# fixie-ai/ultravox

A fast multimodal LLM for real-time voice

Repository: https://github.com/fixie-ai/ultravox
Canonical: https://ross.abutalabs.com/products/ultravox
Homepage: https://ultravox.ai
Language: Python
License: MIT
License Family: permissive
Topics: ai, llm, slm, speech
Last push: 2025-12-12T18:09:40+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 56, release rhythm 19, longevity 59
- inputs: {"age_days": 826, "days_push": 264, "days_rel": 380, "gap_med": 139.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4555, forks 386 (observed 2026-08-28T04:08:53.348966+00:00)

## What it is
Ultravox is a fast multimodal LLM that understands human speech directly without a separate ASR stage, by projecting audio into the LLM's embedding space. It extends open-weight models like Llama 3, Mistral, and Gemma for real-time voice interactions and streaming text output.

## Use cases
- build real-time voice AI agents
- transcribe and understand speech without ASR
- run a speech-native LLM for low-latency voice conversations
- fine-tune a multimodal audio LLM on open-weight models
- stream text from live audio input
- build voice-to-voice chatbots

## When to choose
- you need low-latency voice AI without the ASR-to-LLM pipeline overhead
- you want to preserve paralinguistic cues like tone and timing in speech understanding
- you want to self-host or fine-tune a speech-capable LLM on your own models
- you're building real-time conversational voice agents

## When to avoid
- you only need traditional batch speech-to-text transcription
- you have no GPU resources for inference
- you need a fully managed hosted solution without running your own infrastructure
- your use case is text-only LLM work

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, speech-recognition, machine-learning, llm-training
- domain: large-language-models, speech-processing, artificial-intelligence
- platform: python, cloud
- tags: multimodal-llm, voice-ai, speech-native, audio-understanding, real-time-voice, asr-free, llama, mistral, voice-agents, ai-agents, gpu, docker

## Member repositories
- fixie-ai/ultravox (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.348966+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:02.807915+00:00, confidence not recorded.
  - readme: https://github.com/fixie-ai/ultravox (fetched 2026-08-28T04:08:53.348966+00:00, sha 10ba050bc50f)
  - homepage: https://ultravox.ai (fetched 2026-08-29T09:05:43.173520+00:00, sha 3a35da67ed51)
  - site_page: https://www.ultravox.ai/about (fetched 2026-08-29T09:05:43.178141+00:00, sha 3b1317102dca)
  - site_page: https://www.ultravox.ai/pricing (fetched 2026-08-29T09:05:43.176439+00:00, sha efa100c67822)
- Data as of 2026-08-30T08:39:29.467469+00:00.