This demo application uses the ElevenLabs API to generate high-quality text-to-speech conversions.
Choose from 1.000+ voices (45 by default, more in their Voice Library) and 26 languages to personalize your audio output.
The main frontend logic is found in the app/voice folder. Components used are found in the components/voice folder.
Adjust various settings like stability, similarity, and style to fine-tune your audio output.
The API endpoints for text-to-speech can be found in app/api/voice/*. There are 4 endpoints: (1) get available voices, (2) get available models, (3) generate speech and (4) upload the audio.
Listen to your generated audio directly in the browser with our built-in audio player.
Explore different AI models for voice generation in the settings.
