Kokoro-82M
Released
2025-01-27
Last refreshed
2026-11-18
Status
Researched today
Open sourceCommercial use: permittedMultimodalVisionAudio
Specifications
- Family
- Kokoro
- Released
- 2025-01-27
- Parameters
- 82M
- Architecture
- Audio / Speech
- Specialization
- text-to-speech
- Openness
- Open source
- License
- Apache 2.0OSI-approvedPermitted
- Weights
- Available
- Code
- Unknown
Pricing
Input / 1M chars
$0.62/1M chars
Cheapest of 4 routes · OpenRouter
Links
Pricing
Input / 1M chars
$0.62/1M chars
Cheapest of 4 routes · OpenRouter
Links
About
Kokoro-82M is an open-weight text-to-speech model with 82 million parameters and Apache-2.0 weights, published by hexgrad on Hugging Face.
Providers(4)
Compare all 4Compare published input / 1m chars across 4 tracked provider routes.
| Provider | Input / 1M chars | Route |
|---|---|---|
| OpenRouter | $0.62/1M chars | Serverless |
| FlexAI | $0.99/1M chars | Serverless |
| Together AI | $4.00/1M chars | Serverless |
| fal API | $20.00/1M chars | Serverless |
Available via routers & gateways(1)
Capabilities
MultimodalAudio
Benchmark peer barsfor Vision
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
Kokoro-82Mhexgrad/Kokoro-82M