fixie-ai / ultravox
A fast multimodal LLM for real-time voice
Why this job: matched by what the repo talks about: voice, time, real, fast
What it does
Ultravox currently takes in audio and emits streaming text. As we evolve the model, we'll train it to be able to emit a stream of speech tokens that can then be converted directly into raw audio by an appropriate unit vocoder.
Get started
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
brew update
brew install just - Maintenance
- Inactive
- Last commit 11 months ago
- Stars
- 4,588
- +5 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.6
- Released 15 months ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 48% closed
- 53 still open
- Pull requests
- 96 merged
- 9 waiting
- Releases
- 5
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| babysor / MockingBird | 36,871 | 8 months ago | Custom | No downloads |
| huggingface / speech-to-speech | 13,680 | yesterday | Apache-2.0 | No downloads |
| DigitalPhonetics / IMS-Toucan | 2,212 | 9 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Just <1%
- Shell <1%
- Dockerfile <1%
Topics
- ai
- llm
- slm
- speech
Project record
- JobSpeech and audio
- StatusListed
- Commits128
- Forks387
- Watching55
- Stars in 28 days+16
- CreatedMay 29, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026