Loading...
Convert text into natural-sounding speech using advanced AI voice synthesis models. Choose from hundreds of voices across dozens of languages with adjustable emotion, speed, and tone. Perfect for YouTube voiceovers, podcasts, audiobooks, e-learning content, and accessibility applications with human-quality audio output.
Text to generate speech from
Desired delivery style. Use auto to let the model choose.
Controls speech expressiveness (0.25-2.0, neutral=0.5, extreme values may be unstable)
Controls randomness in generation (0.05-5.0, higher=more varied)
Audio sample rate in Hz.
MP3 bitrate in bits per second
mono for 1 channel (default), stereo for 2 channels
Show in the public gallery
Sample audio preview
Enter text and click Generate to create speech