landscape
Search⌘KSubmit a productSign in

Map / Core AI / Multimodal & Perception / Kyutai STT

Kyutai STT

by Kyutai

Streaming speech-to-text models for real-time transcription

CuratedSpeech Recognition

I use this adds Kyutai STT to your stack and finds people with similar stacks. Every mark feeds the counts on Pulse. Sign in to mark it.

No ratings yet

Who uses it

0 use this
0use it now
0tried it, dropped it
0want to try

Nobody has marked it yet. Press I use this, Tried it or Want to try to be the first.

Ratings

Only from people who use it or tried it
No ratings yet

The first rating comes from someone who uses Kyutai STT or tried it.

Use Kyutai STT?

Sign in, mark it as I use this or Tried it, then rate it.

Sign in to rate

What it does

Kyutai STT is a pair of streaming speech-to-text models from Kyutai that transcribe audio while it arrives: a 1B English and French model with a built-in semantic voice activity detector, and a 2.6B English model tuned for accuracy. Code is in the Apache 2.0 delayed-streams-modeling repo and weights are CC-BY 4.0, with PyTorch, MLX and Rust builds.

Alternatives on the map

All 30 alternatives

Multimodal & Perception, starting with the other Speech Recognition.

Compare with

People who use it also use

Not enough marks yet to tell. When people who use Kyutai STT mark the rest of their stack, it shows up here.

Open website