SarvamAITTS
Sarvam AI text-to-speech (TTS) synthesizer.Constructor
Sarvam AI API key. Defaults to the
SARVAM_API_KEY environment variable.TTS model id. Default
'bulbul:v3'.Language code. Default
'en-IN'.Speaker/voice id. Default
'shubh'.Stream audio as it is synthesized. Default
true.Output audio sample rate in Hz. Default
24000.Output audio codec.
Pitch adjustment. Default
0.0.Speaking pace multiplier. Default
1.0.Loudness multiplier. Default
1.0.Sampling temperature. Default
0.6.Output audio bitrate. Default
'128k'.Minimum buffer size before emitting audio.
Maximum characters per synthesis chunk.
Enable text preprocessing/normalization. Default
false.close
closeEmitter
emit
getRuntimeConfig
interrupt
listenerCount
off
on
once
onFirstAudioByte
removeAllListeners
synthesize
text on the active session.