Skip to content

Runtime guide

Connect speech input to Open WebUI

Route dictation in Open WebUI to an Oruk model served on your own transcription endpoint.

Check the transcription server

Start the vLLM example first and confirm that its audio upload returns a text field. Open WebUI must be able to reach this endpoint from its backend. Loopback works when both processes share the same host network.

Set the speech-to-text provider

In Admin Settings → Audio, select an OpenAI-compatible speech-to-text provider. Enter the transcription server’s base URL, model ID and, for an authenticated server, its key. Leave the audio request format set to multipart.

Settings for a new same-host instance
AUDIO_STT_ENGINE=openai
AUDIO_STT_OPENAI_API_BASE_URL=http://127.0.0.1:8000/v1
AUDIO_STT_MODEL=oruk/orukqwen-asr-1.7b-v2
AUDIO_STT_OPENAI_API_REQUEST_FORMAT=multipart

Dictate a test phrase

  1. Open a chat, allow microphone access and record a short phrase. Check the resulting input text before sending it.
  2. If Open WebUI runs in a separate container, configure an authenticated private endpoint reachable from the container. Inside the container, localhost identifies the container itself.
  3. On an existing installation, saved admin settings take precedence over initial environment variables. Update the Audio settings and try the same recording again.