Text-to-speech service implementation using Groq’s TTS API
GROQ_API_KEY
.
TextFrame
- Text content to synthesize into speechTTSSpeakFrame
- Text that should be spoken immediatelyTTSUpdateSettingsFrame
- Runtime configuration updatesLLMFullResponseStartFrame
/ LLMFullResponseEndFrame
- LLM response boundariesTTSStartedFrame
- Signals start of synthesisTTSAudioRawFrame
- Generated audio data chunks (WAV format)TTSStoppedFrame
- Signals completion of synthesisErrorFrame
- API or processing errorsVoice 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 |
GroqTTSService
and use it in your pipeline:
TTSUpdateSettingsFrame
for the GroqTTSService
: