
multimodal LLMfamily
Ultravox
Speech language models that join a Whisper encoder to an open LLM such as Llama through a trained adapter, so the model takes speech and text input directly.
Levelfamily
Classmultimodal LLM
Parametersnot in the notes
Contextnot in the notes
Released5 Feb 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Lineage
Ultravox v0.5 Llama 3.2 1B belongs to this familymultimodal LLM6 Feb 2025683.12M
Ultravox v0.5 Llama 3.1 8B belongs to this familymultimodal LLM5 Feb 2025687.31MWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text, audio
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- Thai, Vietnamese
- Jakarta hosting
- unknown
- Languages
- Checkpoint model cards list 42 languages
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Industry Use Cases
No industry use case links this model.
Links
Developer
Fixie.aistartup
Fixie.aistartupModel
UltravoxFixie.ai, multimodal LLM
UltravoxFixie.ai, multimodal LLMUse Casesnone recorded
Who Runs Itnone recorded
Models 2
Organisations 1
Sources
- github.com/fixie-ai/ultravox https://github.com/fixie-ai/ultravox
- huggingface.co/api/models?pipeline_tag=audio-text-to-text&so... https://huggingface.co/api/models?pipeline_tag=audio-text-to-text&sort=downloads&limit=50
- huggingface.co/fixie-ai/ultravox-v0_5-llama-3_2-1b https://huggingface.co/fixie-ai/ultravox-v0_5-llama-3_2-1b
- huggingface.co/fixie-ai/ultravox-v0_5-llama-3_1-8b https://huggingface.co/fixie-ai/ultravox-v0_5-llama-3_1-8b
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Ultravox", https://aurion.semai.id/models/fixie-ai-ultravox/, records of October 2026.