Apps similar to SherpaTTS include VoiceStudio, which is free and open source. Other options are ElevenLabs, NaturalReader, Kokoro and eSpeak. There's no shortage of Text to Speech Services like SherpaTTS , with more than 50 alternatives for the web, Windows, Mac, Linux and Android.
AI-powered tool for editing audio and video by editing transcribed text, featuring transcription, filler removal, captions, background replacement, rapid translation, collaboration, mastering, recording, and viral content identification features.
United States
The eSpeak NG is a compact open source software text-to-speech synthesizer for Linux, Windows, Android and other operating systems. It supports more than 100 languages and accents. It is based on the eSpeak engine created by Jonathan Duddington.
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.
Singapore
Amazon Polly uses deep learning technologies to synthesize natural-sounding human speech, so you can convert articles to speech. With dozens of lifelike voices across a broad set of languages, use Amazon Polly to build speech-activated applications.
United States
Free open source AI voice cloning and text to speech synthesis. Clone a voice in 5 seconds to generate arbitrary speech in real-time.
Supertonic TTS is a high-performance, on-device text-to-speech (TTS) system for Android. It uses Supertonic ONNX models to provide high-quality speech synthesis entirely offline, ensuring privacy and availability without an internet connection.
Generates realistic AI-driven voice-overs using over 100 voices and 15 languages, converts scripts or personal recordings into pro-quality speech, offers precise timing sync with video or slides, easy script editing, music blending, and secure cloud storage.
United States
Processes both audio and text inputs with a multi-task framework supporting over 30 language and sound tasks, enabling multi-turn dialogue, sound reasoning, and tool use, while excelling in benchmarks without task-specific fine-tuning or retraining.
China
Creates natural-sounding speech from text in multiple languages and voices using neural networks, with an advanced browser editor, export options as MP3, WAV, or MP4, SSML formatting, transcription, video recording, customization features, and collaboration tools.
Germany
EU
Mimic is a powerful TTS tool. Mimic is low-latency and has a small resource footprint. Its range of high quality voices also set it apart from other open source text-to-speech projects.
TurboTTS is a free text-to-speech online tool. Up to 70 languages, more than 300 types of real-life voices to choose from, simple and easy to use.
Belgium
