Descript

Train your own voice and use it for text-to-speech

About

Descript is an audio/video editor that includes transcription, a screen recorder, publishing, and AI tools like ultra-realistic voice cloning with Overdub, free voice models, privacy first features, ability to make mid-sentence changes to real recordings, creating multiple voices, sharing with trusted collaborators, and a high quality stock voice library. It also provides 44.1KHz broadcast quality speech synthesizer and a live Overdubing.

Categories

speech-to-text text-to-speech

Penno Partner Deal

Get 1 month free with our partner Penno.

Code: AI-POWERED

Join Our Newsletter

Find it useful?

Subscribe to get weekly recommendations for your profession

Related Tools

AI Music Vocal Generator

text-to-speech music

Real-time transcription audio to text

AI realistic text-to-speech voice generator

Tool for creating animated stories with original characters, scenes, dialogue, and assets

text-to-speech generative video

Text-to-speech tool for podcasts

podcasting text-to-speech

Save anything, including conversations and make them searchable

speech-to-text productivity

Text-to-speech tool with over 80 languages, 120 accents, and 900 voices

Transcribe calls and create notes to train sales teams

speech-to-text marketing

Deciphr timestamps and summarizes your entire podcast transcript for you

speech-to-text podcasting

Convert text to voice in real time