Rasa Voice Frontend

This project runs a Flask + Socket.IO voice frontend using Azure Speech services and a Rasa backend.

Run with Docker

1. Build the image

docker build -t rasa-voice-frontend .

2. Create an env file from template

cp template.env .env

Update .env with real values (especially Azure credentials and demo login credentials).

3. Start the container

docker run --rm -p 5001:5001 --env-file .env rasa-voice-frontend

The app will be available at:

• http://localhost:5001

Required Environment Variables

The container entrypoint enforces these at startup. If they are missing, empty, or left as template placeholders, the container exits.

• AZURE_SPEECH_KEY (required, secret)
• AZURE_SERVICE_REGION (required)
• APP_USERNAME (required)
• APP_PASSWORD (required, secret)

The app requires login before loading the main UI. After startup, open http://localhost:5001, then sign in with APP_USERNAME and APP_PASSWORD.

Optional Environment Variables

• APP_SECRET_KEY (recommended; used for Flask session signing)
• RASA_URL (default: http://localhost:5005)
• RASA_TIMEOUT (default: 10)
• RASA_TOKEN (optional, secret; set only if your Rasa server requires auth)

Example .env

AZURE_SPEECH_KEY=your_real_azure_speech_key
AZURE_SERVICE_REGION=eastus
APP_USERNAME=demo_user
APP_PASSWORD=your_demo_password
APP_SECRET_KEY=replace_with_a_long_random_secret
RASA_URL=http://host.docker.internal:5005
RASA_TIMEOUT=10
RASA_TOKEN=

Notes on Secrets

• Do not hardcode secrets in Dockerfile.
• Pass secrets at runtime via --env-file or -e.
• Do not commit real secret values to git.