Nari Labs
Open-weight TTS AI for realistic dialogue
San Francisco, CA, USA
Founded 2025
Nari Labs develops open-weight text-to-speech AI models designed to generate ultra-realistic dialogue in a single pass. Its flagship model, Dia, supports customizable speaker tones, emotional inflections, nonverbal cues, and voice cloning from reference audio.
Last Updated: March 13, 2026
Current Valuation
No valuation data available
Funding Summary
No funding data available.
Announcement
April 22, 2025
TechCrunch: Two undergrads built an AI speech model to rival NotebookLM
Key People
Core OSS Projects
A 1.6B parameter text-to-speech model that generates ultra-realistic dialogue in a single pass, supporting voice cloning, emotional tone control, and nonverbal cues.
License: Apache-2.0
Business Information
Category
Text-to-SpeechIndustries
Media & Entertainment
Technologies
Generative AIAI ModelsVoice CloningAudio
Sectors
Developers
Licenses
Apache-2.0
Similar Companies
Socials and Communities
Cossmology Badge
COSS Weekly Newsletter
Stay up to date with the latest news, funding rounds, and announcements from the COSS universe.
Check out COSS Weekly on the web