Freedom251 › Text-to-speech tools
VoiceCraft-X
Facts from VoiceCraft-X's own pages
- Authorship
- The repository credits Zhisheng Zheng and the University of Texas at Austin with copyright in 2025. · github.com, 13 Oct 2026
- Availability
- The repository's listed inference examples are speech editing and speech synthesis Jupyter notebooks. · github.com, 13 Oct 2026
- Checkpoints
- The repository links to a default multilingual checkpoint and English and Chinese monolingual checkpoints, with more languages noted as forthcoming. · github.com, 13 Oct 2026
- Code-switching
- The site shows Chinese-English code-switching samples and says Spanish-English and French-English samples are coming soon. · voicecraft-x.github.io, 13 Oct 2026
- Commercial use
- No · voicecraft-x.github.io, 20 Sept 2026
- Consent
- The repository says speech generation or editing should not be performed using someone's speech without that person's consent. · github.com, 13 Oct 2026
- Development status
- The repository lists environment setup, inference code, additional monolingual checkpoints, hosted demos, Colab notebooks, command-line support, and efficiency improvements as TODO items. · github.com, 13 Oct 2026
- Fine-tuning
- A code-switching sample table includes a VoiceCraft-X (10h fine-tuning) column. · voicecraft-x.github.io, 12 Oct 2026
- Input and training
- The system overview caption says the model takes text and a speaker embedding as input and is trained to predict speech-token sequences. · voicecraft-x.github.io, 12 Oct 2026
- Languages
- The site lists English, Mandarin, Korean, Japanese, Spanish, French, German, Dutch, Italian, Portuguese, and Polish. · voicecraft-x.github.io, 13 Oct 2026
- License
- The work is licensed under Creative Commons Attribution-NonCommercial 4.0 International, and the repository says to contact the authors for commercial use. · github.com, 13 Oct 2026
- Model architecture
- The site says VoiceCraft-X uses the Qwen3 large language model for phoneme-free cross-lingual text processing. · voicecraft-x.github.io, 12 Oct 2026
- Platforms
- self_hosted · voicecraft-x.github.io, 20 Sept 2026
- Product
- VoiceCraft-X is an autoregressive neural codec language model for multilingual speech editing and zero-shot text-to-speech synthesis. · voicecraft-x.github.io, 12 Oct 2026
- Purpose
- VoiceCraft-X combines multilingual speech editing with zero-shot text-to-speech synthesis in one autoregressive neural codec language model. · voicecraft-x.github.io, 13 Oct 2026
- Setup
- The repository installation instructions create a Python 3.10 Conda environment and install dependencies with pip. · github.com, 13 Oct 2026
- Speech editing
- The site presents examples of editing existing speech by changing or adding words in a transcript. · voicecraft-x.github.io, 12 Oct 2026
- Speech editing dependency
- Montreal Forced Aligner is used for speech editing, and the repository says it can be skipped if installation is difficult. · github.com, 13 Oct 2026
- Speech generation
- Its token reordering mechanism uses time-aligned text and speech tokens to frame editing and synthesis as sequence generation. · voicecraft-x.github.io, 13 Oct 2026
- Text processing
- The model uses Qwen3 for phoneme-free cross-lingual text processing. · voicecraft-x.github.io, 13 Oct 2026
- Token mechanism
- The site describes a token reordering mechanism using time-aligned text and speech tokens. · voicecraft-x.github.io, 12 Oct 2026
- Voice cloning
- The project describes its speech synthesis as voice-cloning and zero-shot TTS. · voicecraft-x.github.io, 13 Oct 2026
Where VoiceCraft-X stands on Freedom251
- Text-to-speech tools#232 of 232
- Text-to-Speech Software#223 of 223