examples/speech-to-speech/README.md

Speech to Speech Example

In this example, we showcase how to build a simple speech-to-speech voice assistant pipeline using nvidia-pipecat along with pipecat-ai library and deploy for testing. This pipeline uses a Websocket based ACETransport, Riva ASR and TTS models and NVIDIA LLM Service. We recommend first following the Pipecat documentation or the ACE Controller Pipecat overview section to understand core concepts.

Prerequisites

1. Copy and configure the environment file:

   cp env.example .env  # and add your credentials
   

2. Ensure you have the required API keys:

   • NVIDIA_API_KEY - Required for accessing NIM ASR, TTS and LLM models
   • (Optional) ZEROSHOT_TTS_NVIDIA_API_KEY - Required for zero-shot TTS

Option 1: Deploy Using Docker

Prerequisites

• You have access and are logged into NVIDIA NGC. For step-by-step instructions, refer to the NGC Getting Started Guide.

• You have access to an NVIDIA Volta™, NVIDIA Turing™, or an NVIDIA Ampere architecture-based A100 GPU. For more information, refer to the Support Matrix.

• You have Docker installed with support for NVIDIA GPUs. For more information, refer to the Support Matrix.

From the example/speech-to-speech directory, run below commands:

docker compose up -d

Option 2: Deploy using Python environment

Prerequisites

From the examples/speech-to-speech directory, run the following commands to create a virtual environment and install the dependencies:

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install dependencies
uv sync

Make sure you've configured the .env file with your API keys before proceeding.

After making all required changes/customizations in bot.py, you can deploy the pipeline using below command:

python bot.py

Start interacting with the application

This will host the static web client along with the ACE controller server, visit http://WORKSTATION_IP:8100/static/index.html in your browser to start a session.

Note: For mic access, you will need to update chrome://flags/ and add http://WORKSTATION_IP:8100 in Insecure origins treated as secure section.

If you want to update the port, make changes in the uvicorn.run command in the bot.py and the wsUrl in the static/index.html.

Bot customizations

Enabling Speculative Speech Processing

Speculative speech processing reduces bot response latency by working directly on Riva ASR early interim user transcripts instead of waiting for final transcripts. This feature only works when using Riva ASR.

• Refer to the comments in bot.py for guidance on enabling or disabling specific frame processors as needed.

• See the ACE Controller Microservice documentation on Speculative Speech Processing for more details.

Switching ASR, LLM, and TTS Models

You can easily customize ASR (Automatic Speech Recognition), LLM (Large Language Model), and TTS (Text-to-Speech) services by configuring environment variables. This allows you to switch between NIM cloud-hosted models and locally deployed models.

The following environment variables control the endpoints and models:

• RIVA_ASR_URL: Address of the Riva ASR (speech-to-text) service (e.g., localhost:50051 for local, "grpc.nvcf.nvidia.com:443" for cloud endpoint).
• RIVA_TTS_URL: Address of the Riva TTS (text-to-speech) service. (e.g., localhost:50051 for local, "grpc.nvcf.nvidia.com:443" for cloud endpoint).
• NVIDIA_LLM_URL: URL for the NVIDIA LLM service. (e.g., http://<machine-ip>:8000/v1 for local, "https://integrate.api.nvidia.com/v1" for cloud endpoint. )

You can set model, language, and voice using the RIVA_ASR_MODEL, RIVA_TTS_MODEL, NVIDIA_LLM_MODEL, RIVA_ASR_LANGUAGE, RIVA_TTS_LANGUAGE, and RIVA_TTS_VOICE_ID environment variables.

Update these variables in your Docker Compose configuration to match your deployment and desired models. For more details on available models and configuration options, refer to the NIM NVIDIA Magpie, NIM NVIDIA Parakeet, and NIM META Llama documentation.

Example: Switching to the Llama 3.3-70B Model

To use larger LLMs like Llama 3.3-70B model in your deployment, you need to update both the Docker Compose configuration and the environment variables for your Python application. Follow these steps:

• In your docker-compose.yml file, find the nvidia-llm service section.
• Change the NIM image to 70B model: nvcr.io/nim/meta/llama-3.3-70b-instruct:latest
• Update the device_ids to allocate at least two GPUs (for example, ['2', '3']).
• Update the environment variable under python-app service to NVIDIA_LLM_MODEL=meta/llama-3.3-70b-instruct

Setting up Zero-shot Magpie Latest Model

Follow these steps to configure and use the latest Zero-shot Magpie TTS model:

1. Update Docker Compose Configuration

Modify the riva-tts-magpie service in your docker-compose file with the following configuration:

 riva-tts-magpie:
  image: <magpie-tts-zeroshot-image:version>  # Replace this with the actual image tag
  environment:
    - NGC_API_KEY=${ZEROSHOT_TTS_NVIDIA_API_KEY}
    - NIM_HTTP_API_PORT=9000
    - NIM_GRPC_API_PORT=50051
  ports:
    - "49000:50051"
  shm_size: 16GB
  deploy:
    resources:
      reservations:
        devices:
          - driver: nvidia
            device_ids: ['0']
            capabilities: [gpu]

• Ensure your ZEROSHOT_TTS_NVIDIA_API_KEY key is properly set in your .env file:

  ZEROSHOT_TTS_NVIDIA_API_KEY=
  

2. Configure TTS Voice Settings

Update the following environment variables under the python-app service:

RIVA_TTS_VOICE_ID=Magpie-ZeroShot.Female-1
RIVA_TTS_MODEL=magpie_tts_ensemble-Magpie-ZeroShot

3. Zero-shot Audio Prompt Configuration

To use a custom voice with zero-shot learning:

• Add your audio prompt file to the workspace
• Mount the audio file into your container by adding a volume in your docker-compose.yml under the python-app service:

  services:
    python-app:
      # ... existing code ...
      volumes:
        - ./audio_prompts:/app/audio_prompts
  

• Set the ZERO_SHOT_AUDIO_PROMPT environment variable to the path relative to your application root:

  environment:
    - ZERO_SHOT_AUDIO_PROMPT=audio_prompts/voice_sample.wav  # Path relative to app root
  

Note: The zero-shot audio prompt is only required when using the Magpie Zero-shot model. For standard Magpie multilingual models, this configuration should be omitted.