Speechmatics Speed Test Bot (Pipecat)

Test Speechmatics real-time transcription speed and end-to-end voice latency using Pipecat AI.

This bot uses:

• Speechmatics (STT)
• Groq (LLM)
• Cartesia (TTS)

It runs locally using your microphone and speakers.

Prerequisites

• Speechmatics API key: https://portal.speechmatics.com/
• Groq API key: https://console.groq.com/
• Cartesia API key: https://play.cartesia.ai/sign-up
• Python 3.10+ (Python 3.12 recommended)
• PortAudio (required for local audio)

Quick Start

1. Install PortAudio

   • macOS: brew install portaudio

2. Create and activate a virtual environment

   • cd python
   • python3 -m venv venv
   • source venv/bin/activate

3. Install dependencies

   • pip install --upgrade pip
   • pip install -r requirements.txt

4. Configure API keys

   • cp ../.env.example .env
   • Edit python/.env and set:
     • SPEECHMATICS_API_KEY=...
     • GROQ_API_KEY=...
     • CARTESIA_API_KEY=...

5. Run the example

   • python main.py

Troubleshooting

• Browser permissions

  • Allow microphone access when prompted.

• Connection issues

  • Try a different browser.
  • Disable VPN / check firewall rules.
  • Note: WebRTC uses UDP.

• Audio issues

  • Confirm microphone and speakers work and are not muted.