Convert text to natural-sounding speech using Speechmatics TTS API.

Generate high-quality speech audio from text in under 5 minutes with minimal setup.

• How to use the Speechmatics TTS SDK
• Generate speech from text with different voices
• Save audio output to WAV files
• Available voice options (UK/US English)

• Speechmatics API Key: Get one from portal.speechmatics.com
• Python 3.8+

Step 1: Create and activate a virtual environment

On Windows:

cd python
python -m venv .venv
.venv\Scripts\activate

On Mac/Linux:

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

Step 2: Install dependencies

pip install -r requirements.txt

Step 3: Configure your API key

cp ../.env.example .env

Open the .env file and add your API key:

SPEECHMATICS_API_KEY=your_actual_api_key_here

Step 4: Run the example

python main.py

This is the complete code to generate speech:

import asyncio
import os
from dotenv import load_dotenv
from speechmatics.tts import AsyncClient, Voice, OutputFormat

load_dotenv()

async def main():
    api_key = os.getenv("SPEECHMATICS_API_KEY")

    text = "Hello! Welcome to Speechmatics text to speech."

    async with AsyncClient(api_key=api_key) as client:
        # Generate speech
        response = await client.generate(
            text=text,
            voice=Voice.SARAH,
            output_format=OutputFormat.WAV_16000,
        )

        # Read complete audio response and save to file
        audio_data = await response.read()
        with open("output.wav", "wb") as f:
            f.write(audio_data)

if __name__ == "__main__":
    asyncio.run(main())

from speechmatics.tts import Voice

# UK Female
voice = Voice.SARAH

# UK Male
voice = Voice.THEO

# US Female
voice = Voice.MEGAN

# US Male (use string ID)
voice = "jack"

Speechmatics Text-to-Speech Demo
========================================
Text: Hello! Welcome to Speechmatics text to speech. This is a demonstration of natural sounding speech synthesis.
Voice: Sarah (English UK Female)
Output: output.wav

Generating speech...
Audio saved to: assets/output.wav

Available voices:
  - sarah: English Female (UK)
  - theo: English Male (UK)
  - megan: English Female (US)
  - jack: English Male (US)

Now that you have basic TTS working, explore:

• Hello World - Transcribe audio (STT)
• Batch vs Real-time - Understand different STT modes
• LiveKit Voice Assistant - Build a complete voice agent with STT + LLM + TTS

Error: "Invalid API key"

• Check your .env file has the correct SPEECHMATICS_API_KEY
• Verify your key at portal.speechmatics.com
• Make sure there are no extra spaces or quotes around the key

Error: "Module not found"

• Make sure you installed dependencies: pip install -r requirements.txt
• Verify you're in the activated virtual environment

No audio output

• Check the assets/ folder for the output.wav file
• Try playing the file with your default audio player

• Speechmatics TTS Quickstart
• Speechmatics TTS Product Page
• API Reference

Help us improve this guide:

• Found an issue? Report it
• Have suggestions? Open a discussion

Time to Complete: 5 minutes Difficulty: Beginner SDK: TTS

Back to Basics | Back to Academy