Hackernews posts about Kyutai

RSS feed for Kyutai

01
newKyutai 1.6B Streaming TTShuggingface.co
▲ 21robotswantdata 458d discuss
02
newKyutai STT – A speech-to-text optimized for real-time usagekyutai.org
▲ 6ajuhasz 472d discuss
03
newDelayed Streams Modeling: Kyutai STT and TTSgithub.com
▲ 3jasonjmcghee 452d discuss
04
newMira – New OSS World Model from Kyutaimira-wm.com
▲ 2pain_perdu 91d discuss
05
newKyutai unveils Invincible Voice: AI in the service of human connectionwww.iliad.fr
▲ 2JeanKage 245d discuss
06
newKyutai MuScriptor: Automatic Multi-Instrument Transcriptionkyutai.org
▲ 1Sebastian_09 55d discuss
07
newiOS Port of Pocket TTS from Kyutai Labsgithub.com
▲ 1unamentis 226d discuss
08
newShow HN: Audio AI had a wild day – 5 major open-source / real-time TTS dropsgithub.com
▲ 5pratik227 255d 💬 2
09
newShow HN: Dia2, open-weights TTS model for realtime speech to speechgithub.com
▲ 3toebee 319d 💬 2
10
newShow HN: I hated an audiobook narrator, so I built a voice cloning ePub readergithub.com
▲ 1jarodise 245d discuss
11
newPocket TTS: A high quality TTS that gives your CPU a voicekyutai.org
▲ 635pain_perdu 263d 💬 158
12
newNeural audio codecs: how to get audio into LLMskyutai.org
▲ 428karimf 349d 💬 119
13
newAudio is the one area small labs are winningwww.amplifypartners.com
▲ 319rocauc 234d 💬 96
14
newHibiki: High-Fidelity Simultaneous Speech-to-Speech Translationgithub.com
▲ 5Philpax 605d 💬 1
15
newUnmute: Speak with a text LLM in real timegithub.com
▲ 3cranium 457d 💬 1
16
newUnmute: Make LLMs Listen and Speakkyutai.org
▲ 3ilnmtlbnm 495d 💬 1
17
newPost-training speech models for better interactivitykyutai.org
▲ 2pr337h4m 116d discuss
18
newCASA: Cross-Attention via Self-Attentionkyutai.org
▲ 2swyx 285d discuss
19
newMoshiVis – an Open-Source Vision Speech Model (VSM)kyutai.org
▲ 2falcor84 558d discuss
20
newOvie – One view is enoughgithub.com
▲ 1Sebastian_09 164d discuss
21
newHibiki-Zero:real-time and multilingual speech translation modelkyutai.org
▲ 1pain_perdu 234d discuss