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

Qwen3-TTS is an open multilingual speech family for voice cloning, expressive generation, streaming, and instruction-based delivery.
Best for: Cloning a reference voice, Generating multilingual speech, Building low-latency voice applications
Record, clean, edit, and transcribe podcast audio in a browser without installing a desktop editor.
Turn a video, social link, or audio file into a transcript, subtitles, and a summary.
Generate expressive speech and clone an authorized voice locally with an efficient open-source TTS model.