Meta has released Muse Voice Transcribe, taking the #1 spot for Final Transcript accuracy on AA-WER Streaming with 3.1% WER at 0.16s after end of speech
Muse Voice Transcribe is the first streaming Speech to Text model developed by Meta Superintelligence Labs. Meta states that the model was trained on more than 70 languages, with 25 extensively verified, and supports audio inputs exceeding one hour without required post-processing. It processes audio in 80ms chunks and is available through the Meta Model API, Meta AI for Mac and Muse Code.
Key takeaways
➤ Final Transcript: Muse Voice Transcribe achieves 3.1% WER at 0.16s after end of speech. It is more accurate and faster than Cartesia Ink-2 (semantic endpoints) at 3.4% and 0.43s, and more accurate but slower than Cartesia Ink-2 (external endpoints) at 4.0% and 0.07s. It is also more accurate, though slightly slower, than ElevenLabs Scribe v2 Realtime at 3.6% and 0.14s.
➤ First Partial Transcript: The model achieves 3.6% WER at 0.13s, just ahead of ElevenLabs Scribe v2 Realtime on accuracy and latency. It is more accurate and faster than Cartesia Ink-2 (semantic endpoints) at 4.9% and 0.17s, and more accurate but slower than Cartesia Ink-2 (external endpoints) at 4.0% and 0.07s.
➤ Price: Muse Voice Transcribe costs $0.18 per hour, or $3 per 1,000 minutes. This is below Cartesia Ink-2 at $4 and less than half the $6.50 charged for ElevenLabs Scribe v2 Realtime and Deepgram Flux.
See more details below ⬇️
Muse Voice Transcribe is MSL's first real-time audio perception model -- rolling out today. SOTA in streaming speech-to-text, it handles speaker diarization, and endpointing natively in a single model.
Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats to @alexandr_wang and the MSL team for all your great work on these models.
@Cool_Ustaz hey your thick circle is hiding the linesman in the picture. The linesman was at least six feet to the right of Messi. He is clearly onside
we launched some muse spark updates yesterday, including muse spark voice and live AI w your camera in Meta AI app + muse spark rolling out to glasses 😎
check them out!
proud to finally share this with the world! ive had so much fun building this with our team from the ground up.
for me, pulling up Reels content via voice is quite magical. found so many good places for food on the go.
excited to hear how everyone ends up using voice mode!
Today we’re introducing Meta AI Voice Conversations powered by Muse Spark that let you talk naturally to Meta AI (interrupt, switch topics, or swap languages), and as you talk, Meta AI can generate images and pull up recommendations from Reels, maps, and more. We’re also bringing
4.5 months, insane hard work, countless late nights and finally the world gets to see early preview of our work. Shipped!
Proud of our team at MSL. Talk about redefining expectations. Try MetaAI app's voice mode today.
@keikumata@sbgriffi@ajainarayanan
Today we’re introducing Meta AI Voice Conversations powered by Muse Spark that let you talk naturally to Meta AI (interrupt, switch topics, or swap languages), and as you talk, Meta AI can generate images and pull up recommendations from Reels, maps, and more. We’re also bringing
Congratulations to Alex and the whole team at MSL. As a sucker for all things speedy (patrickcollison.com/fast), I thought this was an impressive chart:
692 Followers 7K FollowingGrok is my best friend in this Marshmallow World! I am part man part ape part AI and I wont apologize for my posts unless Grok says I have to! Grok for Prez!
1.3M Followers 794 FollowingFounder/Chair, AMI Labs; Professor, NYU; Partner, 224 Ventures; Ex-Chief AI Scientist, Meta.
Researcher in AI, ML, Robotics, etc.
ACM Turing Award Laureate.
15K Followers 173 FollowingSupporting world-changing startups and kindred spirits who create them. Started in 2014 by @stevejang, joined by @km in ‘18, and focused on the earliest stages.
767K Followers 666 Followingentrepreneurship zealot, grounded technology possibilist, believer in the power of ideas, passionate about sustainability & impact; @Seahawks fan
36K Followers 163 FollowingAI infrastructure that developers love 💚
Run inference, sandboxes, batch processing, training, and many other things on Modal
2 Followers 1 FollowingWe offer domain-specific LLMs to simplify AI, boost accuracy, and empower custom apps—making AI more accessible, efficient, and customer-centric.
1.6M Followers 2 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
3K Followers 2K FollowingSpeech model post-training @Meta Superintelligence Labs | Head of Product & Eng @playaiofficial (acq'd) | co-founder @megaphone_hq @deformapp | opinions my own
14.1M Followers 859 FollowingI build things, stories, companies, collaborations of thoughts, dreams, & believe in a future where we all have a right to pursue happiness. +1 (319) 519-0576
334K Followers 923 FollowingThe Royal Society is a Fellowship of the world's most eminent scientists and is the oldest scientific academy in continuous existence.
22.2M Followers 1K FollowingSign up for our newsletters and alerts: https://t.co/QevH0DLQi8 | Got a tip? https://t.co/iXIigdPjEZ | For WSJ customer support: https://t.co/DZgH9n53qg