The open-source alternatives to ElevenLabs are Chatterbox, Kokoro, Piper, Fish Speech and F5-TTS, plus two runtimes, Speaches and sherpa-onnx, that serve such models through an API or on a phone. Chatterbox and Kokoro carry MIT and Apache licences on both code and weights, so they are the ones a company can ship with. Piper is the small, fast engine behind Home Assistant. Fish Speech and F5-TTS produce voice clones from a ten-second clip, and both restrict commercial use of their weights, which this page spells out. A team switches when it wants the audio generated on its own hardware, no per-character bill, and a licence it has read.
ElevenLabs, in the vendor's own words: an AI voice generator and voice agents platform with access to 5,000+ voices in 70+ languages through APIs and SDKs, by the vendor's own count. elevenlabs.io.
| Project | Openness | Licence | Runs as | Platforms | Self-host | Hosted option | Last release | Stars |
|---|---|---|---|---|---|---|---|---|
| Fish Speech | Source available | See LICENSE | Docker, CLI, Web UI, Server | Linux (GPU server), Docker | Yes | Yes | May 31, 2025 | 32,719 |
| Chatterbox | OSI | MIT | pip, Python library | Linux (tested on Debian 11), CPU or NVIDIA GPU | Yes | Yes | Jun 13, 2025 | 26,448 |
| F5-TTS | Open weights | MIT | pip, Docker, CLI, Web UI (Gradio) | Linux (NVIDIA, AMD ROCm, Intel GPU), macOS (Apple Silicon) | Yes | No | Jul 23, 2026 | 15,239 |
| sherpa-onnx | OSI | Apache-2.0 | Libraries in 12 languages, prebuilt Android and Flutter apps, WebAssembly, websocket server | Linux, macOS, Windows, Android, iOS, HarmonyOS, Node.js, WebAssembly, Raspberry Pi and named boards | Yes | No | Sep 10, 2026 | 14,808 |
| Piper | OSI | GPL-3.0 | pip, CLI, Server, C/C++ library | Linux, macOS, Windows, small devices (used by Home Assistant) | Yes | No | Sep 4, 2026 | 5,598 |
| Kokoro FastAPI | OSI | Apache-2.0 | Docker, Server (OpenAI-compatible API) | Linux, macOS (Apple Silicon when run directly), Windows | Yes | No | Sep 10, 2026 | 5,449 |
| Speaches | OSI | MIT | Docker, Server (OpenAI-compatible API) | Docker on GPU or CPU | Yes | No | Dec 27, 2025 | 3,665 |
Licence, release and star figures read from GitHub on September 16, 2026. Openness labels: The code, and the weights where the project is a model, carry a licence on the OSI approved list. The code is public, and the licence limits what you may do with it. Read the LICENSE file before commercial use. The model weights can be downloaded and run. The training data or code is closed, or the weights carry a restriction the code does not.
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.
Docker, CLI, Web UI, Server · Linux (GPU server), Docker · Runs on your own machines · Hosted version available from the maintainers · Weights: Fish Audio Research License, non-commercial without a separate agreement
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.
pip, Python library · Linux (tested on Debian 11), CPU or NVIDIA GPU · Runs on your own machines · Hosted version available from the maintainers
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.
pip, Docker, CLI, Web UI (Gradio) · Linux (NVIDIA, AMD ROCm, Intel GPU), macOS (Apple Silicon) · Runs on your own machines · Weights: CC-BY-NC-4.0 on the pretrained models; the code is MIT
A runtime under Apache-2.0 from the next-generation Kaldi team that runs speech to text, text to speech, speaker diarization and voice activity detection locally on CPUs, NPUs and phones, with no internet connection.
Libraries in 12 languages, prebuilt Android and Flutter apps, WebAssembly, websocket server · Linux, macOS, Windows, Android, iOS, HarmonyOS, Node.js, WebAssembly, Raspberry Pi and named boards · Runs on your own machines
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.
pip, CLI, Server, C/C++ library · Linux, macOS, Windows, small devices (used by Home Assistant) · Runs on your own machines
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.
Docker, Server (OpenAI-compatible API) · Linux, macOS (Apple Silicon when run directly), Windows · Runs on your own machines
An OpenAI-compatible server under MIT for streaming transcription, translation and text to speech, loading Whisper, Kokoro and Piper models on demand, described by its maintainers as Ollama for speech models.
Docker, Server (OpenAI-compatible API) · Docker on GPU or CPU · Runs on your own machines
It depends on what you need to ship. For a commercial product, Chatterbox (MIT code and weights, voice cloning from a reference clip) and Kokoro (Apache-2.0 code and weights, preset voices, 82 million parameters) are the two whose licences allow it without a separate agreement. For a small device or a home automation setup, Piper is the one Home Assistant uses. For the closest voice clone, Fish Speech and F5-TTS, both of which restrict commercial use.
Yes. Chatterbox, Kokoro, Piper, Fish Speech and F5-TTS all run on your own machine with no account and no network call once the model is downloaded. Kokoro FastAPI and Piper both run on a CPU. Chatterbox Nano is described by its maintainers as running faster than real time on 8 CPU cores.
Chatterbox, Fish Speech and F5-TTS all clone a voice from a short reference recording, typically ten to thirty seconds, with no training step. Kokoro does not clone voices: it ships preset voices and a mixing feature its own README calls a tuner rather than a cloner. Piper uses trained voice models rather than cloning.
Chatterbox (MIT), Kokoro (Apache-2.0) and Piper (GPL-3.0 on the code; check the licence of each voice model separately). Fish Speech releases code and weights under the Fish Audio Research License, which requires a separate written licence for any commercial purpose. F5-TTS code is MIT but its pretrained weights are CC-BY-NC-4.0, which excludes commercial use.
This page does not rank voice quality, because nobody here has measured it on a shared test. Each project's demo page is linked from its own page so you can listen with your own text. What can be stated: Chatterbox and Fish Speech publish inline emotion tags, Kokoro is a small model that runs on a CPU, and Piper is built for speed on small devices.
Kokoro FastAPI exposes an OpenAI-compatible speech endpoint on port 8880 that works with the OpenAI SDKs. Speaches, listed under speech-to-text engines, serves Kokoro and Piper voices through the same OpenAI-compatible shape. Chatterbox and F5-TTS are Python libraries with a Gradio web app, so a small wrapper is needed for an HTTP API.
Open source means the code and the weights both carry a licence on the OSI approved list, such as MIT or Apache-2.0. Open weights means you can download and run the model, but the training data or code is closed, or the weights carry a restriction the code does not. F5-TTS is the clearest example on this page: MIT code, non-commercial weights.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.