Whisper ASR logo
AI · self-hosted

Whisper ASR in one click.

Whisper ASR is an openai whisper speech-to-text api service you can run on your own machine. Launch it in Even Stacks in one click, serve it over trusted HTTPS, and let your AI agents operate it.

What is Whisper ASR?

Whisper ASR Webservice wraps OpenAI's Whisper speech recognition model in a containerized REST API. It exposes transcription and translation endpoints compatible with standard HTTP clients.

CategoryAI
Default port8804
Container imageonerahmet/openai-whisper-asr-webservice:latest

Run Whisper ASR in Even

Even Stacks launches Whisper ASR as a managed container on your own machine. No compose files, no manual setup.

  1. Open the Even Stacks panel in Even. The container engine starts on demand.
  2. Find Whisper ASR in the one-click services and click Launch.
  3. Even pulls the image, starts it on port 8804, and serves it over trusted HTTPS at https://whisper-asr.localhost.

Drive Whisper ASR with your AI agents

Even ships an MCP, so any agent you run inside Even (Claude Code, Codex, and more) can operate Whisper ASR directly, at both the UI level and the container level.

Through the Even MCP an agent can pull a model, call the local endpoint, and wire it into a tool, all on your own hardware. It runs commands inside the container, reads its logs, and for web apps opens and clicks through the interface in Even's own browser pane. Ask once, for example "set up Whisper ASR and get it ready", and the agent handles it end to end.

How agents reach it: Transcribe audio by POSTing multipart/form-data with an audio file field to http://localhost:8804/asr; add ?language=en for language hints or ?task=translate for translation. Response is plain text or JSON depending on the Accept header. No persistent data is stored.

More AI services

Other one-click services you can launch in Even Stacks.