About Dia
Dia is an open-weight text-to-speech model from Nari Labs that writes out a whole conversation from one transcript. You tag lines with [S1] and [S2] for the two speakers and can add nonverbal tags such as laughs, coughs and sighs. The original model has 1.6B parameters and needs about 4.4 GB of VRAM in half precision on an NVIDIA GPU. A 5-10 second audio prompt lets you steer the voice. Dia2 (1B and 2B, released November 2025) adds streaming, so it can start speaking before the full text arrives. English only. Apache-2.0.
Key Features
💰 Pricing
Free open weights (Apache-2.0).
Frequently Asked Questions
Is Dia free?
What is Dia used for?
What platforms does Dia work on?
What are the best alternatives to Dia?
Reviews
Loading reviews...
Questions & Answers
Questions submitted will appear here soon
Join the community to share knowledge about Dia
📊 Comparison vs Alternatives
| Feature | ||||
|---|---|---|---|---|
| Pricing | Free | Free | Freemium | Paid |
| Rating | — | ⭐ 4.4 | ⭐ 4.5 | ⭐ 5.0 |
| Free Tier | ✅ | ✅ | ✅ | ❌ |
| Popularity | 45% | 82% | 80% | 80% |
Are you the creator of Dia?
Claim this listing to get a verified badge, edit tool details, and respond to reviews. You’ll sign in and confirm a work email so we can verify ownership.
Claim this listingQuick Stats
Categories
Dia Alternatives
The Weekly AI Tools & Skills Digest
Launching soon: trending agent skills, new tools, and what's actually worth trying. Sign up to get the first issue.
Free forever. Unsubscribe anytime.