---
title: "Insights"
method: GET
path: "/media/insight/{mediaId}"
tags: ["Media (Audio/Video)"]
---

# Insights

`GET /media/insight/{mediaId}`

## Request

- Base URL: `https://api.speakai.co/v1`
- URL: `https://api.speakai.co/v1/media/insight/{mediaId}`
- Auth: API key in header `x-speakai-key` and API key in header `x-access-token`

Load the results of analysis (sentiment, transcription, named entities, etc) for your media object here.

- You can pass `userId` in `params` to get specifically for any user.

## Path parameters

- `mediaId` string, required

## Response `200`

OK

- object
  - `status` string
  - `data` object
    - `insight` object
      - `isAnalyze` boolean
      - `transcript` object[]
        - `id` integer
        - `text` string
        - `confidence` number
        - `speakerId` integer
        - `language` string
        - `instances` object[]
          - `adjustedStart` string
          - `adjustedEnd` string
          - `start` string
          - `end` string
      - `faces` unknown[]
        - unknown
      - `keywords` object[]
        - `isDeleted` boolean
        - `instances` object[]
          - `adjustedStart` string
          - `adjustedEnd` string
          - `start` string
          - `end` string
        - `id` integer
        - `name` string
      - `labels` unknown[]
        - unknown
      - `brands` unknown[]
        - unknown
      - `topics` object[]
        - `isDeleted` boolean
        - `instances` object[]
          - `adjustedStart` string
          - `adjustedEnd` string
          - `start` string
          - `end` string
        - `id` integer
        - `name` string
      - `people` unknown[]
        - unknown
      - `locations` unknown[]
        - unknown
      - `arts` unknown[]
        - unknown
      - `dates` unknown[]
        - unknown
      - `events` unknown[]
        - unknown
      - `geopolitical` unknown[]
        - unknown
      - `languages` unknown[]
        - unknown
      - `laws` unknown[]
        - unknown
      - `money` unknown[]
        - unknown
      - `ordinals` unknown[]
        - unknown
      - `percentages` unknown[]
        - unknown
      - `quantities` unknown[]
        - unknown
      - `times` unknown[]
        - unknown
      - `cardinals` unknown[]
        - unknown
      - `nationalities` unknown[]
        - unknown
      - `products` unknown[]
        - unknown
    - `duration` object
      - `inSecond` string
      - `end` string
      - `start` string
    - `summary` object
      - `original` object
        - `text` string
        - `createdAt` string, date-time
    - `tags` unknown[]
      - unknown
    - `translationSource` object: Present only on a file Speak AI created by translating another one. It says whether the original source-language transcript can be read, so a client can offer the control without fetching the transcript. Fetch the transcript itself from GET /media/transcript/{mediaId}/source, which documents every reason value.
      - `available` boolean
      - `reason` string: Why the original cannot be read. Present only when available is false.
      - `sourceMediaId` string
      - `sourceLanguage` string
      - `mediaType` string
    - `isTranscriptionOnly` boolean
    - `processingProgress` string
    - `state` string
    - `remark` string
    - `sentiment` object[]
      - `document` object
        - `Negative` integer
        - `Neutral` integer
        - `Positive` integer
      - `sentences` object[]
        - `id` integer
        - `instances` unknown[]
          - unknown
        - `score` object
          - `compound` integer
          - `neg` integer
          - `neu` integer
          - `pos` integer
        - `text` string
    - `createdAt` string, date-time
    - `updatedAt` string, date-time
    - `name` string
    - `description` string
    - `publishedUrl` string
    - `mediaId` string
    - `originalCreatedAt` string, date-time
    - `faceSpriteImg` string
    - `transcriptRevision` integer: Revision of the transcript. Starts at 0 and increases by one on every saved change to the transcript. Send it back as `expectedTranscriptRevision` when you save the transcript, label a passage or comment on one.
    - `thumbnail` object: The video's thumbnail. An empty object when the file has none, which includes every audio file and text note. Use it to follow a frame asked for with PUT /media/{mediaId}/thumbnail: pending is true while the frame is being made, and error is set when it failed, while url still shows the previous thumbnail.
      - `url` string: A signed link to the current thumbnail. Present only when the file has one. It expires, so do not store it.
      - `source` 'auto' | 'custom': `auto` for the thumbnail Speak AI made, `custom` for one you set. Present only when the file has a thumbnail.
      - `pending` boolean: Present and true while a requested frame is still being made.
      - `error` string: Why the last requested frame was not saved, for example "The frame took too long. Try again." Present only when it failed.

---

[API](https://skmtc.dev/speakai/apis/speak-ai-api.md) · [All operations](https://skmtc.dev/speakai/apis/speak-ai-api/llms.txt) · [OpenAPI document](https://skmtc.dev/speakai/apis/speak-ai-api/revisions/52d777e6d46e?raw)