Foundation 1
🚀
66
Generate custom music clips from text prompts
Transcribe audio files with timestamps and download transcripts
Generate speech in a cloned voice from a short audio sample
Voice cloning model
A text-to-speech model powered by SparkAudio and Mobvoi.
Voice Clone Multilingual TTS
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
Try Orpheus TTS here
New Ghibli EasyControl model is now released!!
Generate custom scenes with your own character image
Describe any selected part of an image