
One API for AI image, video, LLM and audio models, billed only when requests succeed
Generate Unique Voices from Text Prompts
Generate unique AI voices using a text-to-speech tool for voiceovers, gaming, audiobooks, and more.
Voice Design, powered by the latest Text to Speech v3 model, allows users to create lifelike AI voices from text prompts. Users can customize tone, accent, age, pacing, delivery, emotion, and audio quality, and preview text before generating. Voice Design is available free to start and offers an API for generating and saving voice previews.
Free plan with 10k credits per month; Starter $6/month with 30k credits; Creator $22/month (first month $11) with 121k credits; Pro $99/month with 600k credits. Plans include varying voice cloning and custom voice options.

One API for AI image, video, LLM and audio models, billed only when requests succeed


AI subliminal maker for custom, studio-quality subliminal audio


AI video generator and creative studio for planning, generating and editing video with images, audio and music.

AI speaker separation that splits one recording into individual, time-aligned WAV tracks per detected speaker.

Test your speakers and headphones in seconds β left, right and stereo channels, a full 20 Hzβ20 kHz sweep, polarity and test tones.



AI podcast studio that turns any content into audio and video podcasts
