Meta returns to open source AI with Omnilingual ASR models that can transcribe 1,600+ languages natively

Meta has just released a new multilingual automatic speech recognition (ASR) system supporting 1,600+ languages — dwarfing ...
Slator

AppTek Pioneers Next-Generation Expressive Text-to-Speech for AI Dubbing

AppTek’s sophisticated multilingual TTS model ensures that prosodic patterns are accurately generated, resulting in human-like emotional speech range with granular control over every voice parameter.

Meta Expands AI Speech Recognition to 1,600+ Languages

Omnilingual Automatic Speech Recognition can transcribe speech in over 1,600 languages — including 500 low-resource languages ...
News9Live on MSN

ElevenLabs launches Scribe v2 realtime: Ultra-fast multilingual speech-to-text model

ElevenLabs has launched Scribe v2 Realtime, a cutting-edge Speech-to-Text model that delivers human-quality transcription in ...
Slator

memoQ and Voiseed Announce Integration to Enhance Text-to-Voice Workflows

Q  and Revoiceit by Voiseed are now fully integrated, connecting professional translation with AI voice production in a seamless workflow.
Advanced Television

CAMB.AI, Broadcom bring voice AI to the chip

CAMB.AI, the advanced AI Localisation platform startup, and Broadcom, a specialist in semiconductor and infrastructure software solutions, are collaborating in ...
eLife

Progressive postnatal hearing development limits early parent-offspring vocal communication in the zebra finch

Zebra finches are a prominent model system for vocal learning and auditory system function, yet little is known about the functional development of the auditory system. Here, the authors convincingly ...