UPDATES

2024-09-17 NEW
We've released a detailed technical report and code for our core contributions. We thank you for your interest and support.

---

2024-04-17
We've released a demo of 500ms low-latency voice chat.

---

2024-04-03
We enjoyed the cherry blossoms in NYC.

---

2024-03-19
We've released a stronger joint speech-language model and live demo. Read our technical report or get the weights on Hugging Face.

---

2024-03-06
We've released a research preview of our joint speech-language model.

---

2024-02-16
We've validated our joint speech-language modeling approach. Read more in our report.

OPEN SOURCE

Gazelle | HuggingFace | Github
Gazelle is an audio-native speech-language model.

Gondola | Github
Gondola is our real-time orchestrator for voice conversation with an LLM.

Taolun | Github
Taolun is our React library for building real-time speech applications.

Pause ASR | HuggingFace
Pause ASR is our turn-taking and pause prediction model.