canonical: https://jentic.com/apis/justtranscribe.ai/justtranscribe

# JustTranscribe API

The JustTranscribe API turns public videos and audio into timestamped text from a link. It accepts public URLs from YouTube, TikTok, Instagram, Facebook, Pinterest, and Google Drive for media up to 150 minutes long, starts the job asynchronously, and lets you poll the transcript until its status is complete or receive a webhook. Finished transcripts export as txt, srt, vtt, csv, or md, with options to drop timestamps or add speaker labels, and you can list past transcripts or delete one permanently.

## For AI agents

Transcribe a public YouTube, TikTok, Instagram, Facebook, Pinterest, or Google Drive video into timestamped text, poll until it is complete, and export it as txt, srt, vtt, csv, or md.

## Scope

Does not handle private or login-required videos, live streaming transcription, or translation. Use for transcribing public video and audio links and exporting the text only.

## Capabilities

- Start transcribing a public video or audio URL up to 150 minutes long, with an optional webhookUrl for completion
- Poll a transcript by id as its status moves through stages such as queued, transcribing, and complete
- Export a finished transcript as txt, srt, vtt, csv, or md, dropping timestamps with ts=0 or adding speaker labels with sp=1
- List past transcripts newest first, filtered by status and sorted by createdAt or completedAt
- Include the plain transcript text in list results with include=text
- Permanently delete a transcript by id

## Use cases

### Video Research Through Jentic

An AI agent asked to summarise a public talk starts a JustTranscribe job from the video link, polls the transcript until its status is complete, and reads the text to write the summary. Through Jentic the agent finds the create and get operations by intent and calls them with your API key, which stays on your own machine.

Example prompt: Create a transcript for a public YouTube URL, poll GET `/api/v1/transcripts/{id}` until status is 'complete', then summarise the text in five bullet points

### Subtitle Files for Short-Form Video

A creator repurposing TikTok and Instagram clips needs caption files. The agent transcribes each public link and exports the result as srt or vtt, ready to upload with the video, or as csv when the creator wants to edit segments in a spreadsheet.

Example prompt: Transcribe a public TikTok URL and, once complete, export it with format 'srt' and also as 'vtt'

### Content Notes Without Timestamps

A writer turning podcasts and webinars into articles wants clean prose. The agent exports each finished transcript as md with ts=0 to drop timestamps, adding sp=1 when cached speaker labels help attribute quotes.

Example prompt: Export a completed transcript with format 'md', ts '0', and sp '1', then draft an article outline from it

### Webhook-Driven Transcription Queue

An app that transcribes many links passes a webhookUrl when creating each transcript, then lists finished jobs sorted by completedAt to pick up anything a webhook missed. This keeps a backlog moving without polling every job individually.

Example prompt: Create transcripts for three public Google Drive video links with a webhookUrl, then list transcripts with status 'complete', sort 'completedAt', and include 'text'

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/v1/transcripts` | Start transcribing a public URL |
| GET | `/api/v1/transcripts/{id}` | Get a transcript and its status |
| GET | `/api/v1/transcripts/{id}/export/{format}` | Export as txt, srt, vtt, csv, or md |
| GET | `/api/v1/transcripts` | List transcripts |
| DELETE | `/api/v1/transcripts/{id}` | Delete a transcript |

## Key resources

- **Transcripts** — Asynchronous transcription jobs from public media URLs: create, poll, list, export, and delete.
- **Account** — The account identified by the API key.

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 63 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 100 / 100
  - Developer Experience & Jentic Compatibility: 56 / 100
  - AI-Readiness & Agent Experience: 45 / 100
  - Agent Usability: 94 / 100
  - Security: 60 / 100
  - AI Discoverability: 67 / 100
- **View full report:** https://jentic.com/apis/justtranscribe.ai/justtranscribe/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring JustTranscribe by hand means handling its bearer key, the asynchronous create-then-poll flow through statuses like transcribing and complete, and picking export formats and flags. Through Jentic you install once, import the JustTranscribe API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** JustTranscribe puts the transcript id in the URL path (`/api/v1/transcripts/{id}`), so a rule can bound your agent to one transcript and the operations you pick. You choose the operations it may call, so the permanent delete operation is not included unless you add it.
- **Credential handling:** Your JustTranscribe API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'transcribe a YouTube video' or 'export subtitles as srt', and Jentic returns the matching JustTranscribe operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **AssemblyAI** — AssemblyAI transcribes audio files you host with speech models and audio intelligence features; JustTranscribe works from public social and Drive links.
- **Deepgram** — Deepgram offers speech-to-text for prerecorded and streaming audio.
- **OpenAI** — OpenAI models can summarise, translate, or extract notes from a finished JustTranscribe transcript.
- **Notion API** — Notion stores exported md transcripts as pages for notes and research.

## FAQ

### What authentication does the JustTranscribe API use?

Per its OpenAPI spec, the JustTranscribe API uses bearer authentication with an API key starting with jt_live_, created on the JustTranscribe API keys page and sent in the Authorization header. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's context.

### Is there a JustTranscribe MCP server?

You don't need an MCP server to give your agent the JustTranscribe API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls it, finding the create, poll, and export operations on demand instead of loading a server's tool definitions into its context.

### Can I limit what my agent is allowed to do with the JustTranscribe API?

Yes. Write a rule that allows only the create, get, and export operations, so the agent can transcribe and read results but cannot delete anything, and every call it makes is logged. Because the transcript id sits in the URL path, a rule can also pin an agent to one transcript under `/api/v1/transcripts/{id}.`

### Which videos can the JustTranscribe API transcribe?

Per the spec, public links only from YouTube, TikTok, Instagram, Facebook, Pinterest, and Google Drive, up to 150 minutes long. Private or login-required videos are not supported. POST `/api/v1/transcripts` returns immediately with an id that you poll until status is complete.

### What are the rate limits for the JustTranscribe API?

The OpenAPI spec does not specify rate limits. Check https://justtranscribe.ai/developers for current limits and plan details.

### How do I transcribe a YouTube video with the JustTranscribe API through Jentic?

Search Jentic for an intent like 'transcribe a YouTube video', import the JustTranscribe API from the API Directory, and store your API key. Your agent calls POST `/api/v1/transcripts` with the url, polls GET `/api/v1/transcripts/{id}` until it is complete, then calls the export endpoint with a format such as srt. To run it on your own infrastructure, install Jentic One from its GitHub repo.