Video recording · replacement recipe

Go from Descript to whisper.cpp

The job: Video podcast editing (Text-based video editing, Transcription). Pick where you are today and where you want to land; the move below follows your pick.

From · what you pay for now
Descript
Descript Hobbyist · $24/mo
Year one−$62modeled
To · your pickCosts more in year one
whisper.cpp
Self-hosted · $0 a month + 0.5 h upkeep a month
Change where you land

The money

$24/mo today $0/mo

Descript Hobbyist

Year one, net−$62
Pays back innever

Modeled from public list prices, with your time at $50 an hour. Show the math

Does it do the job? 1 of 2 covered

  • Text-based video editing
  • Transcription

The work

Setup
About 1 h
Upkeep
0.5 h a month
Watch out
Doesn't cover: Text-based video editing

Make the move in four steps

  1. Export from Descript

    Finished compositions (video, audio, GIF, text or subtitle files). Format: Video, audio, GIF, text or subtitle files

    Export steps

  2. Set up whisper.cpp

    Local transcription on your own computer (CPU or GPU); no text-based video editing.

    Details

  3. Switch links and integrations

    Point links, embeds and integrations at whisper.cpp, then send a test through every one.

  4. Cancel Descript

    Turn off renewal before your renewal date, once the new setup works. Access runs until: The end of the current billing cycle; then the Drive moves to the Free plan.

    How to cancel Descript
Open whisper.cppHow to cancel Descript
Modeled, not measured. Savings use public prices and planning assumptions: the bill you stop paying, minus the new tool, your upkeep time and your setup time at $50/hour, over the first 12 months. Paths marked Tested by Stackcut were run end to end by us on our own products. They're our tests, not customer results. Check the must-haves in each recipe before you switch.

The whole recipe: 3 ways out, best first

What you use

  • Text-based video editing
  • Transcription

Not covered

  • Screen recording
  • Remote recording
  • AI voice (Overdub)
  • Studio Sound cleanup
  • Captions

Check before switching

  • You only rely on: Text-based video editing, Transcription
  • Export your data from Descript before canceling

Agents: get_recipe("replace-descript") on the Stackcut MCP server.

3 ways out, best first

Open sourcewhisper.cppCosts $62 more in year one
$24/mo today → $0/mo + 0.5 h upkeep · setup 1 h
Covers 50% of the core features (not: Text-based video editing)
Local transcription on your own computer (CPU or GPU); no text-based video editing.
License: MIT
How we got this
You pay now: Descript Hobbyist$24/user/mo × 1 user$24/mo
New cost: whisper.cppruns on your own machine$0/mo
Your upkeep time0.5 h/mo × $50/h$25/mo
Difference each month$24 − $0 − $25−$1/mo
Over 12 months−$1 × 12−$12
Setup, once1 h × $50/h−$50
Year one−$12 − $50−$62
  • Not counting your time (7 h in year one): saves $288 in year one.

Year one = 12 × (what you pay now − the new cost − upkeep) − setup, with your time at $50/hour. Prices are public list prices; hours are Stackcut’s planning estimates. Price it for your team

Sources: descript.comgithub.com
Agent skillfaster-whisper skill (local transcription)Costs $112 more in year one
$24/mo today → $0/mo + 0.5 h upkeep · setup 2 h
Transcribing recorded calls, voice memos and videos on your own machine (text, SRT/VTT, speaker labels) so your agent can write the notes, instead of paying per-minute or per-seat transcription.
Covers 50% of the core features (not: Text-based video editing)
Assumes you already pay for an agent that runs skills (an agent that supports Agent Skills (e.g. Claude Code/Cowork, Codex, Cursor, Gemini CLI); the agent's own subscription is not counted; shell access; Python 3.10+ (GPU optional); speaker diarization uses a Hugging Face token (--hf-token)); that agent's cost isn't counted. Setup (2 h) and upkeep (0.5 h a month) are Stackcut's estimates; not tested by Stackcut.
License: MIT
Install: npx skills add https://github.com/theplasmak/faster-whisper --skill faster-whisper (skills.sh; or unzip the GitHub release into your skills folder), then ./setup.sh creates a venv with faster-whisper and ./setup.sh --diarize adds pyannote.audio (README)
How we got this
You pay now: Descript Hobbyist$24/user/mo × 1 user$24/mo
New cost: faster-whisper skill (local transcription)runs in the agent you already pay for$0/mo
Your upkeep time0.5 h/user/mo × 1 user × $50/h$25/mo
Difference each month$24 − $0 − $25−$1/mo
Over 12 months−$1 × 12−$12
Setup, once2 h × $50/h−$100
Year one−$12 − $100−$112
  • Not counting your time (8 h in year one): saves $288 in year one.

Year one = 12 × (what you pay now − the new cost − upkeep) − setup, with your time at $50/hour. Prices are public list prices; hours are Stackcut’s planning estimates. Price it for your team

Sources: github.comraw.githubusercontent.comdescript.com
Agent skillAgent skill: video-use (Browser Use)Priced by usage
Free to install; needs ElevenLabs API (Scribe speech-to-text) (Starter: 30k credits/mo; commercial license; instant voice cloning; 20 Studio projects; Creator: 121k credits/mo; first month 50% off ($11); professional voice cloning; additional credits available)
Transcript-driven edits of talking heads, tutorials and interviews: the agent reads a word-level transcript, cuts filler words and dead space, grades color, burns subtitles and renders final.mp4, instead of a Descript seat.
Covers 100% of the core features
Assumes you already pay for an agent that runs skills (Claude Code, Codex or another agent with shell access; ffmpeg; Python with uv); that agent's cost isn't counted. Needs ElevenLabs API (Scribe speech-to-text): priced by usage, so this way isn't priced here. Setup (2 h) and upkeep (0.5 h a month) are Stackcut's estimates; not tested by Stackcut.
License: MIT
Install: git clone https://github.com/browser-use/video-use ~/Developer/video-use && ln -sfn ~/Developer/video-use ~/.claude/skills/video-use && cd ~/Developer/video-use && uv sync (README 'Manual install'; needs ffmpeg and ELEVENLABS_API_KEY in .env)
Sources: github.comraw.githubusercontent.comdescript.com

Compare before you switch

Read the checked comparisons and workload guides for the tools this recipe replaces.

More Video recording recipes

All 139 recipes · Savings leaderboard · Every vendor, with prices and cancel steps