realtime playback of specific speaker id in multispeaker model

rhasspy / piper

A fast, local neural text to speech system

https://rhasspy.github.io/piper-samples/

MIT License

4.57k stars 315 forks source link

realtime playback of specific speaker id in multispeaker model #423

Closed LaptopDev closed 2 months ago

LaptopDev commented 2 months ago

How do you do a realtime playback of a specific speaker id with en_US-libritts_r-medium? This is a multispeaker model? Do you need to train it to get the specific speaker or is it baked into the .onnx and .onnx.json?

LaptopDev commented 2 months ago

ah, it was hiding in the --help output under --output_raw, --speaker [id] or -s [id]