Muse Voice Transcribe — Model Drop — Dropday.ai

Model Drops Leaderboard

Sign in

← All model drops

Live drop

Muse Voice Transcribe

MetaDropped Sep 1, 20262 builds2 makers1 prompt

Single real-time model for streaming ASR, diarization of 20+ speakers, and endpointing.

Browse in feed Submit a build

The most interesting things people are building with AI, all in one place — followed and tracked as they evolve from first demo to real product.

1379 indexedPress / to search--:--:-- UTC

Dropday is new — we're looking for genuine feedback.

Home Leaderboard Top creators What is this?Privacy Terms

DROPDAY.ai

Oh-My-Hermes

Veeza AI

About this release

What is Muse Voice Transcribe?

Muse Voice Transcribe is Meta Superintelligence Labs’ first real-time audio perception model. It performs streaming speech-to-text, speaker diarization for more than 20 speakers, and endpointing natively in one autoregressive pass with no separate post-processing. Trained on 70+ languages (25 validated at launch) and already powering dictation in Meta AI for Mac and Muse Code.

Read the official Meta launch page

Worth opening first

Standouts

Open sourcePrompt

Oh-My-Hermes

A professional operating layer and plugin system for Hermes Agent.

Veeza AI

AI travel agent for tourist visa assistance for the Global South

Playable1 Prompts1

Playable

1

Veeza AI

AI travel agent for tourist visa assistance for the Global South

Apps

Prompts

1

Open sourcePrompt

Oh-My-Hermes

A professional operating layer and plugin system for Hermes Agent.

Apps

Built something with Muse Voice Transcribe?

Paste the URL and Dropday.ai will credit you, track the build as it evolves, and put it on this drop.