Speech model
Kokoro 82M
hexgrad/kokoro-82m
hexgrad/kokoro-82m is a text-to-speech model from Hexgrad you can call on the OceanToken API at $0.00062 per 1,000 characters.
At a glance
| Model ID | hexgrad/kokoro-82m |
|---|---|
| Type | Speech |
| Publisher | Hexgrad |
| Price | $0.00062 per 1,000 characters of input text |
| Endpoint | /v1/audio/speech |
| API shape | OpenAI-compatible |
| In the catalog since | 2026-04-23 |
Call it
Base URL https://api.oceantoken.ai/v1, your OceanToken key as the bearer token, and the model ID above as model. The OpenAI SDKs work unchanged; see your first request.
curl https://api.oceantoken.ai/v1/audio/speech \
-H "Authorization: Bearer $OCEANTOKEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "hexgrad/kokoro-82m", "input": "Welcome to OceanToken."}' --output speech.mp3
Compared with similar models
Speech models on OceanToken closest to hexgrad/kokoro-82m in price. Every price is what you pay, in US dollars, with no platform fee on top.
| Model | Publisher | Context | Price (per 1K characters) |
|---|---|---|---|
| Kokoro 82M | Hexgrad | $0.00062 | |
Gemini 3.1 Flash TTS Previewgoogle/gemini-3.1-flash-tts-preview | $0.001 | ||
Orpheus 3B 0.1 Ftcanopylabs/orpheus-3b-0.1-ft | Canopylabs | $0.007 | |
Csm 1Bsesame/csm-1b | Sesame | $0.007 |
Use it
Create an account All models and prices
Prices and capabilities on this page were read from the live OceanToken catalog on 2026-10-18 (UTC), when the documentation was built. If a price has changed since, the console's Models page shows the current one.