Overview
GroqTTSService provides fast text-to-speech synthesis using Groq’s TTS API with multiple voice options.
Groq TTS API Reference
Pipecat’s API methods for Groq TTS integration
Example Implementation
Complete example with Groq STT and LLM
Groq Documentation
Official Groq API documentation and models
Voice Options
Explore available voice models and features
Installation
To use Groq services, install the required dependencies:Prerequisites
Groq Account Setup
Before using Groq TTS services, you need:- Groq Account: Sign up at Groq Console
- API Key: Generate an API key from your account dashboard
- Voice Selection: Choose from available voice models
Required Environment Variables
GROQ_API_KEY: Your Groq API key for authentication
Configuration
GroqTTSService
str
required
Groq API key for authentication.
str
default:"None"
deprecated
Deprecated since 0.0.105, removed in 2.0.0. Use
settings=GroqTTSService.Settings(model=...) instead.str
default:"None"
deprecated
Deprecated since 0.0.105, removed in 2.0.0. Use
settings=GroqTTSService.Settings(voice=...) instead.str
default:"wav"
Audio output format. Must be
"wav": the service decodes each response as
WAV, so any other format produces an ErrorFrame instead of audio.int | None
default:"None"
Audio sample rate in Hz. Not sent to Groq: audio frames carry the sample rate
of the WAV that Groq returns, so this value doesn’t change the output audio.
InputParams
default:"None"
deprecated
Deprecated since 0.0.105, removed in 2.0.0. Use
settings=GroqTTSService.Settings(...) instead.Settings
Runtime-configurable settings passed via thesettings constructor argument using GroqTTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.