Loading video...

Video Failed to Load

Go Home

Yesterday we introduced Moshi, the lowest latency conversational AI ever released. Moshi can perform small talk, explain various concepts, engage in roleplay in many emotions and speaking styles. Talk to Moshi here and learn more about the method below 🧵.

110,344 views • 2 years ago •via X (Twitter)

10 Comments

kyutai's profile picture
kyutai2 years ago

Moshi is an audio language model that can listen and speak continuously, with no need for explicitly modelling speaker turns or interruptions. When talking to Moshi, you will notice that the UI displays a transcript of its speech. This does *not* come from an ASR nor is an input to a TTS, but is rather part of the integrated multimodal modelling of Moshi. Here, listen to it whispering about quantum physics.

kyutai's profile picture
kyutai2 years ago

Moshi is not an assistant, but rather a prototype for advancing real-time interaction with machines. It can chit-chat, discuss facts and make recommendations, but a more groundbreaking ability is its expressivity and spontaneity that allow for engaging into fun roleplay.

kyutai's profile picture
kyutai2 years ago

The underlying model of Moshi is incredibly easy to adapt and tweak by finetuning on specific data. For example, make it listen to phone calls from the late 90’s early 00's and you get a magic phone to the past.

kyutai's profile picture
kyutai2 years ago

Developing Moshi required significant contributions to audio codecs, multimodal LLMs, multimodal instruction-tuning and much more. We believe the main impact of the project will be sharing all Moshi’s secrets with the upcoming paper and open-source of the model.

kyutai's profile picture
kyutai2 years ago

For now, you can experiment with Moshi with our online demo. The development of Moshi is more active than ever, and we will rollout frequent updates to address your feedback. This is just the beginning, let's improve it together.

Matt Huntsman's profile picture
Matt Huntsman2 years ago

Except talking to Moshi is like trying to have a conversation with a dementia patient. Sure it talks with low latency, but that’s about the extent of it

Alex Volkov (Thursd/AI)'s profile picture
Alex Volkov (Thursd/AI)2 years ago

This is incredible, we'll be discussing Moshi in our weekly AI space in 10 minutes, welcome to hop on and tell us about it!

Tsoof Bar Or's profile picture
Tsoof Bar Or2 years ago

Incredible work. Technical paper coming soon?

Praveen Kumar's profile picture
Praveen Kumar2 years ago

Although many are criticizing this, this is probably the closest to 4o.

selfhost. (ノಠ益ಠ)ノ's profile picture
selfhost. (ノಠ益ಠ)ノ2 years ago

its just the pressure

Related Videos