Create and add an OpenAI API key

Prerequisites

• An OpenAI Platform account at platform.openai.com. This is separate from a ChatGPT account even when you sign in with the same email.
• A payment method or prepaid credits on the Platform account.

A ChatGPT Plus, Pro, or Team subscription does not fund API usage. API billing is entirely separate. This is the single most common reason a valid-looking key fails.

Steps

1. Open the OpenAI API keys page and sign in.
2. Create a new secret key and copy it immediately. OpenAI shows the full value only once; if you lose it, create another.
3. Set up API billing on the Platform account — add a payment method or prepaid credits. OpenAI's prepaid billing guide covers the current flow.
4. In RoughCut, open Settings. On the Basic tab (or Full → LLM) find OpenAI API key, paste the value, and click Save. RoughCut confirms it was saved to the Keychain.
5. For AI editing on OpenAI: set LLM provider to openai. Long transcripts are split into overlapping chunks and merged back automatically, so long videos work.
6. For Cloud transcription (Pro): leave the provider wherever you like and instead choose ✦ Cloud (OpenAI) in the Transcription control on a job. The two settings are independent.
7. Test with a short clip before committing a long recording.

Expected result

The OpenAI API key field shows a green confirmation with the value masked. Depending on what you set up, either the editing pass runs on OpenAI, or Cloud transcription becomes available on jobs.

Cloud transcription needs whisper-1

Cloud transcription sends the job's audio to OpenAI's transcription endpoint and requires word-level timestamps, because RoughCut's cut plan and SRT export are both built from word times.

As of the current release, only whisper-1 returns them. Newer transcription models do not, and RoughCut fails loudly rather than producing a broken cut:

OpenAI model '<model>' returned a transcript without word timestamps, which the cut
pipeline and SRT export require. Per OpenAI's docs only 'whisper-1' supports word
timestamps — set Settings → Full → Transcription → OpenAI transcription model to 'whisper-1'.

Leave OpenAI transcription model at whisper-1 unless you have confirmed a newer model returns word timestamps.

What is sent, and when

Your video is never uploaded in any of these paths. Cloud transcription sends audio only, split at silence boundaries so chunks never break mid-sentence. Full detail in Privacy and data flow.

Common mistakes

• Funding ChatGPT instead of the API. They are different balances.
• Losing the key. The full value is shown once. Create a new one rather than hunting for it.
• Changing the transcription model. Anything other than whisper-1 currently fails the job at the timestamp check.
• Assuming Cloud transcription works without Pro. It is a Pro feature and needs your own key — both are required.

Troubleshooting