Ultravox streams spoken prompts into Llama 3.3 without a separate speech recognizer.

The open‑weight model runs on a 70‑billion‑parameter Llama 3.3 backbone, with an 8 billion‑parameter variant on Hugging Face. Training the adapter took 2‑3 hours on eight H100 GPUs for 14 k steps. The system accepts r…

Ultravox replaces the three‑stage pipeline—speech‑to‑text, language model, text‑to‑speech—with a single projector that maps audio into the LLM’s high‑dimensional space. Because the audio encoder and the LLM remain fro…

The model currently outputs streaming text. The roadmap promises a speech‑token stream that a vocoder can turn into raw audio, completing a true voice‑to‑voice loop. By avoiding explicit transcription, Ultravox also p…