The best open source alternative to ElevenLabs is Voxtral. If that doesn't suit you, our users have ranked more than 50 alternatives to ElevenLabs and ten of them is open source so hopefully you can find a suitable replacement. Other interesting open source alternatives to ElevenLabs are VoiceCraft, X to Voice, Kokoro and SherpaTTS .
Advanced audio models for transcription, translation, and understanding, optimized for production and edge deployment, API accessible, open-source with Apache 2.0, delivering high accuracy, resource efficiency, and support for both large-scale and local use cases.
VoiceCraft is a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on in-the-wild data including audiobooks, internet videos, and podcasts.
Open-source tool that analyzes your X/Twitter profile data to generate a custom voice with ElevenLabs Voice Design API, integrating with Hedra's video API for an innovative audio-visual experience.
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.
SherpaTTS is an Android Text-to-Speech engine based on Next-gen Kaldi using Piper or Coqui voices.
We're excited to introduce Chatterbox, Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations.
QwenVoice is a native SwiftUI macOS application that brings state-of-the-art text-to-speech to Apple Silicon Macs with no Python install, no terminal, and no dependencies required of the user — just download and run.
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.
A privacy-focused online video editor that processes videos entirely in your browser using FFmpeg and WebAssembly. No uploads, no signups required.
France
EU
United States
Canada
Singapore
It has nothing to do with Elevenlabs: Elevenlabs "speaks" voices, Voxtral "hears" voices.
Don't confuse text-to-speech (TTS; Elevenlabs) with speech-to-text (STT; Voxtral).