Audio & Voice

Edit audio and video by editing the transcript like a document.

Speak naturally and get clean, polished text in any app.

Split any song into vocals, drums, bass and more to practice or remix.

Generate and edit original music in many styles, then download a short MP3 or MIDI draft for a project.

Make text-to-speech alerts and sound clips for a livestream.

Generate a usable music track from a style and mood in a few clicks.

Transform a live sound into a new playable texture while keeping its musical shape.

A multimodal audio studio for natural speech, voice design, voice cloning, music, and sound creation.

Paste text and turn it into natural-sounding speech online without signup or a complicated editor.

An AI music workspace that turns natural-language ideas into complete songs, arrangements, and production drafts.

Turn a recording or live conversation into a structured transcript with captions, timestamps, and speakers.

Generate expressive, multilingual speech from a short voice reference with an open local model.

Turn English speech into punctuated text with word timestamps using an NVIDIA open ASR model.

Generate or extend short music and sound effects from a prompt.

Generate natural speech locally or in a public demo with a small open-weight TTS model.

Turn text into speech with a small TTS model that can run locally on CPU.

Give the model a video, text, or audio cue and create a scene-aware sound layer or edit.

Upload a noisy recording and get a cleaner speech track without manual audio cleanup.