netease-youdao / EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Apache License 2.0
7.46k stars 633 forks source link

Getting Same voice with Different Emotion Prompts #29

Open ShivamSinghal1 opened 1 year ago

ShivamSinghal1 commented 1 year ago

Speaker - Maria_Kasper Text - "Emoti Voice is a powerful and modern open-source text-to-speech engine. Emoti Voice speaks both English and Chinese, and with over two thousand different voices. The most prominent feature is emotional synthesis, allowing you to create speech with a wide range of emotions, including happy, excited, sad, angry and others" Emotion Prompts Tried - Happy / Sad / Excited / Angry / Whisper / Shout Generated Audios - https://drive.google.com/drive/folders/1JqWnVFSiu5DMyZhGt7XyGXhrlB6eCvPR?usp=sharing Generated Using the Demo UI

Can someone please help, if i am missing something here?

rafaels88 commented 1 year ago

Same happened here. It would be interesting to understand what's the available options for the prompt field

MaxLikesCode commented 1 year ago

It works if you translate the emotion to chinese. And even then, the difference is very subtle and it only works with Sad, Angry and Exited in my tests.

Sad -> δΌ€εΏƒ Angry -> η”Ÿζ°”ηš„ Excited -> ε…΄ε₯‹ηš„

This needs to be fixed.

syq163 commented 1 year ago

Thanks to @MaxLikesCode for the prompt fix. We will work on enhancing the prompt's capability in the future.

deguodedongxi commented 8 months ago

Is there any update on this one? The emotional conversion would be very helpful, but it still doesn't seem to have any effect.