Hackernews posts about Kyutai

  1. Mira – New OSS World Model from Kyutai (mira-wm.com)
    1 points by pain_perdu about 10 hours ago | discuss
  2. Post-training speech models for better interactivity (kyutai.org)
    2 points by pr337h4m 26 days ago | discuss
  3. Kyutai 1.6B Streaming TTS (huggingface.co)
    21 points by robotswantdata about 1 year ago | discuss
  4. Kyutai STT – A speech-to-text optimized for real-time usage (kyutai.org)
    6 points by ajuhasz about 1 year ago | discuss
  5. Delayed Streams Modeling: Kyutai STT and TTS (github.com)
    3 points by jasonjmcghee 12 months ago | discuss
  6. Kyutai unveils Invincible Voice: AI in the service of human connection (www.iliad.fr)
    2 points by JeanKage 5 months ago | discuss
  7. Kyutai Introduces Moshi: Revolutionizing Conversational AI (medium.com)
    2 points by ringer007 almost 2 years ago | discuss
  8. iOS Port of Pocket TTS from Kyutai Labs (github.com)
    1 points by unamentis 5 months ago | discuss
  9. Moshi AI: New Chatbot with Real-Time Voice Assistant by Kyutai (moshiai.org)
    1 points by ringer007 almost 2 years ago | discuss
  10. Show HN: Audio AI had a wild day – 5 major open-source / real-time TTS drops (github.com)
    5 points by pratik227 5 months ago | 2 comments
  11. Show HN: Dia2, open-weights TTS model for realtime speech to speech (github.com)
    3 points by toebee 8 months ago | 2 comments
  12. Show HN: I hated an audiobook narrator, so I built a voice cloning ePub reader (github.com)
    1 points by jarodise 5 months ago | discuss
  13. Pocket TTS: A high quality TTS that gives your CPU a voice (kyutai.org)
    635 points by pain_perdu 6 months ago | 158 comments
  14. Neural audio codecs: how to get audio into LLMs (kyutai.org)
    428 points by karimf 9 months ago | 119 comments
  15. Moshi: A speech-text foundation model for real time dialogue (github.com)
    365 points by gkucsko almost 2 years ago | 64 comments
  16. Audio is the one area small labs are winning (www.amplifypartners.com)
    319 points by rocauc 5 months ago | 96 comments
  17. Hibiki: High-Fidelity Simultaneous Speech-to-Speech Translation (github.com)
    5 points by Philpax over 1 year ago | 1 comments
  18. Unmute: Speak with a text LLM in real time (github.com)
    3 points by cranium about 1 year ago | 1 comments
  19. Unmute: Make LLMs Listen and Speak (kyutai.org)
    3 points by ilnmtlbnm about 1 year ago | 1 comments
  20. CASA: Cross-Attention via Self-Attention (kyutai.org)
    2 points by swyx 7 months ago | discuss
  21. MoshiVis – an Open-Source Vision Speech Model (VSM) (kyutai.org)
    2 points by falcor84 over 1 year ago | discuss
  22. Ovie – One view is enough (github.com)
    1 points by Sebastian_09 2 months ago | discuss
  23. Hibiki-Zero:real-time and multilingual speech translation model (kyutai.org)
    1 points by pain_perdu 5 months ago | discuss