Kokoro 82M
by hexgradSpeech synthesis
Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese)...
- Context
- 4.1K tokens
- Max output
- 3,686 tokens
- Released
- 2026-04-23
- Weights
- unknown
hexgrad/kokoro-82m
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-04-23
- Weights
- unknown
- Input
- Text
- Output
- speech
- Context window
- 4,096 max across endpoints
- Max output
- 3,686
- Providers
- 0 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- no comparable direct price
More details
- Last updated
- —
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool callingunknown
- Parallel toolsunknown
- Structured outputunknown
- Reasoningunknown
- Image inputunknown
- PDF inputunknown
- Audio inputunknown
- Audio outputunknown
- Video inputunknown
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperatureunknown
- Streamingunknown
- Attachmentsunknown
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Cost calculator
Loading endpoints…
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model