Fish Audio S2
Real Expressive AI Voices
Omnilingual ASR
Advancing automatic speech recognition for 1,600+ languages
Meta's Omnilingual ASR is an open-source (Apache 2.0) speech recognition model supporting 1,600+ languages. It uses an LLM-based architecture that can be extended to new languages with just a few in-context examples, without retraining.
Omnilingual ASR first appeared on November 11, 2025, 7 months ago. Its focus lies in the Open Source, Artificial Intelligence (AI), and Audio sectors. The startup has built up 137 votes and 2 comments, marking it as an up-and-coming startup.
Browse all startups in Open Source, Artificial Intelligence (AI), Audio.
Similar startups
Other startups building in the same space
Wispr Flow
Speak naturally, write perfectly & 3x faster in every app
Coval
Simulation & evals to ship delightful voice & chat AI agents
Wondercraft
Canva for audio
Voicenotes Pages
What if publishing felt like talking to a friend?
AssemblyAI - Speech-to-Text API
APIs to automatically transcribe and understand audio
Design Studio by Tiledesk
Unlock AI magic for elevated customer engagement, fast
BlogBowl
Keyword‑driven AI articles auto‑posted to your blog
Probo
Compliance for Startups to get SOC2/ISO27001/HIPAA in a week
...
Discussion 0