Molten Hub Code Voice Dictation Setup

Run Molten Hub Code with Faster Whisper so you can dictate prompts from the Code UI.

Use this guide to run Molten Hub Code with local voice dictation through a Faster Whisper service.

Overview

This Docker Compose setup runs two services:

• agent: the Molten Hub Code application.
• whisper: the Faster Whisper transcription service.

The agent connects to the whisper container for speech processing using MOLTEN_HUB_SPEECH_HOST and MOLTEN_HUB_SPEECH_PORT.

docker-compose.yml

View the full docker-compose.yml source file.

services:
  agent:
    image: moltenai/moltenhub-code:vnext
    environment:
      - MOLTEN_HUB_SPEECH_HOST=whisper
      - MOLTEN_HUB_SPEECH_PORT=10300
    command:
      - harness
      - hub
      - --ui-listen
      - :7777
    ports:
      - '3331:7777'
    depends_on:
      - whisper
    restart: unless-stopped

  whisper:
    image: lscr.io/linuxserver/faster-whisper:latest
    environment:
      - PUID=${PUID:-1000}
      - PGID=${PGID:-1000}
      - TZ=${TZ:-America/Vancouver}
      - WHISPER_MODEL=${WHISPER_MODEL:-auto}
      - WHISPER_LANG=${WHISPER_LANG:-auto}
      - WHISPER_BEAM=${WHISPER_BEAM:-1}
    volumes:
      - ./data/whisper:/config
    ports:
      - '${WHISPER_PORT:-10300}:10300'
    restart: unless-stopped

Start the Stack

1. Save the snippet as docker-compose.yml.
2. Run docker compose up -d from the same directory.
3. Open http://localhost:3331.

Use Voice Dictation

Once the stack is running, use the voice controls in the Molten Hub Code prompt composer.

1. Click the voice dictation button in the composer.

   

2. Speak while Molten Hub Code shows the capturing state.

   

3. Review the transcribed text before you send the prompt.

   

What This Does

• Starts Molten Hub Code in the agent container.
• Starts Faster Whisper in the whisper container.
• Connects the agent to Whisper using MOLTEN_HUB_SPEECH_HOST=whisper and MOLTEN_HUB_SPEECH_PORT=10300.
• Exposes the Molten Hub Code UI on port 3331.