whatmodel.sh / tts / Dia 1.6B (0626)
Dia 1.6B (0626)
↗ share
+ contribute
Dia 1.6B (0626) is an open-weights text-to-speech model from Nari Labs, released June 2025. Its published size is 1.61B parameters. Licence: apache-2.0.
Catalogue identity notes
nari-labs/Dia-1.6B-0626 (1,611,160,576 parameters per HF metadata), the June 2025 checkpoint the README and examples load. Distinct from the original nari-labs/Dia-1.6B (April 2025).
$ how it compares
Scored text-to-speech models released closest to Dia 1.6B (0626), out of 148 with a score, then more from Nari Labs.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 3 |  Gemini 2.5 Flash Preview TTS | 72±3 | comparison only | ||
| 5 |  OpenAudio S1 | 71±8 | api $15.00/M chars | ||
| 42 |  ZipVoice | 62±3 | local | ||
| 65 |  ElevenLabs v3 Alpha | 55±9 | comparison only | ||
| 107 | OpenAudio S1 Mini | 41±5 | api price unknown +local | ||
| more from Nari Labs | |||||
| 99 | Dia2 2B | 45±6 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ where to run it
Other ways to run it
version
- Run it as published · needs ~6.75 GB · from github.com/nari-labs (official)
git clone https://github.com/nari-labs/dia.git && cd dia && pip install -e . && python example/simple-cpu.py
Official weights and documentation: huggingface.co/nari-labs ↗
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json