Marketing ops · Production

Cloudinary makes video production 70% faster with Descript's AI-powered editing

The problem

Cloudinary's Customer Education team spent excessive time on video editing due to inaccurate transcription of technical terminology, tedious filler-word removal, and inconsistent audio quality from remotely recorded experts, slowing production to a crawl.

First attempt

Neither human nor AI transcription services could accurately handle Cloudinary's domain-specific vocabulary, including technical terms, proprietary lingo, and acronyms, especially from non-native English speakers, and correcting the resulting errors took hours.

Workflow diagram · grounded in source
1
Expert records live session
trigger
“Cloudinary's in-house experts often recorded their training sessions live, then handed them off to the Customer Education team to edit for publication”
2
AI transcription with glossary
ai_action
“The Cloudinary team uses Descript's transcription glossary feature to teach the AI those especially tricky terms, so when it hears "JSON," Descript transcribes it that way, not as "Jason." Descript's AI transcription also learns and gets…”
3
Collaborative transcript correction
human_review
“Cloudinary's editor can invite multiple editors to every video project, so experts can quickly scrub inaccuracies using Descript's effortless transcript-correction tool. All the changes happen in the cloud, so editors can work simultaneo…”
4
Automatic filler-word removal
ai_action
“Descript's automatic filler-word detection and removal enabled Cloudinary's editors to remove every unwanted filler word from the transcript in a few clicks. Same for any excessive filler words in the video. Descript also adds room tone …”
5
Studio Sound audio enhancement
ai_action
“It uses AI voice re-generation to strip out background noise, reverb and other stuff you don't want, then re-construct the voice audio so it sounds like it was recorded in a studio.”
6
Publish video at higher frequency
output
“go from one podcast episode every few months to two episodes a month with the same team, at the same cost”
Reported outcome

Cloudinary reduced video production time by 70%—from 13 hours per episode to 4 hours—and increased podcast output from one episode every few months to two per month, at the same cost with the same team.

Reported metrics
Video production speed improvement70% faster
Podcast episode output frequencytwo episodes a month, up from one every few months
Audio qualitycrystal-clear audio even when experts have bad mics or setups
Potential video output increase (general platform claim)2.5x more video output
Reported stack
DescriptStudio Soundtranscription glossary
Source
https://www.descript.com/customers/cloudinary
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Cloudinary reduced video production time by 70%—from 13 hours per episode to 4 hours—and increased podcast output from one episode every few months to two per month, at the same cost with the same team.

What tools did this team use?

Descript, Studio Sound, transcription glossary.

What results were reported?

Video production speed improvement: 70% faster; Podcast episode output frequency: two episodes a month, up from one every few months; Audio quality: crystal-clear audio even when experts have bad mics or setups; Potential video output increase (general platform claim): 2.5x more video output (source-reported, not independently verified).

What failed first in this deployment?

Neither human nor AI transcription services could accurately handle Cloudinary's domain-specific vocabulary, including technical terms, proprietary lingo, and acronyms, especially from non-native English speakers, and…

How is this marketing ops AI workflow structured?

Expert records live session → AI transcription with glossary → Collaborative transcript correction → Automatic filler-word removal → Studio Sound audio enhancement → Publish video at higher frequency.

Related marketing ops cases