Audio & Voice

Fly through music genres and hear the sound change in real time.

Replace a GitHub URL segment to hear an AI-generated podcast about the repository.

Speak to ChatGPT, let it read replies aloud, and use shortcuts to keep the conversation moving without typing.

Turn messy speech into cleaner notes with an offline dictation workflow.

Qwen3-TTS is an open multilingual speech family for voice cloning, expressive generation, streaming, and instruction-based delivery.

Turn a script or short voice sample into expressive, editable audio.

Turn lyrics into a song or test a cover and stem workflow with a small free allowance.

Have any text, PDF or web page read aloud to you.

Change your voice in real time for games, Discord and streams.

Turn text into lifelike speech, clone a voice, or dub a video into another language.

Generate royalty-free background music for videos and podcasts.

Transcribe audio privately on your Mac, with no uploads.

Record, clean, edit, and transcribe podcast audio in a browser without installing a desktop editor.

Paste song links and hear a quick mashup or DJ set in the browser.

A controllable text-to-speech and voice-production studio for turning scripts into natural-sounding audio in many languages.

Create voice content or check and protect synthetic media through one voice and security platform.

Turn a style idea into a song draft you can shape.

Record, clean up, and repurpose audio or video in one creator workspace.