Text in die Rede KI-Agenten Musik Audio zu Text Stimme Klonen Sprachgestaltung Marktplatz Mehr
Report Bug / Feature Request

Multi-Track Studio

Arrange voice tracks, music beds and chapter markers on a timeline. One-click mixdown export.

Kostenlos anmelden
Unsaved
My Projects
0:00 / 0:00

Tracks

No tracks yet. Click "Add Voice Track" above to get started.

Chapter Markers

0

No chapter markers. Click "Chapter" above to add one at the playhead.

Mixdown Result

queued
Queued...

Häufig gestellte Fragen

A Descript/Murf-style timeline editor for AI audio. Add multiple voice tracks, optional music or sound-effect beds, drag each region into position on a timeline, drop chapter markers on the ruler, then render a single mixed-down MP3 export.

The original Audio Studio is a sequential chapter editor — chapters play back-to-back. The Multi-Track Studio is a free-form timeline where regions can overlap, sit at any timestamp, and have independent volume.

Yes. Projects autosave a few seconds after you stop editing.

Voice tracks (text → TTS using any model and voice you have access to), music beds (uploaded audio URL), and sound-effect tracks (uploaded audio URL). Each track has its own volume slider and start time.

Chapter markers are flag icons on the timeline ruler with a name + start time in seconds. They are saved with the project.

When you click Render, every voice track is generated via TTS in parallel. The GPU server then uses ffmpeg to stitch the clips in order at their start times into a single MP3.

Only voice tracks consume characters — music and SFX tracks are free passthroughs. Total voice text is multiplied by the model tier cost and atomically deducted before rendering starts.
5.0/5 (1)

Was könnten wir verbessern? Ihr Feedback hilft uns, Probleme zu beheben.

Bereit für den Anfang?

Melde dich kostenlos an und erhalte 15.000 Zeichen. Keine Kreditkarte erforderlich.

Kostenlos anmelden Preise anzeigen