How to Use X (Twitter) video transcript in Gemini CLI
Get AI-generated transcript text and a success flag from a video attached to an X post. Use it to summarize spoken announcements, extract claims, or compare interview clips; it transcribes speech rather than retrieving native captions.
Prompts to try with X (Twitter) video transcript in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use X (Twitter) video transcript for https://x.com/OpenAI/status/1790089500246323309 and add the returned text and source URL to my project's research collection.
Use X (Twitter) video transcript for https://x.com/TheoVon/status/1916982720317821050 and create a Markdown research note containing the interview questions and summarized answers.
Use X (Twitter) video transcript for https://x.com/OpenAI/status/1790089500246323309 and add a searchable transcript entry to the existing video research interface.
Use X (Twitter) video transcript for https://x.com/TheoVon/status/1916982720317821050 and write a CSV of factual claims, supporting transcript passages, and the source URL.
Use X (Twitter) video transcript for https://x.com/OpenAI/status/1790089500246323309 and compare the spoken product descriptions with the claims in our project's demo notes.
How to set up X (Twitter) video transcript in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run X (Twitter) video transcript
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "scrapecreators", "model": "scrapecreators/twitter-tweet-transcript", "input": { "url": "https://x.com/TheoVon/status/1916982720317821050" } }'
Then paste one of the prompts above: Gemini CLI finds X (Twitter) video transcript on Spiral, shows the price and runs it.
X (Twitter) video transcript providers and prices
Spiral runs X (Twitter) video transcript through ScrapeCreators. Open a card for today's price, with every fee included.
Settings you can ask for
Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Cache max age | 1d, 3d, 7d, 14d, or 30d | If we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (Returned native captions cost 1 credit, even for long videos with the paid flag. By default, successful AI up to 120 seconds costs a flat 1 credit per request; over 120 seconds requires allow_long_transcription=true, which bills ALL successful AI at 10 credits per started minute, including short videos; empty AI results and errors cost 0 credits; no transcript: 0 credits). See the Caching page for details. |
Every API field of X (Twitter) · Transcript is on its tool page: open its card above.
What can you do with X (Twitter) video transcript in Gemini CLI?
Build a searchable transcript collection from selected public X video posts. A coding agent can connect the returned speech text to your project's research notes, claim tables, or search interface.
Summarize spoken announcements
Turn the transcript of a public company's X video into a brief covering the announcement, supporting statements, and unanswered questions.
Build a claim review queue
Extract factual claims from public interview clips and link each claim to its source post for editorial verification.
Compare product messaging
Compare transcripts from selected public product demos to identify differences in promised benefits, examples, and calls to action.
Make video research searchable
Index transcript text from selected public X videos so researchers can find spoken references to products or topics.
Draft an interview brief
Use a public creator's interview clip to list the questions asked, summarize the answers, and suggest follow-up questions.
Prepare content for adaptation
Turn an owned or authorized X video transcript into a newsletter outline, FAQ draft, or short written recap.
More on X (Twitter) video transcript and Gemini CLI
X (Twitter) video transcript in other agents
Questions about X (Twitter) video transcript in Gemini CLI
Can Gemini CLI use X (Twitter) video transcript?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run X (Twitter) video transcript like any built-in tool.
How much does X (Twitter) video transcript cost in Gemini CLI?
Up to $0.0013 per run. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need a ScrapeCreators account to use X (Twitter) video transcript in Gemini CLI?
No. Spiral runs X (Twitter) video transcript on its own ScrapeCreators account. You sign in to Spiral once and never paste a key.
How long does it take to set up X (Twitter) video transcript in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while X (Twitter) video transcript runs?
X (Twitter) video transcript runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.
Does this return X's captions or generate a transcript?
It generates an AI transcript from a video tweet. The endpoint documentation explicitly distinguishes this from native captions and specifies transcript text plus a success flag.
How long can the video be?
The default transcription limit is 120 seconds. The documentation also warns that long videos may time out, so a full interview or broadcast is a less dependable target than a short clip.
What content does this cover?
The target is a video attached to an X post. ScrapeCreators describes its source data as publicly available; this is not documented access to private messages or protected content.
Is the source data fetched live?
ScrapeCreators says cache misses fetch publicly available data directly from the source. A cached response therefore should not be described as a fresh retrieval.
Start using X (Twitter) video transcript in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


