Skip to content
SPECIFICTION
Get listed

MARS5-TTS

github.com

Free plan LinuxAPISelf-hosted
Visit github.com
Spec score 8.0 #112 of 223 in Text-to-Speech Software

Spec sheet

Purpose
MARS5 is CAMB.AI’s English text-to-speech speech model.Read 12 Oct 2026 · github.com
Platforms
api,self_hostedRead 20 Sep 2026 · github.com
Deployment
The project documents loading through torch.hub or Hugging Face and provides a Docker image and Dockerfile build instructions.Read 12 Oct 2026 · github.com
Support
The repository invites questions and feedback through the CAMB.AI forum and Discord, and lists [email protected] for API credit inquiries.Read 12 Oct 2026 · github.com
License
The English model is open-sourced under GNU AGPL 3.0, and the README says to email CAMB.AI about commercial inquiries or licensing the closed-source version.Read 12 Oct 2026 · github.com
API access
The README directs users without the required hardware to use the CAMB.AI API and says they can contact [email protected] about extra test credits.Read 12 Oct 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Hardware limit
Local inference requires GPU capacity to store at least 750M plus 450M parameters and run inference with 750M active parameters.Read 12 Oct 2026 · github.com
Inference modes
MARS5 supports shallow cloning without a reference transcript and deep cloning with one, which typically provides higher quality at the cost of slower inference.Read 12 Oct 2026 · github.com
Known limitations
The project lists inference stability, speed, long-reference selection, and long-form generation among areas needing improvement or contribution.Read 12 Oct 2026 · github.com
Local requirements
The quickstart lists Python 3.10 or later and Torch 2.0 or later, plus Torchaudio, Librosa, Vocos, Encodec, safetensors, and regex.Read 12 Oct 2026 · github.com
Prosody controls
Punctuation and capitalization in the text can guide pauses and emphasis in generated speech.Read 12 Oct 2026 · github.com
Reference audio
The README recommends clean reference audio between 1 and 12 seconds and says around 6 seconds gives optimal results.Read 12 Oct 2026 · github.com
Speech generation
The model can generate speech from text using a short audio reference, including prosodically challenging scenarios such as sports commentary and anime.Read 12 Oct 2026 · github.com
Technical design
MARS5 uses a two-stage autoregressive and non-autoregressive pipeline, with a multinomial diffusion component refining speech codes.Read 12 Oct 2026 · github.com
Voice cloning
Speaker identity is specified with an audio reference, and supplying its transcript enables a slower deep-clone mode intended to improve cloning quality.Read 12 Oct 2026 · github.com

Plans and prices

MARS5-TTS Free English speech model; AGPL-3.0; commercial licensing inquiries by email Read 12 Oct 2026 · github.com

Every MARS5-TTS plan and price →

Where Specifiction places it

Alternatives to MARS5-TTSAll alternatives →