Kokoro · Hexgrad
Kokoro is an extremely efficient open-source TTS model. Surprising quality for its size. No cost for use.
About Kokoro
Kokoro is an extremely efficient open-source TTS model. Surprising quality for its size. No cost for use.
Where it shines: 100% free · Open-weights · High speed.
How to use Kokoro
-
1
Write the text
Paste the text to convert to voice. Up to 3000 characters per generation.
-
2
Generate
Click the main button. Wait 2-30 seconds depending on the model and input size.
-
3
Download or share
Download the result or share the direct link. No watermark, ready to use.
Frequently asked questions
How much does it cost to use Kokoro?
Kokoro is one of the free models in the catalog, each use discounts 50 tokens from your pool, but open models like Kokoro don’t cost us, so the rate-limit is generous. A free account comes with 500 initial tokens and 25 more every day — you usually don’t get to touch the card.
Is there a limit on how Kokoro is used?
There is no fixed monthly fee for Kokoro on the free account — the actual limit is the rate per minute/hour, not per month. Anonymous are limited by IP; with account you can do much more volume, if you reach 500+25 tokens and need more, a Pro plan at $9/month covers it.
What makes Kokoro special?
Hexgrad released Kokoro with open weights — one of the most efficient TTSs out there, surprisingly for its size, with specific strengths: 100% free, open-weights and high speed.
How much latency does Kokoro have?
Kokoro is one of the faster models: typically ~300ms latency per generation.Latency matters when you're using it in voice assistants; for pre-recorded narration it's quality, not latency, that matters.
How do I use Kokoro on ia.gratis?
You can use Kokoro from /audio/voice/ with Kokoro in the voice selector, or via the REST API by sending the text and `model=kokoro`. Quick summary: open-source. Free and very fast. The internal model identifier is `kokoro` — useful when integrating via API.