Groq

Text-to-speech service implementation using Groq’s TTS API

Overview

Groq’s TTS API provides fast text-to-speech synthesis with multiple voice options. The service operates at a fixed 48kHz sample rate and offers efficient audio streaming for real-time applications.

API Reference

Complete API documentation and method details

Groq TTS Docs

Official Groq API documentation and models

Example Code

Working example with Groq STT and LLM

Installation

To use Groq services, install the required dependencies:

pip install "pipecat-ai[groq]"

You’ll also need to set up your Groq API key as an environment variable: GROQ_API_KEY.

Get your API key by signing up at Groq Console.

Frames

Input

• TextFrame - Text content to synthesize into speech
• TTSSpeakFrame - Text that should be spoken immediately
• TTSUpdateSettingsFrame - Runtime configuration updates
• LLMFullResponseStartFrame / LLMFullResponseEndFrame - LLM response boundaries

Output

• TTSStartedFrame - Signals start of synthesis
• TTSAudioRawFrame - Generated audio data chunks (WAV format)
• TTSStoppedFrame - Signals completion of synthesis
• ErrorFrame - API or processing errors

Voice Models

Groq TTS supports various voice options through the PlayAI model:

Voice ID	Description	Gender
Celeste-PlayAI	Natural, conversational voice	Female
Iris-PlayAI	Professional, clear voice	Female
Oliver-PlayAI	Warm, friendly voice	Male
William-PlayAI	Authoritative, confident voice	Male

Voice availability may vary. Check the Groq documentation for the latest available voices.

Audio Configuration

Sample Rate

• Fixed at 48kHz - Groq TTS only supports 48,000 Hz sample rate
• Automatic resampling if pipeline uses different rates

Usage Example

Basic Configuration

Initialize GroqTTSService and use it in your pipeline:

from pipecat.services.groq.tts import GroqTTSService
from pipecat.transcriptions.language import Language
import os

# Configure service
tts = GroqTTSService(
    api_key=os.getenv("GROQ_API_KEY"),
    model_name="playai-tts",
    voice_id="Celeste-PlayAI",
    params=GroqTTSService.InputParams(
        language=Language.EN,
        speed=1.0
    )
)

# Use in pipeline
pipeline = Pipeline([
    transport.input(),
    stt,
    context_aggregator.user(),
    llm,
    tts,
    transport.output(),
    context_aggregator.assistant()
])

Dynamic Configuration

Make settings updates by pushing a TTSUpdateSettingsFrame for the GroqTTSService:

from pipecat.frames.frames import TTSUpdateSettingsFrame

await task.queue_frame(
    TTSUpdateSettingsFrame(settings={"voice": "your-new-voice-id"})
)

Metrics

The service provides comprehensive metrics:

• Time to First Byte (TTFB) - Latency from text input to first audio
• Processing Duration - Total synthesis time

Learn how to enable Metrics in your Pipeline.

Additional Notes

• Fixed Sample Rate: Service operates at 48kHz only - resampling handled automatically
• Speed Control: Adjust speech rate from 0.5x to 2.0x normal speed