Kokoro 82M
Lightweight 82M parameter text-to-speech model with natural voices.
Input Types
text
Output Types
audio
Capabilities
- Text-to-speech
- Natural voices
- Lightweight
Use Cases
- Voice-overs
- Narration
- Accessibility
Tags
tts lightweight fast
Documentation
License: Open Source
Similar Models
MiniMax (via Replicate)
Speech 02 HD
High-definition text-to-speech with premium voice quality.
Fal.ai
Maya TTS
State-of-the-art speech model for expressive voice generation.
Fal.ai
Chatterbox TTS
Text-to-speech for memes, videos, games, and AI agents.
Coqui (via Replicate)
XTTS-v2
Clone any voice with just 6 seconds of audio. Supports 17 languages.
Use Kokoro 82M in Promptha
Create powerful AI workflows using Kokoro 82M and other models on Promptha.