
- Meetily Desktop meeting recorder that transcribes and summarizes meetings locally.
- LibreTranslate Self-hosted machine translation API with no dependency on Google or DeepL.
- Speaches OpenAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper).
- Scriberr Self-hosted web app that transcribes audio offline, with speaker labels and AI summaries.
Whisper ASR Webservice FAQ
How much RAM does Whisper ASR Webservice need?
Whisper ASR Webservice does not publish an official RAM figure, so we do not state one. Memory use depends on the Whisper model you pick (tiny to large-v3). GPU passthrough does not work in Docker on macOS.
Does Whisper ASR Webservice need a GPU?
Optional (GPU image with --gpus all). A CPU image is available; on CPU the default quantization is int8.
How much does it cost to self-host Whisper ASR Webservice?
The software is free to download. The project publishes no official RAM figure, so we do not estimate a monthly server cost.
Is Whisper ASR Webservice free for commercial use?
Whisper ASR Webservice is licensed under MIT (Permissive). Internal business use is allowed under the license text. Permissive. Internal and commercial use allowed; keep the license notice. The image bundles FFmpeg libraries under the LGPL-2.1. This is a summary, not legal advice.
What are common problems when self-hosting Whisper ASR Webservice?
The model is downloaded again every time the container starts unless you mount a cache volume; with a persistent cache you no longer receive model updates. Speaker diarization needs the WhisperX engine and a Hugging Face token (HF_TOKEN) to download the diarization model. GPU acceleration in Docker works only on Linux hosts; Docker on macOS cannot pass the GPU through. Distilled models (distil-large-v3 and others) work only with the faster_whisper and whisperx engines, not the default openai_whisper engine.
Is Whisper ASR Webservice still maintained?
Yes, it is actively developed. Last commit: Aug 9, 2026. Latest release: v1.10.0 (Aug 9, 2026). Checked Oct 27, 2026.
How do I install Whisper ASR Webservice?
The official method is Docker. The exact commands are in the "How to deploy" section above and in the official instructions: https://ahmetoner.github.io/whisper-asr-webservice/run/
What are self-hosted alternatives to Whisper ASR Webservice?
Other apps in Speech & translation: whisper.cpp, PDFMathTranslate, Meetily, LibreTranslate, Speaches, Scriberr.
Sources
- GitHub repository: github.com/ahmetoner/whisper-asr-webservice
- Official documentation: ahmetoner.github.io/whisper-asr-webservice/
- License text: github.com/ahmetoner/whisper-asr-webservice/blob/main/LICENCE
- Hardware requirements, Deploy instructions, Gotcha 1, Gotcha 3: ahmetoner.github.io/whisper-asr-webservice/run/
- Gotcha 2, Gotcha 4: ahmetoner.github.io/whisper-asr-webservice/environmental-variables/
- Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
- GitHub stars, commits and releases: GitHub REST API, fetched
Facts on this page were checked against the project's own repository and docs on 2026-10-27. Spotted something out of date? Tell us.