Kyutai, an open science research lab, made headlines over the summer when they released their real-time speech-to-speech AI assistant (beating OpenAI to market with their teased GPT-driven speech-to-speech functionality). Alex from Kyutai joins us in this episode to discuss the research lab, their recent Moshi models, and what might be coming next from the lab. Along the way we discuss small models and the AI ecosystem in France. :link: https://practicalai.fm/298
Ch | Start | Title | Runs |
---|---|---|---|
01 | 00:00 | Welcome to Practical AI | 00:34 |
02 | 00:35 | Sponsor: Fly | 02:29 |
03 | 03:16 | What is Kyutai? | 02:43 |
04 | 05:59 | French AI ecosystem | 02:42 |
05 | 08:41 | Formin a non-profit | 01:50 |
06 | 10:31 | Connecting to open science | 01:57 |
07 | 12:28 | What makes Kyutai stand out? | 03:46 |
08 | 16:26 | Sponsor: Timescale | 02:21 |
09 | 19:04 | Moshi's capabilities | 03:54 |
10 | 22:58 | History of speech-to-speech models | 07:55 |
11 | 30:53 | Cool things to try | 03:12 |
12 | 34:13 | Sponsor: WorkOS | 02:51 |
13 | 37:13 | Fine tuning data sets | 05:16 |
14 | 42:28 | Model sizes | 02:42 |
15 | 45:10 | Things to come | 03:23 |
16 | 48:34 | Thanks for joining us! | 00:35 |
17 | 49:16 | Outro | 00:46 |
Last updated: Dec 12 2024 at 16:20 UTC