Token
Extract text or detect regions from uploaded images
Extract text or detect regions from uploaded images
Convert source voice to match a reference voice
Convert speech to sound like another voice
Transcribe WAV audio into wordβlevel timestamps
Generate wordβlevel timestamps from uploaded WAV audio
Extract vocals from any song in seconds
Extract vocals from any audio file
Translate English SRT subtitles to Hindi instantly
Kokoro, But It Clones Voices Now
Clone a voice to speak custom text
RVC-v2 Beatrice-v2 - CPU inference + training
RVC-v2 Beatrice-v2 - CPU inference + training
Clone a voice from a sample to speak any text
Clone a voice to speak your text
Generate wordβlevel transcript with timestamps from audio
Transcribe audio with speaker diarization
Transcribe audio files to text with batch processing
Generate custom voice audio from text and a speaker sample