You are helping me build the following AI agent workflow.

## Goal
Audio Video Transcription: Upload audio or video files and get structured text transcriptions in 99+ languages via ElevenLabs Scribe.

## Specification
- What it does: Upload your audio or video files to instantly get structured transcriptions in over 99 languages using ElevenLabs Scribe. This process handles the file upload and API processing automatically so you can export ready-to-use text for tasks like creating subtitles, podcasts, or SEO content with high accuracy.
- Trigger: Triggered by an event (Manual · on file upload)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - n8n: Workflow orchestration
  - ElevenLabs Scribe API: Speech to text transcription

## Known pitfalls, handle each one explicitly in your implementation
1. Large video files may exceed HTTP payload limits so you must implement chunking or use a direct file upload method supported by the API.
2. Sensitive legal content might be processed by third-party servers so ensure you have explicit user consent before uploading confidential materials.
3. Audio quality issues like heavy background noise reduce transcription accuracy so add a preprocessing step to filter out static or silence.

## Reference implementation
https://n8n.io/workflows/3105 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/automate-audio-video-transcription/ via usecasesforagents.com