Skip to content
SPECIFICTION
Get listed

VoiceCraft

github.com

WebWindowsLinuxSelf-hosted
Visit github.com
Spec score 7.4 #185 of 233 in Text-to-speech tools

Spec sheet

Purpose
VoiceCraft is a token-infilling neural codec language model for zero-shot speech editing and text-to-speech on in-the-wild data such as audiobooks, internet videos, and podcasts.Read 10 Oct 2026 · github.com
Intended users
The repository documents inference use as well as model training and fine-tuning for developers preparing their own datasets.Read 10 Oct 2026 · github.com
Integrations
The repository provides scripts for integrating VoiceCraft into other projects and documents demos on Hugging Face Spaces and Replicate.Read 10 Oct 2026 · github.com
License
The repository states that the code is under CC BY-NC-SA 4.0 and the model weights are under the Coqui Public Model License 1.0.0.Read 10 Oct 2026 · github.com
API access
NoRead 20 Sep 2026 · github.com
Code license
The codebase is licensed under CC BY-NC-SA 4.0, with some identified components under separate licenses.Read 9 Oct 2026 · github.com
Commercial use
NoRead 20 Sep 2026 · github.com
Compute requirement
The Docker instructions assume Docker with NVIDIA Container Toolkit and pass GPUs into the container.Read 10 Oct 2026 · github.com
Consent guidance
The project says people must not use the technology to generate or edit someone's speech without that person's consent.Read 9 Oct 2026 · github.com
Dataset access
The training instructions say downloading GigaSpeech requires signing an agreement and using an authentication token.Read 10 Oct 2026 · github.com
Editing and TTS
The Gradio interface offers zero-shot TTS, speech editing, and long-text TTS modes.Read 10 Oct 2026 · github.com
Hardware requirements
The Docker instructions assume Docker and NVIDIA container support, and the examples check GPU visibility with nvidia-smi.Read 9 Oct 2026 · github.com
Model length limit
For the giga330M TTS model described in its news section, the repository says maximum prompt plus generation length should be 16 seconds.Read 10 Oct 2026 · github.com
Model license
The model weights use Coqui Public Model License 1.0.0, which permits only non-commercial use of the model and its outputs.Read 9 Oct 2026 · github.com
Model limits
The README says the enhanced TTS models were trained with utterances no longer than 16 seconds and recommends keeping prompt plus generation length at or below 16 seconds for those models.Read 9 Oct 2026 · github.com
Training
Training requires utterances and transcripts, encoded audio codes, phoneme sequences, and a manifest; the project includes preparation guidance.Read 10 Oct 2026 · github.com
Transcript control
Its smart transcript feature lets users write only the text they want to generate.Read 10 Oct 2026 · github.com
Voice cloning
To clone or edit an unseen voice, VoiceCraft needs only a few seconds of reference audio.Read 9 Oct 2026 · github.com
Voice consent
The project disclaimer prohibits generating or editing someone’s speech without their consent.Read 10 Oct 2026 · github.com
Voice reference
The project says cloning or editing an unseen voice requires only a few seconds of reference audio.Read 10 Oct 2026 · github.com
Ways to run
The project documents inference through Google Colab, Docker, local setup, and standalone command-line scripts.Read 10 Oct 2026 · github.com
Windows and Linux
The Docker quick start says it was tested on Linux and Windows and should work on hosts with Docker installed.Read 10 Oct 2026 · github.com

Where Specifiction places it

Alternatives to VoiceCraftAll alternatives →