Text-to-speech service implementation using the Piper TTS server
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 headers automatically removed)TTSStoppedFrame
- Signals completion of synthesisErrorFrame
- HTTP server or processing errorsen_US-lessac-medium
- Natural female voice, balanced qualityen_US-ryan-high
- High-quality male voiceen_US-amy-medium
- Clear female voiceen_GB-alan-medium
- British male voicevoice_id
parameter: