Tool
Kokoro TTS
Tiny ~82M Apache-2.0 TTS with strong English quality
About
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.
As of April 2025, the market rate of Kokoro served over API is under $1 per million characters of text input , or under $0.06 per hour of audio output. (On average, 1000 characters of input is about 1 minute of output.) Sources: ArtificialAnalysis/Replicate at 65 cents per M chars and DeepInfra at 80 cents per M chars .
This is an Apache-licensed model, and Kokoro has been deployed in numerous projects and commercial APIs. We welcome the deployment of the model in real use cases.
Fake websites like kokorottsai_com (snapshot: https://archive.ph/nRRnk ) and kokorotts_net (snapshot: https://archive.ph/60opa ) are likely scams masquerading under the banner of a popular model.
Features
- Website Tasks
- Organizations
- Daily Papers
- Solutions Team & Enterprise
- Hugging Face PRO
- Enterprise Support
- Pricing
- Open Source
- Pricing detail
- Apache-2.0 tiny TTS weights on Hugging Face
- Platforms
- Local, API, CLI
Alternatives from our catalog
Tools on the same shelves as Kokoro TTS, ordered by shared tags and our own comparisons. Not vendor endorsements.
- VibeVoiceOpen Source · Desktop, Local
Privacy-first Qwen3-TTS workflow; free GPU-local
also in AI Audio
- IzwiOpen Source · Desktop, CLI, API, Local
Desktop/CLI/server in one; docs at izwiai.com
also in AI Audio
- Fish SpeechOpen Source · Local, API
Often cited as open alternative for cloning quality
also in AI Audio
- MeloTTSOpen Source · Local, API
CPU-friendly; MIT
also in AI Audio
- GradiumFreemium · API, Web
Strong pronunciation / agent-focused positioning
also in AI Audio
- RimeUsage-based · API, On-prem
Enterprise pronunciation accuracy niche
also in AI Audio