AI applications / Speech & Audio / Descript
Descript
Descript is an AI-powered editor for podcasts and videos that transcribes recordings automatically and lets you cut or rearrange media simply by editing the text transcript. Its Overdub feature lets you fix spoken mistakes by typing corrections using a cloned version of your own voice. It targets podcasters, journalists, and video creators who want an accessible, fast post-production workflow.
Written by Claude claude-sonnet-4-6
Other tools in this category
Adobe Podcast (Enhance Speech)
AI tool that instantly converts podcast and voice recordings to studio quality. Removes background noise and improves voice quality automatically.
ElevenLabs
Most realistic AI voice generation on the market. Clones voices in seconds. Supports 29 languages. Used by podcast creators, publishers and game studios.
Murf AI
AI voice-over studio with 120+ realistic voices in 20+ languages. Ideal for e-learning, videos and podcasts without a microphone.
Resemble AI
AI voice cloning and text-to-speech platform for developers. Real-time voice generation and deepfake detection built in.
Whisper (OpenAI)
OpenAI's open-source speech-to-text model. Excellent transcription in 99 languages. Free to download and use.