FreeAIRepo
Voice & audio

herimor/voxtream

VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control

Commercial OK · Apache-2.02.2 GB VRAMRuns on MacPython
Open on GitHub Website
Stars
256
Forks
36
Open issues
8
Last push
11d ago

About voxtream

voxtream is a free, open-source AI voice and audio tool by herimor, written mainly in Python. VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency and Speaking rate Control. It has 256 GitHub stars and 36 forks, and was last updated 11d ago. It's released under the Apache-2.0 license, a standard open-source license. According to the project, it needs a GPU with at least 2.2 GB of memory and works on macOS.

License
Apache-2.0
Commercial use
Commercial OK
Language
Python
Stars
256
Last update
11d ago
Runs on Mac
Yes (as stated by the project)
GPU
2.2 GB+ (as stated by the project)
Paid API key
Not stated
Self-hostable
Yes

Similar free tools

All Voice & audio tools →

voxtream FAQ

Can I use voxtream commercially?

Yes. Apache-2.0 is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.

Is voxtream free?

Yes. voxtream is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does voxtream run on a Mac?

Yes. According to the project, voxtream works on macOS.

Does voxtream need a GPU?

According to the project, voxtream needs a GPU with at least 2.2 GB of memory.

Is voxtream still maintained?

Yes. It was last updated 11d ago and has 8 open issues on GitHub.

What are alternatives to voxtream?

Similar free, open-source tools include Real-Time-Voice-Cloning, voicebox, VoiceStudio, VoxCPM.

Related topics

streamingtext-to-speechttsvoice-cloningspeech-synthesisvoicevoxtream