Spark TTS
A text-to-speech model powered by SparkAudio and Mobvoi.
Actually Kokoro can do anything Microsoft Edge tts does what about adding pitch support too? I don't think it's something to be embedded in the model tho I guess we have to do it as a post processing right?
Holy moly my goodness this model is amazing, thank you for writing this blog and hosting a demo, this is literally the best the best TTS I've ever seen 10 times better than any other model I've seen
Generate customized images using text and an ID image
Quickly edit the expression of a face
Import a portrait, click to move the head!
MaskGCT TTS Demo
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)