Artwork

Full-duplex, real-time dialogue with Kyutai

Practical AI

1,535 subscribers

published

Play Playing
iconShare
 
MP3•Episode home
Manage episode 453647338 series 2385063
Content provided by Changelog Media and Practical AI LLC. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Changelog Media and Practical AI LLC or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://staging.podcastplayer.com/legal.

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.

Join the discussion

Changelog++ members save 10 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

  • Fly.io – The home of Changelog.com — Deploy your apps close to your users — global Anycast load-balancing, zero-configuration private networking, hardware isolation, and instant WireGuard VPN connections. Push-button deployments that scale to thousands of instances. Check out the speedrun to get started in minutes.
  • Timescale – Purpose-built performance for AI Build RAG, search, and AI agents on the cloud and with PostgreSQL and purpose-built extensions for AI: pgvector, pgvectorscale, and pgai.
  • WorkOS – AuthKit offers 1,000,000 monthly active users (MAU) free — The world’s best login box, powered by WorkOS + Radix. Learn more and get started at WorkOS.com and AuthKit.com

Featuring:

Show Notes:

Something missing or broken? PRs welcome!

…   continue reading

Chapters

1. Welcome to Practical AI (00:00:00)

2. Sponsor: Fly (00:00:35)

https://fly.io/

3. What is Kyutai? (00:03:16)

4. French AI ecosystem (00:05:59)

5. Formin a non-profit (00:08:41)

6. Connecting to open science (00:10:31)

7. What makes Kyutai stand out? (00:12:28)

8. Sponsor: Timescale (00:16:26)

https://www.timescale.com

9. Moshi's capabilities (00:19:04)

10. History of speech-to-speech models (00:22:58)

11. Cool things to try (00:30:53)

12. Sponsor: WorkOS (00:34:13)

https://workos.com

13. Fine tuning data sets (00:37:13)

14. Model sizes (00:42:28)

15. Things to come (00:45:10)

16. Thanks for joining us! (00:48:34)

17. Outro (00:49:16)

323 episodes

#Artificial Intelligence #Changelog #Machine Learning #Deep Learning #Neural Networks #Computer Vision #Changelog Media #Tech