schibsted/WAAS

What is it?

Key features

• 01Asynchronous transcription jobs processed by a Redis-backed queue and worker.
• 02Completion notifications via email or signed webhook callbacks.
• 03Export results as JSON, SRT, WebVTT, plain text, or timecoded text.
• 04Browser-based local editor for reviewing and correcting transcript segments.
• 05Language detection and transcribe-or-translate tasks through the API.
• 06docker-compose setup with optional NVIDIA CUDA support.

Use cases

• Transcribing recorded interviews or meetings on an internal server instead of a cloud service.
• Generating subtitle files (SRT or VTT) for video content in batches.
• Adding speech-to-text to an internal application through the HTTP API with webhook callbacks.
• Reviewing and correcting machine transcripts in the local browser editor.

Quick start

1. 1

   Create a Python virtual environment

   python3 -mvenv .venv
2. 2

   Activate the virtual environment

   source .venv/bin/activate
3. 3

   Install the Python requirements

   pip install -r requirements.txt
4. 4

   Create the .envrc file and allowed_webhooks.json as described in the README, then start all containers

   docker-compose --env-file .envrc up

Things to know

• !Needs a GPU with VRAM for larger Whisper models; the smallest model needs about 1GB.
• !Requires Python 3.8-3.10 and a Redis instance, plus SMTP settings for email callbacks.
• !Full setup via docker-compose requires configuring several environment variables and a webhook file.

In collections

Topics

FAQ

What is WAAS?

A self-hosted GUI and REST API for OpenAI Whisper speech-to-text, with a job queue, email or webhook callbacks, and SRT/VTT/text output. WaaS (Whisper as a Service) wraps OpenAI Whisper in a web GUI and an HTTP API so audio or video files can be transcribed without running the model by hand. Clients submit a file to the transcribe endpoint, which places the job on a Redis-backed queue processed by a separate worker. When a job finishes, the user is notified by email or by a signed webhook POST.

Is WAAS free to use? What license does it have?

WAAS is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.

Is WAAS still maintained?

Actively maintained. The last commit to WAAS was on Oct 30, 2026.

What can I use WAAS for?

Transcribing recorded interviews or meetings on an internal server instead of a cloud service. Generating subtitle files (SRT or VTT) for video content in batches. Adding speech-to-text to an internal application through the HTTP API with webhook callbacks. Reviewing and correcting machine transcripts in the local browser editor.

How do I install WAAS?

Create a Python virtual environment: python3 -mvenv .venv Activate the virtual environment: source .venv/bin/activate Install the Python requirements: pip install -r requirements.txt Create the .envrc file and allowed_webhooks.json as described in the README, then start all containers: docker-compose --env-file .envrc up

Where can I get WAAS?

The source code and installation instructions are on GitHub: https://github.com/schibsted/WAAS