Meta's Omnilingual ASR Brings Speech Recognition to 1,600 Languages

Meta's open-source speech system covering 1,600+ languages, including 500 never before transcribed by AI, lands on TIME's Best Inventions list.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-15 22:32 · AlphaSignal
Meta's Omnilingual ASR Brings Speech Recognition to 1,600 Languages

More stories

Meta and NVIDIA Release Major Open-Weight AI Models — AWS Machine Learning Blog
Meta and Apple Partner to Bring Open-Weight Muse AI Model to Macs — Wall Street Journal Technology
Meta engineers adopt AI-native approach to build new app Forum — Engineering at Meta
Meta Study: Most Small Businesses Use AI for Productivity — Meta Newsroom
Meta launches Muse Wonder and Muse Wonder Full AI models: Features, pricing and availability — Mint AI
Meta, Milan’s Pinacoteca di Brera, and EssilorLuxottica Expand Access to Art Through AI Glasses — Meta Newsroom
Alibaba launches Qwen N1 AI glasses with 50MP cameras and swappable batteries — Mint AI
Meta details scaling of GEM foundation model for ads recommendation — Engineering at Meta

Get the daily brief of stories like this at 6:30 every morning →