Open-source text to speech and voice cloning
Models and servers that turn text into spoken audio on your own hardware, including ones that copy a voice from a short reference clip. The licence on the weights matters as much as the licence on the code here, and the table shows both.
An AGPL-3.0 desktop workflow engine for voice cloning, voice design, video dubbing, dictation and audiobooks, running 16 speech engines and 10 transcription engines locally, with a local API and an MCP server for agents.
A multilingual text-to-speech system with voice cloning from a 10 to 30 second clip and inline emotion tags, released with its weights under a research licence that requires a separate agreement for commercial use.
A family of text-to-speech models from Resemble AI under MIT, with zero-shot voice cloning from a reference clip and a multilingual model covering 23 languages.
A research text-to-speech model with zero-shot voice cloning whose code is MIT but whose pretrained weights are non-commercial, because of the dataset they were trained on.
A fast, local neural text-to-speech engine maintained by the Open Home Foundation, used by Home Assistant and the NVDA screen reader, under GPL-3.0.
A Docker image that serves the 82-million-parameter Kokoro model through an OpenAI-compatible speech endpoint, with streaming, voice mixing and nine languages, all under Apache-2.0.
Tencent Hunyuan's 1.5-billion-parameter speech foundation model under MIT for code and weights, covering zero-shot text to speech, speech editing, enhancement and separation through one natural-language instruction interface.
An open-weight bilingual English and Chinese text-to-speech model built for real-time interaction, with voice cloning, voice design and inline vocal events, whose weights and self-hosted outputs are non-commercial.
A programmatic AI video engine built on Remotion under MIT, that wires 40+ open-source voice, avatar, caption, video, music and image projects into one local render pipeline.
An MIT-licensed Windows text-to-speech studio that runs Piper and Kokoro locally for voice synthesis, Whisper for speech-to-text, with voice blending, a visual SSML editor and SRT export.
Questions people ask
What is the best open-source text-to-speech model?
It depends on the licence you need and whether you need cloning. Chatterbox (MIT code and weights) clones voices and can ship in a product. Kokoro (Apache-2.0) is small, runs on a CPU and ships preset voices. Fish Speech and F5-TTS clone well by their own demos but restrict commercial use of their weights. Piper is the engine for small devices.
Which open-source text-to-speech models allow commercial use?
Chatterbox (MIT), Kokoro (Apache-2.0) and Piper (GPL-3.0 on the engine, with each voice's licence to check). Fish Speech's research licence and F5-TTS's CC-BY-NC weights both exclude commercial use without a separate agreement, and this directory labels them source available and open weights for that reason.
Can open-source text to speech clone a voice?
Yes. Chatterbox, Fish Speech and F5-TTS all clone from a short reference clip, typically ten to thirty seconds, with no training step. Kokoro and Piper do not clone: Kokoro's README calls its voice mixing a tuner rather than a cloner, and Piper speaks with trained voice models.
Does open-source text to speech need a GPU?
Not always. Kokoro FastAPI ships CPU images and quotes under a second to first audio on an Apple M3 Pro. Piper is built for small machines. Chatterbox Nano is described as running faster than real time on 8 CPU cores. Fish Speech and F5-TTS quote their figures on NVIDIA GPUs.
Paying for an AI tool you would rather own?
Reveneau sets up the replacement on your own servers, connects it to your product, and builds the software around it.