GoKawiilMeta launches Muse Voice Transcribe, a real-time multilingual speech-to-text model
Meta unveiled Muse Voice Transcribe, its first real-time audio perception model, capable of transcribing over 20 speakers simultaneously while switching between more than 20 validated languages, including mid-sentence code-switching. CEO Mark Zuckerberg demoed the tool on X, noting it uses adaptive delay to balance speed and accuracy. The model is now available through Meta's Mac AI app, Muse Code, and its Model API at $3 per 1,000 audio minutes.
GoKawiil's interpretation of the reporting above, not reported fact.
This release positions Meta directly against Google, which launched a similar transcription model, Gemini 3.5 Transcribe, just days earlier, signaling an intensifying race among tech giants to dominate real-time speech AI. Unlike Google, which is embedding its model into Android and Chrome, Meta's integration plans remain unclear, raising questions about how it will compete for mainstream adoption beyond developer and Mac app use cases.
- Muse Voice Transcribe handles 20+ speakers and mid-sentence language switching in real time.
- It launches just days after Google's rival Gemini 3.5 Transcribe model.
- Meta hasn't confirmed plans to integrate it into major consumer products, unlike Google's Android/Chrome rollout.
Anker PowerConf S3 Bluetooth Speakerphone — If you want to put multi-speaker transcription to the test, you need a mic that can actually hear everyone at the table. The Anker PowerConf S3 uses a 360-degree six-mic array built for group calls, making it a natural companion for real-time speech-to-text tools like Meta's Muse Voice Transcribe. It connects over Bluetooth or USB-C, so it works with laptops and phones alike.
See Anker PowerConf S3 Bluetooth Speakerphone on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: engadget.com — Karissa Bell, 2026-09-01
Published there as: “Meta's new AI transcription model can distinguish between multiple speakers and languages in real-time”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.