Descript

Doc-style video and audio editor

Free tier + paidAI media generationdescript.com

What it is

Edits audio and video by editing the transcript - delete a word in the document and it vanishes from the timeline. Underlord is the AI editing agent that removes filler, finds clips and drafts sequences; Overdub does voice cloning and Studio Sound rescues bad recordings.

Why it earns a slot

The biggest time-saver for podcasts, interviews and talking-head content: fixing a misspoken line means retyping it, not re-recording it. Nothing else combines transcript editing, filler removal, voice cloning and multitrack screen recording in one app.

Know before you commit

Media hours and AI credits are metered separately, so you can exhaust one while the other sits unused. The free tier watermarks exports and caps them at 720p, and voice cloning needs Creator ($24/mo annual) or above.

Getting started

No self-serve public generation API; integrations run through Zapier and the app ecosystem.

Field notes

0 from the community

Loading notes…

Field check

Unverified

Pricing snapshot

Free 1 hr/mo, 720p watermarked. Hobbyist $16/mo annual (10 hrs, 400 AI credits), Creator $24 (30 hrs, 800), Business $50 (40 hrs, 1,500). Monthly billing runs about 45% higher.

Snapshots move fast — verify at checkout, and post a field note if it changed.

Drop into your Lovable chat

Evaluate Descript (https://www.descript.com) for this project, then use it only if it fits what we are already building.
Context: Doc-style video and audio editor. Edits audio and video by editing the transcript - delete a word in the document and it vanishes from the timeline. Underlord is the AI editing agent that removes filler, finds clips and drafts sequences; Overdub does voice cloning and Studio Sound rescues bad recordings.
Reviewer notes (general, not written for this codebase): The biggest time-saver for podcasts, interviews and talking-head content: fixing a misspoken line means retyping it, not re-recording it. Nothing else combines transcript editing, filler removal, voice cloning and multitrack screen recording in one app.
Watch out for: Media hours and AI credits are metered separately, so you can exhaust one while the other sits unused. The free tier watermarks exports and caps them at 720p, and voice cloning needs Creator ($24/mo annual) or above.
Pricing: Free 1 hr/mo, 720p watermarked. Hobbyist $16/mo annual (10 hrs, 400 AI credits), Creator $24 (30 hrs, 800), Business $50 (40 hrs, 1,500). Monthly billing runs about 45% higher.
Setup: No self-serve public generation API; integrations run through Zapier and the app ecosystem.
Rules: treat the notes above as background only. Do not assume a theme, style, layout or feature that is not already in this project — inspect the existing code first and ask me before changing visual direction.

/api/public/tools/descript

Also in AI media generation

Adobe Firefly

firefly.adobe.com

Indemnified, commercially safe gen

Free tier + paidAI media generation

Free tier with limited watermarked credits. Standard $9.99/mo (2,000 credits), Pro $19.99 (4,000), Premium $199.99 (50,000). API is enterprise contract only.

Open dossier

Black Forest Labs (FLUX)

bfl.ai

Open-weight image models + API

Free tier + paidAI media generation

API per image: FLUX.2 klein from $0.014, pro from $0.03, flex $0.05, max $0.07. Kontext pro $0.04, max $0.08. Open weights free to self-host.

Open dossier

Cartesia

cartesia.ai

Ultra-low-latency TTS for agents

Free tier + paidAI media generation

Free 20K credits, personal use only. Pro $5/mo (100K), Startup $49 (1.25M), Scale $299 (8M). TTS is 1 credit/character, Ink STT 1 credit/second, Line voice agents $0.014/min.

Open dossier

ElevenLabs

elevenlabs.io

Text-to-speech, voice cloning

Free tier + paidAI media generation

Free 10K credits/mo. Starter $6 (30K), Creator $11 first month then $22 (121K), Pro $99 (600K), Scale $299 (1.8M), Business $990 (6M). About 17% off annual.

Open dossier