# ChatGPT Transcription control

**URL:** <https://community.n8n.io/t/chatgpt-transcription-control/90495>\
**Category:** Questions\
**Created:** [March 20, 2025, 6:23am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495 "2025-03-20T06:23:36Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![cmarston1500](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/cmarston1500/32/59691_2.png) [@cmarston1500](https://community.n8n.io/u/cmarston1500)\
**Post date:** [March 20, 2025, 6:23am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495/1 "2025-03-20T06:23:36Z")

</div>

## Describe the problem/error/question

Hi, I want to pass an audio recording for transcription. I have the process of picking up a file from Dropbox and transcribing it working, but I need to control the prompt passed to ChatGPT so it understands how to handle the audio file. I need to use the stereo file and have the conversation broken out into separate speakers (2 in total). I need to timestamp the conversation so I can build it into a chat flow so it can be visually followed.

Any guidance is appreciated.

## What is the error message (if any)?

## Please share your workflow

 ![image](https://europe1.discourse-cdn.com/n8n/original/3X/d/1/d117cd659bbbfc12bfb8bf73f3f5bf3a893f51c4.png)

```auto
(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

```

## Share the output returned by the last node

## Information on your n8n setup

- **n8n version:**
- Hosted
- **Database (default: SQLite):**
- No DB
- **n8n EXECUTIONS\_PROCESS setting (default: own, main):**
- **Running n8n via (Docker, npm, n8n cloud, desktop app):**
- **Operating system:**

---

<div class="post-metadata">

**Author:** ![jksr](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/jksr/32/132705_2.png) [@jksr](https://community.n8n.io/u/jksr)\
**Post date:** [March 20, 2025, 7:39am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495/2 "2025-03-20T07:39:28Z")

</div>

What you are looking for is called diarization and afaik OpenAI Whisper does not support diarization out of the box. I have used this model on replicate before for podcast transcription and speaker labelling: [thomasmol/whisper-diarization – Run with an API on Replicate](https://replicate.com/thomasmol/whisper-diarization). You would have to connect it via HTTP, but it works pretty well. Hope this helps.

---

<div class="post-metadata">

**Author:** ![cmarston1500](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/cmarston1500/32/59691_2.png) [@cmarston1500](https://community.n8n.io/u/cmarston1500)\
**Post date:** [March 20, 2025, 9:51am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495/3 "2025-03-20T09:51:15Z")

</div>

Much appreciated. I will take a look.

---

<div class="post-metadata">

**Author:** ![cmarston1500](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/cmarston1500/32/59691_2.png) [@cmarston1500](https://community.n8n.io/u/cmarston1500)\
**Post date:** [March 28, 2025, 6:45am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495/4 "2025-03-28T06:45:35Z")

</div>

I am still investigating, but this seemed like a great suggestion.

---

<div class="post-metadata">

**Author:** ![system](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/system/32/195824_2.png) [@system](https://community.n8n.io/u/system)\
**Post date:** [April 4, 2025, 6:46am UTC](https://community.n8n.io/t/chatgpt-transcription-control/90495/5 "2025-04-04T06:46:15Z")

</div>

Closed on April 4, 2025, 6:46am UTC

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.