Skip to content
Updated for 2026

MakeThisVid and Descript are different types of AI video tools. MakeThisVid generates original AI video scenes from a text prompt or product photo — synthesized footage with ambient audio, requiring no editing or existing footage. Descript is a full-featured AI-powered video and podcast editor — you bring your own footage or recording, and Descript's AI tools help you edit, transcribe, remove filler words, and overdub it. Descript also added AI video generation features (Creator plan and above) for creating B-roll and short clips from prompts — but its core strength remains editing long-form content.

MakeThisVid vs Descript: Scene Generation vs AI-Powered Video Editing

MakeThisVid and Descript occupy different positions in the video production workflow. Descript is primarily an AI-enhanced video editor: you record a video or podcast, import the footage, and Descript makes editing easier using AI tools — text-based editing (edit the transcript to cut the video), speaker detection, filler word removal, automatic captions, and an Overdub feature that lets you change spoken words by retyping them. Descript has also added AI video generation (Creator plan+), letting users generate B-roll and short clips from text prompts using a selection of AI models. MakeThisVid is purpose-built for the opposite workflow: you start with nothing but a text description or a photo, and MakeThisVid generates a short ad-style clip from scratch — audio included, no editing required. The two tools serve different primary use cases, though Descript's expanding AI generation features mean there is some overlap for short-form clip creation.

MakeThisVid vs Descript 6 criteria

Criterion MakeThisVid Descript
Output type AI scene generator (synthesized footage) AI-powered video editor + AI clip generator (Creator+)
Clip length 6-second 720p or 8-second 1080p clips, audio always on Long-form editing (podcasts, talking-head); short AI clips also available
Audio Yes — always included, no upgrade Voice cloning + auto-transcription; AI-generated audio on Creator+ plans
Commercial use Licensed on every plan and credit pack Included on paid tiers
Starting price $2.99 one-time pack; subscriptions from $19.99/mo Free tier available; paid plans from $24/mo (monthly billing: $35/mo Creator)
Best for Short-form ads, social, branded clips — generate from scratch Podcasts, talking-head video, transcript-based editing, content repurposing

How to Use MakeThisVid

From prompt to downloadable MP4, ready to deploy.

  1. Core workflows — generation vs editing

    Descript's primary workflow requires existing footage or a recording — its AI tools help you edit and polish video you've already captured. Descript also offers AI video generation (Creator plan+) for B-roll and short clips from text prompts, using a selection of AI models. MakeThisVid requires only a text prompt or a single photo and generates a complete short clip with audio. There is no timeline, no editing step, and no existing footage needed.

  2. Pricing comparison

    MakeThisVid: one-time packs from $2.99 (1 credit), or subscriptions — Lite ($19.99/mo, 10 credits), Standard ($49.99/mo, 30 credits), Pro ($79.99/mo, 60 credits). No free tier; every render requires credits. Descript: Free tier (watermarked exports, 1 hour media/month), Hobbyist ($24/mo billed monthly or $16/mo annual), Creator ($35/mo billed monthly or $24/mo annual), Business ($65/mo billed monthly or $50/mo annual). Descript is priced around media hours and AI credits per month.

  3. Content creator vs ad producer use case

    Descript is primarily used by podcasters, YouTubers, and video content creators who record long-form content and need efficient editing. MakeThisVid is used by marketers, ecommerce brands, and agencies who need short-form ad creative — 6-second or 8-second clips — generated on demand from prompts or product photos.

  4. Overdub and voice cloning features

    Descript's Overdub feature lets you fix spoken mistakes in a recorded video by retyping the corrected text — the AI generates your voice saying the new words. Voice cloning is now available across all Descript plans, including free. This is an editorial feature for existing recordings that MakeThisVid doesn't offer or need — MakeThisVid generates video from scratch.

  5. Complementary tools for different stages

    These tools can be used together: generate short scene clips with MakeThisVid, then assemble and caption them in Descript if you need to edit them into a longer piece. For paid ad creative or social posts — a 6-second clip goes straight from MakeThisVid to your ad platform with no editing needed.

Who Uses MakeThisVid for This

MakeThisVid for ad creative generation

Generate 6-second 720p or 8-second 1080p scene clips for TikTok, Instagram, and Facebook ad campaigns — no footage, no recording, no editing required. Describe the scene or drop a product photo, generate, download, run. Audio is always included.

Descript for podcast and YouTube video editing

Record your podcast or YouTube video, import into Descript, and use text-based editing to cut, trim, and clean up your recording efficiently. Descript's core strength is editing long-form content creators already produce.

Descript for content repurposing and captions

Transcribe and caption existing video content, create short clips from longer recordings, and repurpose podcast episodes into social video clips. Descript is purpose-built for these post-production workflows.

Frequently Asked Questions

Yes — Descript added AI video generation in 2025, available on Creator and Business plans. You can type a prompt and Descript will generate B-roll clips or short videos using a selection of AI models. However, Descript's primary use case remains editing existing footage; MakeThisVid is purpose-built for generating short ad-style clips from scratch with audio always included.
No. MakeThisVid generates new AI video scenes from prompts or photos. It doesn't edit, transcribe, or process existing footage. Descript is the specialist for editing workflows.
Yes. You could generate clips with MakeThisVid and then assemble, caption, or further edit them in Descript. For short ad creative (6 seconds), the MakeThisVid output typically goes directly to your ad platform without requiring editing.
Descript. It was purpose-built for podcast production — recording, editing, transcribing, and publishing. MakeThisVid doesn't help with any of those workflows.
Yes. Descript has a free tier with watermarked exports and limited media hours per month. MakeThisVid has no free tier — credits are required for all renders, with automatic refunds on failed renders. Descript's AI video generation features (generate from text prompt) require a paid plan (Creator or above).
MakeThisVid is purpose-built for short-form ad creative — generate a 6-second 720p or 8-second 1080p scene from a prompt or photo in under two minutes, with audio always included, no watermark, and commercial use on every plan. Descript can also generate short clips from prompts on paid plans, but is primarily an editing platform.

Generate original AI video scenes

Describe the moment or drop a product photo. Under two minutes to a downloadable 1080p MP4 — audio included, no editing required.

Try MakeThisVid