search

Migushthe2nd / MsEdgeTTS

A simple Azure Speech Service module that uses the Microsoft Edge Read Aloud API
https://migushthe2nd.github.io/MsEdgeTTS/
MIT License
287 stars 41 forks source link

Whether the role and styledegree fields are supported？ #11

Closed qingfengmy closed 11 months ago

qingfengmy commented 12 months ago

Whether the role and styledegree fields are supported？

const readable = tts.toStream(voiceOver, { rate: ${formatN(opt.rate)}%, pitch: ${formatN(opt.pitch)}st, volume: ${formatN(opt.volume)}%, });

like this

const readable = tts.toStream(voiceOver, { rate: ${formatN(opt.rate)}%, pitch: ${formatN(opt.pitch)}st, volume: ${formatN(opt.volume)}%, role, styledegree });

image

Migushthe2nd commented 12 months ago

No sorry :( Microsoft blocked the use of mstts:express-as tags in this API around a year ago.

Migushthe2nd commented 12 months ago

You could slightly tune the pitch and volume to express positive/negative emotions though

Migushthe2nd commented 12 months ago

Or try other prosody options using the raw methods: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#adjust-prosody