Kokoro
Small open text-to-speech model
Kokoro is an open text to speech model with a small parameter count. It ships under the Apache 2.0 license. The repo provides the inference library and a set of voices.
More in Music & sound
Featured
Featured




ElevenLabs
Music & sound
Voice, speech and sound effect generation
Suno
Music & sound
Song generator with vocals from text prompts
ACE-Step
Music & sound
Open music generation foundation model
AudioCraft
Music & sound
Meta's library for music and audio generation
Coqui TTS
Music & sound
Open source text-to-speech toolkit
Fish Speech
Music & sound
Open multilingual text-to-speech model