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

# Fluen Studio API Reference

The Fluen Studio API transcribes and translates audio and video and manages the resulting caption tracks, so an application can caption and localise media without running its own speech and translation pipeline. You create media by uploading a file or pointing at a URL, attach transcription and translation job specifications, or import existing SRT subtitles for translation without any upload. Finished caption tracks can be exported in a chosen format, re-imported after outside correction, or burned into a video, and webhook endpoints notify your systems as jobs complete.

## For AI agents

Upload audio or video for transcription and translation, import and export subtitle tracks, burn captions into video, and manage a term base in Fluen Studio. Authenticates with an API key in the X-API-Key header.

## Scope

Does not host or stream video, generate voiceovers, or edit footage. Use for transcription, translation, and caption-track management only.

## Capabilities

- Create media by uploading a file or pointing at a URL with transcription and translation specs
- Import existing SRT subtitles for translation without uploading any media
- Export a caption track in a chosen format or re-import a corrected version
- Burn a caption track into a video and fetch the download link
- Maintain a workspace term base to keep translations of key terms consistent
- Register webhook endpoints and inspect recent deliveries for job events

## Use cases

### Agent-Driven Media Localization

An AI agent connected through Jentic localises a video end to end: it creates media from the source, requests a transcription and the target-language translations, then exports or burns in the finished captions, so a team ships subtitled video without a manual captioning tool. Because Fluen keeps each language as a track, the agent can add a language later without redoing the transcription.

Example prompt: Create media from this video URL, request an English transcription and French and German translations, then export each track as SRT

### Subtitle Translation Without Upload

A workflow that already has SRT files translates them without re-uploading media by importing the subtitles and requesting translations, so an archive of existing captions is localised quickly. Corrected subtitles can be re-imported into an existing track to replace its content and optionally restart the translations in one call.

Example prompt: Import this SRT file, translate it into Japanese, and re-import the corrected version into the existing track

### Consistent Terminology Across Languages

A localisation team keeps brand and product terms consistent across every translation by maintaining a workspace term base, adding terms in bulk and exporting it for review, so the same phrase renders the same way in each language. The term base applies to the workspace's translation jobs, so new media inherits the agreed terminology.

Example prompt: Bulk-add our product terms to the workspace term base so every new translation uses the approved wording

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/media` | Create media with transcription and translation specs |
| POST | `/api/media/from-captions` | Create media from imported captions (SRT) |
| GET | `/api/media/{mediaId}` | Read a media item |
| GET | `/api/tracks/{trackId}` | Read a caption track |
| GET | `/api/tracks/{trackId}/export/{format}` | Export a caption track in a format |
| POST | `/api/tracks/{trackId}/import` | Import and replace track content |
| POST | `/api/tracks/{trackId}/burnin/{videoFormat}` | Burn a caption track into a video |
| POST | `/api/webhook-endpoints` | Register a webhook endpoint |

## Key resources

- **Media** — Uploaded or URL-sourced audio and video with transcription and translation job specs
- **Tracks** — Caption tracks that can be exported, imported, and burned into video
- **Term Base** — Per-workspace glossary that keeps translations of key terms consistent
- **Webhook Endpoints** — Registered endpoints notified as transcription and translation jobs complete

## 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:** 57 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 47 / 100
  - Developer Experience & Jentic Compatibility: 55 / 100
  - AI-Readiness & Agent Experience: 48 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 81 / 100
- **View full report:** https://jentic.com/apis/fluen.ai/fluen/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 the Fluen Studio API by hand means handling X-API-Key auth, picking between uploading media and creating it from a URL or captions, and tracking each transcription and translation job to completion. Through Jentic you install once, import Fluen from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** You choose which operations your agent may call, so you can allow creating media and exporting tracks while leaving destructive ones like deleting media or clearing the term base out. Rules bound which operations run, so the agent captions and translates and cannot reach anything you did not grant.
- **Credential handling:** Your Fluen 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 and translate a video' or 'export a caption track', and Jentic returns the matching Fluen operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **AssemblyAI API** — Speech-to-text API with transcription, summarization, and audio intelligence
- **Deepgram API** — Speech recognition API for fast, accurate transcription of audio and video
- **api.video API** — Video hosting, encoding, and delivery platform

## FAQ

### Is there a Fluen MCP server?

You don't need an MCP server to give your agent the Fluen Studio API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent can transcribe, translate, and export caption tracks straight away, with no extra server to run and no tool definitions sitting in the agent's context.

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

Yes. Write a rule that allows only the operations the agent needs, such as creating media and exporting tracks, and leave deletions out. Every call the agent makes is logged, so you can see exactly which media and tracks it created.

### What authentication does the Fluen Studio API use?

The Fluen Studio API authenticates with an API key sent in the X-API-Key header per its OpenAPI spec. Through Jentic the key is stored encrypted by your own instance and added to each request at call time, so it never appears in the agent's prompt or logs.

### Can I translate subtitles without uploading media to the Fluen Studio API?

Yes. One operation creates media directly from captions, so you can import an existing SRT file and request translations without uploading any audio or video. A separate operation re-imports a corrected track to replace its content and optionally restart the translations.

### What are the rate limits for the Fluen Studio API?

The OpenAPI spec does not state request rate limits for the Fluen Studio API. For current limits and fair-use guidance, check the provider documentation at https://api.fluen.ai.

### How do I caption a video through Jentic?

Import the Fluen Studio API from the Jentic API Directory, then have your agent issue a request such as 'transcribe and translate this video'. Jentic matches the intent to the create-media operation and returns its input schema so the agent builds the correct request, with your stored key injected at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.