Spark-TTS

A local text-to-speech system built on Qwen2.5, with Chinese and English voice cloning, adjustable synthetic voices, and Apache 2.0 licensed code.

Spark-TTS is a local text-to-speech system for developers and researchers building speech applications. It can reproduce a voice from reference audio or create a synthetic speaker with chosen vocal traits.

Voice cloning: Generate speech in a reference speaker's voice without training a separate model for that person.
Chinese and English speech: Synthesize both languages, clone voices across them, and produce speech that switches between Chinese and English.
Synthetic speakers: Adjust gender, pitch, and speaking rate to create a voice without copying a reference speaker.

Spark-TTS is built on Qwen2.5 and uses Python and PyTorch. Its code is open source under Apache 2.0. It runs on Linux and Windows, and supports NVIDIA GPU server deployment through Triton Inference Serving and TensorRT-LLM.

Text-to-Speech Models Text-to-Speech and Audiobooks Voice Cloning and Voice Changers macOS Windows Linux Web Hugging Face integration Multilingual Voice cloning

Nobody has claimed Spark-TTS yet

Work on Spark-TTS? Claim this page and we'll verify you by hand. Spark-TTS gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Videos about Spark-TTS

View all Spark-TTS videos

Spark TTS: Arabic fine-tuning and local voice app setup

Similar to Spark-TTS

View all tools

IndexTTS

4 videos

Local text-to-speech software that clones a voice from one recording and supports multilingual speech with emotion and pronunciation controls.

25.1KUpdated 2 months ago

Windows · Linux · Web#Hugging Face integration#Multilingual#Multimodal input

IndexTTS is a local text-to-speech system for people creating spoken audio and developers adding speech generation to applications. It can reproduce a voice from a single reference recording.

Text-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

KittenTTS

1 video

A local text-to-speech library runs on CPU, clones voices from short recordings, and supports multilingual speech on Windows, macOS and Linux.

16.9KUpdated 2 days agoApache-2.0

macOS · Windows · Linux#GGUF#Hugging Face integration#llama.cpp backend

KittenTTS is a Python text-to-speech library for developers adding local speech generation to apps or producing spoken audio from text. It supports voice cloning without model training and doesn't require a GPU.

Inference Libraries and BindingsText-to-Speech and AudiobooksText-to-Speech ModelsVoice Cloning and Voice Changers

Spark-TTS

A local text-to-speech system built on Qwen2.5, with Chinese and English voice cloning, adjustable synthetic voices, and Apache 2.0 licensed code.