Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Who's it for This template is designed for content creators, podcasters, businesses, and researchers who need to transcribe long audio recordings that exceed OpenAI Whisper's 25 MB file size limit ...

Best for

Content Creation automation workflows
Multimodal AI automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.formtrigger, n8n-nodes-base.code, n8n-nodes-base.httprequest, n8n-nodes-base.noop, n8n-nodes-base.if, n8n-nodes-base.wait, n8n-nodes-base.splitinbatches, @n8n/n8n-nodes-langchain.openai

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Julien DEL RIO.

Original n8n.io source

1.1 Workflow description

Title: Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper
Workflow name: Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper

Who's it for

This template is designed for content creators, podcasters, businesses, and researchers who need to transcribe long audio recordings that exceed OpenAI Whisper's 25 MB file size limit (~20 minutes of audio).

How it works

This workflow combines n8n, FileFlows, and OpenAI Whisper API to transcribe audio files of any length:

User uploads an MP3 file through a web form and provides an email address
n8n splits the file into 4 MiB chunks and uploads them to FileFlows
FileFlows uses FFmpeg to segment the audio into 15-minute chunks (safely under the 25 MB API limit)
Each segment is transcribed using OpenAI's Whisper API (configured for French by default)
All transcriptions are merged into a single text file
The complete transcription is automatically emailed to the user

Processing time: Typically 10-15 minutes for a 1-hour audio file.

Requirements

n8n instance (self-hosted or cloud)
FileFlows with Docker and FFmpeg installed
OpenAI API key (Whisper API access)
Gmail account for email delivery
Network access between n8n and FileFlows

Setup

Complete setup instructions, including FileFlows workflow import, credentials configuration, and storage setup, are provided in the workflow's sticky notes.

Cost

OpenAI Whisper API: $0.006 per minute. A 1-hour recording costs approximately $0.36.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - GET Form

Type / Role: n8n-nodes-base.formTrigger - formTrigger
Config choices: Version 2.3

Block 2 - Make 4MiB Chunks

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 3 - Upload Chunk

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 4 - Result

Type / Role: n8n-nodes-base.noOp - noOp
Config choices: Version 1

Block 5 - If succeed

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 6 - Split audio file

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 7 - Wait

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 8 - Split Audio

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 9 - Loop Over Segments

Type / Role: n8n-nodes-base.splitInBatches - splitInBatches
Config choices: Version 3

Block 10 - OpenAI

Type / Role: @n8n/n8n-nodes-langchain.openAi - openAi
Config choices: Version 1.8

Block 11 - Result transcription

Type / Role: n8n-nodes-base.noOp - noOp
Config choices: Version 1

Block 12 - Loop Over Chunks

Type / Role: n8n-nodes-base.splitInBatches - splitInBatches
Config choices: Version 3

Block 13 - Merge transcription

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 14 - Convert to File

Type / Role: n8n-nodes-base.convertToFile - convertToFile
Config choices: Version 1.1

Block 15 - Configuration

Type / Role: n8n-nodes-base.set - set
Config choices: Version 3.4

Block 16 - Filter temporary files

Type / Role: n8n-nodes-base.filter - filter
Config choices: Version 2.2

Block 17 - Rate Limit Delay

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 18 - Send Email with Transcription

Type / Role: n8n-nodes-base.gmail - gmail
Config choices: Version 2.1

Block 19 - Send Error

Type / Role: n8n-nodes-base.gmail - gmail
Config choices: Version 2.1

Block 20 - Send Error1

Type / Role: n8n-nodes-base.gmail - gmail
Config choices: Version 2.1

Block 21 - Chunk

Type / Role: n8n-nodes-base.noOp - noOp
Config choices: Version 1

Block 22 - Segment

Type / Role: n8n-nodes-base.noOp - noOp
Config choices: Version 1

Block 23 - Overview

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 24 - Stage 4 Delivery

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Showing the first 24 of 27 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow	Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper
Complexity	advanced
Nodes	27
Categories	Content Creation, Multimodal AI
Author	Julien DEL RIO
Published	15 Nov 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/10870/10870.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Content Creation workflows Multimodal AI workflows

Frequently asked questions

What does Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Content Creation, Multimodal AI use case.

Julien DEL RIO

3 workflows

Nodes

n8n-nodes-base.formtrigger n8n-nodes-base.code n8n-nodes-base.httprequest n8n-nodes-base.noop n8n-nodes-base.if n8n-nodes-base.wait n8n-nodes-base.splitinbatches @n8n/n8n-nodes-langchain.openai

Complexity

advanced

Published 15 Nov 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/10870/10870.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Send daily LinkedIn post drafts with Tavily, Groq Llama 3.3 and Gmail

