Home › Best AI tools › Open-source AI voice and speech tools
Open-source AI voice and speech tools
23 open-source voice & speech tools. Voice & Speech tools listed as Free because they are open-source projects you can download and run. Check each project's license, and note that hosting and model costs may still apply.
How to read this page. The tools are grouped by category and are not ranked. Pricing labels come from vendors' own pages when we could confirm them. Always verify plans and limits on the vendor's site.
Voice & Speech (23)
| Tool | What it does | Pricing | Link |
|---|---|---|---|
| Applio | Open-source voice conversion tool built on RVC. | Free | Official site |
| Bark | Suno open-source text-to-audio model. | Free | Official site |
| Buzz | Open-source desktop app that transcribes and translates audio offline using Whisper. | Free | Official site |
| Chatterbox | Open-source text-to-speech and voice cloning model from Resemble AI. | Free | Official site |
| Coqui TTS | Open-source deep learning toolkit for text-to-speech with pretrained models. | Free | Official site |
| F5-TTS | Open-source text-to-speech model with zero-shot voice cloning. | Free | Official site |
| faster-whisper | Open-source reimplementation of Whisper using CTranslate2 for faster transcription. | Free | Official site |
| GPT-SoVITS | Open-source few-shot voice cloning and TTS. | Free | Official site |
| Higgs Audio | Boson AI open-source audio foundation model for expressive speech. | Free | Official site |
| Kokoro TTS | Open-weight 82M-parameter text-to-speech model with natural voices that runs on modest hardware. | Free | Official site |
| Moshi | Kyutai open-source real-time speech-to-speech dialogue model. | Free | Official site |
| NVIDIA Broadcast | Free NVIDIA RTX app with AI noise removal, virtual backgrounds and eye contact for calls and streams. | Free | Official site |
| OpenAI Whisper | OpenAI's open-source speech recognition model for multilingual transcription. | Free | Official site |
| OpenVoice | MyShell open-source instant voice cloning. | Free | Official site |
| Orpheus TTS | Open-source speech LLM for human-like TTS from Canopy Labs. | Free | Official site |
| Pipecat | Open-source framework for building real-time voice and multimodal conversational agents. | Free | Official site |
| Piper | Fast, local open-source neural text-to-speech engine. | Free | Official site |
| RVC | Open-source retrieval-based voice conversion web UI. | Free | Official site |
| TTSMaker | Free online text-to-speech tool with many voices and languages. | Free | Official site |
| Vocode | Open-source library for building voice-based LLM phone and web agents. | Free | Official site |
| Vosk | Open-source offline speech recognition toolkit for many languages and devices. | Free | Official site |
| whisper.cpp | Open-source C/C++ port of OpenAI Whisper for fast local speech recognition. | Free | Official site |
| WhisperX | Open-source speech recognition with word-level timestamps and speaker diarization. | Free | Official site |