Closed rosscado closed 3 days ago
A voice synthesis request by Inflection looks like this, with an audio/mpeg
response type.
GET https://pi.ai/api/chat/voice?mode=eager&voice=voice4&messageSid=PzSgpCg8qxYFcRZsVmw2X
Closed with the release of multilingual voices in v1.6.0. 🎉
Pi is capable of generating text responses in non-English languages. However, when Pi reads those text responses aloud, it speaks with an English accent, whatever the language of the text.
This appears to be due to Inflection using one of ElevenLab's English-only voice synthesis models.
Either of ElevenLab's multilingual models give far better spoken results on the same text input.
Attempt to override Pi's voice synthesis for non-English languages (only), and substitute our own using a multilingual TTS model.