## Quick overview This workflow runs daily at 8 AM to rotate through a topic list, research it with Tavily web search, generate a LinkedIn post and image prompt with Groq (Llama 3.3 70B), create a Pollinations.ai image URL, and email you the post with the image attached via Gmail. ## How it works 1. Runs every day at 8:00 AM on a schedule. 2. Selects today’s topic from a rotating list based on the day of the year. 3. Searches the web with Tavily to fetch up-to-date results for the selected topic. 4. Uses a Groq-hosted Llama model to write a LinkedIn post and a matching image prompt grounded in the Tavily results. 5. Builds a Pollinations.ai image generation URL from the image prompt and downloads the generated image file. 6. Emails the post text with the image attached via Gmail, and sends a text-only fallback email if image generation or download fails. ## Setup 1. Add a Groq API credential to the Groq Chat Model node. 2. Create a Tavily API key and configure HTTP Header Auth with `Authorization: Bearer <YOUR_TAVILY_KEY>` for the Tavily Search request. 3. Connect a Gmail OAuth2 credential and update the recipient email address in both Gmail send steps. 4. Edit the topic list in the topic-selection code step if you want different rotating themes. ## Requirements - Groq API key (free tier available) - Tavily API key (free tier — 1,000 searches/month) - Gmail account (OAuth2) ## Customization - Edit the topic list inside the "Pick Today's Topic" code node to change what subjects the post rotates through. - Change the Groq model in the "Groq Chat Model" node if you want a different LLM (e.g. a smaller/faster or larger Groq model). - Adjust the schedule trigger if you want a different posting time, or swap the Gmail "send to" address to deliver the draft to someone else for review. ## Additional info This workflow emails you a draft for manual review before posting — it does not post to LinkedIn automatically. If image generation fails, a text-only fallback email is sent instead so you never miss the post text.

View

Generate VEO3 videos from form ideas with ChatGPT, fal.ai, Drive and Gmail

## Quick overview This workflow collects a video idea via an n8n Form, uses OpenAI to turn it into an optimized prompt, generates an 8-second VEO3 video with native audio via fal.ai, saves the MP4 to Google Drive, and emails the Drive link via Gmail. ## How it works 1. Receives a submission from an n8n Form with the requester’s email, a plain-English video idea, and a selected style. 2. Uses OpenAI (via an AI Agent) to convert the idea and style into a structured VEO3 title and detailed prompt returned as JSON. 3. Cleans and parses the AI JSON, creates a filename-safe title, and sets the generation parameters to 16:9 and 8 seconds. 4. Submits the prompt to fal.ai’s queue endpoint for the fal-ai/veo3 model and gets a request ID. 5. Polls fal.ai every 30 seconds until the job status returns COMPLETED. 6. Retrieves the final MP4 URL from fal.ai, downloads the video, uploads it to Google Drive, and emails the Google Drive web link to the requester via Gmail. ## Setup 1. Create a fal.ai account, generate an API key, and replace `YOUR_FAL_AI_API_KEY` in the fal.ai HTTP request headers. 2. Add an OpenAI API credential in the OpenAI Chat Model node and select the model you want to use. 3. Connect Google Drive OAuth2 and replace `YOUR_GDRIVE_FOLDER_ID` with the target folder ID where videos should be saved. 4. Connect Gmail OAuth2 for sending emails, then activate the workflow and use the Form URL (path `veo3-video-generator`) to submit requests.

View

Generate presentation decks from prompts with Encelade

## Quick overview This workflow starts a presentation generation job in Encelade from a prompt and outline hints, polls Encelade for completion, and outputs the finished deck link (or stops with an error if generation fails). ## How it works 1. Starts when you manually execute the workflow in n8n. 2. Sends the topic, slide count, audience, tone, theme settings, and outline hints to Encelade to generate a 6-slide presentation. 3. Waits 20 seconds and then checks the Encelade session status using the returned session ID. 4. If the session phase is not finished, it keeps waiting and rechecking until the phase changes. 5. When the phase is "done", it returns the generated deck link and project PID. 6. When the phase is "failed", it stops the workflow and raises an error with the failure details. ## Setup 1. Install and configure Encelade credentials in n8n for the Encelade node. 2. Update the generation inputs (topic, page count, outline hints, audience/tone, theme mode, and media provider) to match the deck you want to create. 3. Ensure the workflow has enough time to complete by adjusting the 20-second wait interval if your Encelade generations typically take longer.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Transcribe long audio files beyond 25MB limit with FileFlows and OpenAI Whisper

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Who's it for

How it works

Requirements

Setup

Cost

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - GET Form

Block 2 - Make 4MiB Chunks

Block 3 - Upload Chunk

Block 4 - Result

Block 5 - If succeed

Block 6 - Split audio file

Block 7 - Wait

Block 8 - Split Audio

Block 9 - Loop Over Segments

Block 10 - OpenAI

Block 11 - Result transcription

Block 12 - Loop Over Chunks

Block 13 - Merge transcription

Block 14 - Convert to File

Block 15 - Configuration

Block 16 - Filter temporary files

Block 17 - Rate Limit Delay

Block 18 - Send Email with Transcription

Block 19 - Send Error

Block 20 - Send Error1

Block 21 - Chunk

Block 22 - Segment

Block 23 - Overview

Block 24 - Stage 4 Delivery

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions