- 🆕 Open-weight 82M-parameter TTS model from developer Hexgrad.
- 📏 Compact size positions it for efficient inference, per catalog.
- 🔒 Apache-2.0 licensed and freely deployable.
- 🌐 Version 1.0 distributed as a community ONNX port.
- 🔧 Available via Hugging Face weights and a hosted demo Space.
- 💬 Converts written text into natural-sounding speech audio.
- 📚 Popular open-source baseline for voice applications.
- ⚡ Released March 2025 by an individual open-source developer.
Hexgrad is an AI development group focused on speech synthesis. The organization is best known for creating Kokoro, a lightweight yet capable text-to-speech model that has attracted attention in the open-weight AI community for delivering high-quality voice generation at a…
Kokoro is an open-weight text-to-speech model created by Hexgrad, an individual open-source developer, and released in this v1.0 form in March 2025. With just 82 million parameters, it takes text in and produces audio out, positioning it as a compact alternative to far larger speech systems. Its small footprint is its defining feature, and the catalog describes it as offering efficient inference and natural-sounding voices.
The weights are distributed under the permissive Apache-2.0 license, making the model freely deployable across both production and hobby settings. A community ONNX port of the v1.0 release is published on Hugging Face, broadening the runtimes and platforms on which the model can operate.
The ecosystem around Kokoro includes Hexgrad's hosted demo Space on Hugging Face, where the model can be tried directly in the browser. As the catalog notes, it remains an efficient, low-cost open-source baseline for developers building voice interfaces, audiobooks, and accessibility applications.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Kokoro Text to Speech · Organic sellers
| Seller | Health | Rep↓ | Sales | Routing | $ / 1M chars |
|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | — | #2 | $1.75 |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.4 h | 86.84 | $0.06 | #1 | $1.925 |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.