-
fixie-ai/ultravox-v0_6-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 16.7k • 8 -
fixie-ai/ultravox-v0_6-gemma-3-27b
Audio-Text-to-Text • 0.7B • Updated • 2.18k • 9 -
fixie-ai/ultravox-v0_6-qwen-3-32b
Audio-Text-to-Text • 0.7B • Updated • 3.31k • 9 -
fixie-ai/ultravox-v0_6-llama-3_1-8b
Audio-Text-to-Text • 0.7B • Updated • 2.57k
AI & ML interests
None defined yet.
Organization Card
Ultravox.ai: We're building AIs that can communicate as naturally as humans
Human communication is messy. We interrupt, talk over each other, and don't always wait our turn. But this rapid, messy exchange of ideas serves as the backbone of human progress.
LLMs are revolutionary, but their potential impact is currently limited to situations where text-based chat is sufficient.
We think useful, productive, and accessible AGI will require models that can operate in the fast-paced, ambiguous world of human voice communication.
This is the problem we're tackling. If that sounds interesting, check out our SLM (Speech Language Model), Ultravox!
-
fixie-ai/ultravox-v0_6-llama-3_3-70b
Audio-Text-to-Text • 0.7B • Updated • 16.7k • 8 -
fixie-ai/ultravox-v0_6-gemma-3-27b
Audio-Text-to-Text • 0.7B • Updated • 2.18k • 9 -
fixie-ai/ultravox-v0_6-qwen-3-32b
Audio-Text-to-Text • 0.7B • Updated • 3.31k • 9 -
fixie-ai/ultravox-v0_6-llama-3_1-8b
Audio-Text-to-Text • 0.7B • Updated • 2.57k
Multimodal model for better turn-taking
models
23

fixie-ai/ultravox-v0_6-qwen-3-32b
Audio-Text-to-Text
•
0.7B
•
Updated
•
3.31k
•
9

fixie-ai/ultravox-v0_6-gemma-3-27b
Audio-Text-to-Text
•
0.7B
•
Updated
•
2.18k
•
9

fixie-ai/ultravox-v0_5-glm-4_5-355b
Audio-Text-to-Text
•
0.7B
•
Updated
•
2.73k
•
1

fixie-ai/ultravox-v0_6-llama-3_3-70b
Audio-Text-to-Text
•
0.7B
•
Updated
•
16.7k
•
8

fixie-ai/ultravox-v0_5-llama-3_3-70b
Audio-Text-to-Text
•
0.7B
•
Updated
•
5.19k
•
32

fixie-ai/ultraVAD
Feature Extraction
•
0.7B
•
Updated
•
614
•
24

fixie-ai/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Text Generation
•
5B
•
Updated
•
23

fixie-ai/ultravox-v0_6-llama-3_1-8b
Audio-Text-to-Text
•
0.7B
•
Updated
•
2.57k

fixie-ai/turntaking-multilingual-llama8b-2a
Feature Extraction
•
0.7B
•
Updated
•
350
•
1

fixie-ai/turntaking-pretraining-it-multilingual-3c
8B
•
Updated
•
1.88k
datasets
37
fixie-ai/orpheus_endfiller_1_audiotoken
Viewer
•
Updated
•
1.9k
•
190
•
1
fixie-ai/orpheus_midfiller_1_audiotoken
Viewer
•
Updated
•
1.86k
•
146
fixie-ai/orpheus_grammar_1_audiotoken
Viewer
•
Updated
•
1.92k
•
169
fixie-ai/turntaking-contextual-tts
Viewer
•
Updated
•
400
•
383
•
3
fixie-ai/rime_2
Viewer
•
Updated
•
4.03k
•
107
fixie-ai/orpheus_endfiller_1
Viewer
•
Updated
•
1.9k
•
111
fixie-ai/orpheus_midfiller_1
Viewer
•
Updated
•
1.86k
•
112
fixie-ai/human_convcollector_1
Viewer
•
Updated
•
722
•
98
fixie-ai/orpheus_grammar_1
Viewer
•
Updated
•
1.92k
•
111
fixie-ai/chirp3_1
Viewer
•
Updated
•
163k
•
434