711
Prompt

Transcript Cleaner Prompt

Turn a raw ASR transcript into readable prose.

1 min readupdated 2026-07-04

/ quick answer

First step after Whisper/Deepgram before any downstream generation. Turn a raw ASR transcript into readable prose.

Turn a raw ASR transcript into readable prose. First step after Whisper/Deepgram before any downstream generation. Copy the prompt below, swap the bracketed variables for your own context, and run it in any capable model.
Context
First step after Whisper/Deepgram before any downstream generation.
Prompt
Clean the transcript. Rules:
- Fix punctuation and casing.
- Remove filler words (um, like, you know).
- Keep every substantive word.
- Do NOT paraphrase. Do NOT summarize.
- Preserve speaker labels if present.

Transcript:
{{transcript}}
Example Output
[clean prose version of the raw transcript]
Related Workflow

/ frequently asked

What does the Transcript Cleaner Prompt prompt do?

First step after Whisper/Deepgram before any downstream generation.

Which AI models work with this prompt?

It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.

How do I use this prompt?

1) Copy the prompt with the copy button. 2) Replace every bracketed variable with your real details. 3) Paste it into your AI assistant. 4) Compare the answer with the example output and ask for changes if needed.

What output should I expect?

[clean prose version of the raw transcript].

/ continue exploring

Related concepts

The vocabulary this page depends on.

all dictionary →

Related workflows

Turn this into a repeatable process.

all workflows →

Related tool stacks

The tools that run it in production.

all tool stacks →

Related prompts

Reusable prompts for this job.

all prompts →