- Home
- Text-to-Speech Software
- Spark-TTS
On the recordRead 12 Oct 202615 facts
Spark-TTS
Plans and prices
Spark-TTS (Apache-2.0 open-source inference code)
Free
Inference code; model download required
Read 12 Oct 2026 · github.com
On the record
- Commercial use
- Nosparkaudio.github.io · read 20 Sep 2026
- Deployment
- The repository provides a reference for deploying Spark-TTS with Nvidia Triton and TensorRT-LLM.github.com · read 12 Oct 2026
- Installation
- The project documents Linux installation and links to a Windows installation guide.github.com · read 12 Oct 2026
- Intended use
- The project describes academic research, education, personalized speech synthesis, assistive technologies, and linguistic research as intended uses.github.com · read 12 Oct 2026
- Languages
- It supports Chinese and English, including cross-lingual and code-switching voice cloning.github.com · read 12 Oct 2026
- License
- The repository identifies its license as Apache-2.0.github.com · read 12 Oct 2026
- Model design
- The system uses Qwen2.5 and reconstructs audio directly from codes predicted by the LLM.github.com · read 12 Oct 2026
- Purpose
- Spark-TTS is an LLM-based text-to-speech system for voice synthesis.sparkaudio.github.io · read 12 Oct 2026
- Training materials
- The repository's to-do list names release of the training code and VoxBox training dataset as pending items.github.com · read 12 Oct 2026
- Usage restrictions
- The developers warn against unauthorized voice cloning, impersonation, fraud, scams, deepfakes, and illegal use.github.com · read 12 Oct 2026
- Voice cloning
- It supports zero-shot voice cloning without training data specific to the cloned voice.github.com · read 12 Oct 2026
- Voice controls
- Speech generation can be controlled through speaker gender, pitch, and speaking rate.github.com · read 12 Oct 2026
- Web interface
- The locally launched Web UI supports voice cloning by uploading reference audio or recording it, as well as voice creation.github.com · read 12 Oct 2026
