Smallest download
Use KittenTTS Nano for a smaller first download
KittenTTS Nano is a compact English option for devices or connections where a larger model is inconvenient. Its 57 MB browser bundle runs on the CPU through WebAssembly and includes eight US English voices.
Choose KittenTTS when size matters most
Use KittenTTS for short English clips, quick drafts, or older devices where you want to avoid a larger initial model download. Its delivery is less expressive than Kokoro, so test the real script before choosing it for long narration.
Check whether the smaller model is enough for the job
- 1Generate the opening paragraph or complete short clip with the voice you prefer.
- 2Listen closely to sentence rhythm, proper names, and any line that needs emotional emphasis.
- 3Use the downloaded WAV if the result fits, or switch to Kokoro when the script needs more expressive English narration.
Specifications
| Developer | KittenML |
|---|---|
| Parameters | 15 million |
| Download size | 57 MB (fp32) |
| Output | 24.0 kHz mono |
| Browser voices | 8 |
| Languages | English (US) |
| Voice cloning | No |
| Streaming | No |
| License | Apache-2.0 |
| Speed | Runs faster than real time on many CPU-only devices with a 57 MB download. |
| Runtime | WebAssembly (CPU) |
Specifications checked 2026-07-21 against:
Explore related downloads
The browser studio and downloadable catalog are separate. Use the catalog to find independently published model files and check each source before downloading.
Good fit when
- +57 MB model download
- +No GPU required
- +Eight included English voices
Before you choose it
- −English only
- −Less expressive pacing than the larger models
Voices (8)
See it alongside another model
Questions about KittenTTS Nano
Does AIVoices charge to use KittenTTS Nano?
AIVoices does not charge generation credits for this browser model. The listed model license is Apache-2.0. Check the upstream model and voice terms before use.
What hardware does KittenTTS Nano need?
A current desktop browser and CPU are enough for this model. The 57 MB model is stored in your browser after the first download.
Is my text private when using KittenTTS Nano here?
The supported model executes inside your browser tab. AIVoices does not send the text to a server for speech generation.
Can I use KittenTTS Nano output commercially?
Commercial use depends on the model, selected voice, and source-data terms. This page lists Apache-2.0 for the model, but you should still review the current upstream terms.