fixie-ai
ultravox-v0_4
A multimodal speech-language model combining Llama 3.1-8B and Whisper for real-time voice understanding, speech translation, and voice agent applications.
Available on FriendliAI
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
fixie-ai
Model Tree
Base
this model
Input Modalities
TextAudio
Output Modalities
Text
Supported Functionality
Dedicated Endpoints