VoiceCraft
VoiceCraft is free, open-source software for zero-shot speech editing and text-to-speech on real-world audio such as audiobooks, internet videos, and podcasts.
What VoiceCraft is
VoiceCraft is free, open-source software for zero-shot speech editing and text-to-speech on real-world audio such as audiobooks, internet videos, and podcasts. It uses a token-infilling neural codec language model and can clone or edit an unseen voice from only a few seconds of reference audio. Modes include speech editing, zero-shot TTS, and long-text TTS. Its Gradio interface has a smart transcript feature that lets users write only the words they want generated. The project documents inference through Google Colab, Docker, a local environment, or a standalone command-line script. Gradio can run locally, and the script is intended for integration into other projects. Developers can prepare data and train or fine-tune models. Docker assumes NVIDIA container support. Enhanced TTS models recommend keeping prompt and generated speech within 16 seconds. Code and model licenses permit non-commercial use only, and the project requires consent before editing someone’s speech.
Good
- Free and open source
- Voice cloning from seconds of reference audio
- Speech editing and long-text TTS modes
- Local Gradio and command-line options
- Training and fine-tuning guidance included
Watch out
- Commercial use is not permitted
- No API access
- Enhanced TTS recommends a 16-second limit
- Docker setup assumes NVIDIA container support
Who it suits
VoiceCraft suits developers and researchers who need speech editing, zero-shot TTS, voice cloning, or model training. It is also aimed at users comfortable with Colab, Docker, local setups, or command-line tools.
Verdict
VoiceCraft combines speech editing, zero-shot TTS, and voice cloning with several documented ways to run it. Its non-commercial licensing, consent requirement, and short enhanced-model length guidance matter when planning projects.
The facts
Each one read from VoiceCraft's own pages, with the date it was checked.
What it does
- API access
- Nochecked 20 Sep 2026
- Code license
- The codebase is licensed under CC BY-NC-SA 4.0, with some identified components under separate licenses.checked 9 Oct 2026
- Commercial use
- Nochecked 20 Sep 2026
- Compute requirement
- The Docker instructions assume Docker with NVIDIA Container Toolkit and pass GPUs into the container.checked 10 Oct 2026
- Consent guidance
- The project says people must not use the technology to generate or edit someone's speech without that person's consent.checked 9 Oct 2026
- Dataset access
- The training instructions say downloading GigaSpeech requires signing an agreement and using an authentication token.checked 10 Oct 2026
- Editing and TTS
- The Gradio interface offers zero-shot TTS, speech editing, and long-text TTS modes.checked 10 Oct 2026
- Hardware requirements
- The Docker instructions assume Docker and NVIDIA container support, and the examples check GPU visibility with nvidia-smi.checked 9 Oct 2026
- Integrations
- The repository provides scripts for integrating VoiceCraft into other projects and documents demos on Hugging Face Spaces and Replicate.checked 10 Oct 2026
- Intended users
- The repository documents inference use as well as model training and fine-tuning for developers preparing their own datasets.checked 10 Oct 2026
- 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.checked 10 Oct 2026
- 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.checked 10 Oct 2026
- 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.checked 9 Oct 2026
- 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.checked 9 Oct 2026
- 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.checked 10 Oct 2026
- Training
- Training requires utterances and transcripts, encoded audio codes, phoneme sequences, and a manifest; the project includes preparation guidance.checked 10 Oct 2026
- Transcript control
- Its smart transcript feature lets users write only the text they want to generate.checked 10 Oct 2026
- Voice cloning
- To clone or edit an unseen voice, VoiceCraft needs only a few seconds of reference audio.checked 9 Oct 2026
- Voice consent
- The project disclaimer prohibits generating or editing someone’s speech without their consent.checked 10 Oct 2026
- Voice reference
- The project says cloning or editing an unseen voice requires only a few seconds of reference audio.checked 10 Oct 2026
- Ways to run
- The project documents inference through Google Colab, Docker, local setup, and standalone command-line scripts.checked 10 Oct 2026
Where it runs
- Windows and Linux
- The Docker quick start says it was tested on Linux and Windows and should work on hosts with Docker installed.checked 10 Oct 2026
Alternatives to VoiceCraft
- 1
Voicebox
Free planOpen sourceAndroidiOSWebAPI9.3From $12 a year - 2
Speechify
Free planAndroidiOSWebAPI9.0From $10 a month - 3
Resemble AI
Free planAndroidiOSWebAPI9.0From $280 a month - 4
iSpeech
Free planOpen sourceAndroidiOSWebAPI9.0Free plan - 5
Fliki
Free planAndroidiOSWebAPI8.8From $28 a month - 6
Voice.ai
Free planAndroidiOSWebAPI8.8From $5 a month