Dedicated model · Available as managed deployment
Kokoro — an 82-million-parameter open-weight text-to-speech model with natural voices, fast enough for real-time use, under Apache-2.0. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Why AxForge
| Real-time on one machine | 82M parameters: a dedicated DGX Spark synthesises speech many times faster than real time, for many concurrent streams. |
|---|---|
| Natural voices, several languages | Multiple voices and languages in one small model, with quality close to models many times its size. |
| Apache-2.0 | Permissive weights — commercial use, no licence conversation, no per-character vendor pricing. |
Specifications
| Model | Kokoro — hexgrad |
|---|---|
| Modalities | Text → speech |
| Licence | Open weights — apache-2.0; commercial use permitted |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Full details, benchmarks and FAQ on the Kokoro page. Prices exclude VAT.
How it works
| 1 | Request deployment — describe your traffic, context needs and rental term. |
|---|---|
| 2 | You receive the configuration, hardware rental and managed-service price in writing before anything is billed. |
| 3 | AxForge deploys Kokoro on a dedicated DGX Spark reserved for you. |
| 4 | Point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | Adjust the term — hour, week, month or year — as your workload settles. |
Request deployment or sign in to start.
FAQ
Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
Piper is the lightweight TTS AxForge serves per character; Kokoro is the higher-quality option for a dedicated deployment where voice quality matters.
Several English voices plus other languages; AxForge lists the voices available in your build with the deployment.
AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.
Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.