get transcript

Every spoken word on the timeline with its position in the cut, as frame numbers at the timeline’s rate, the positions remove_words takes. granularity words: [index, text, from_frame, to_frame], 10000 a page; sentences: [first_word_index, text, from_frame, to_frame], 1000 a page, each row’s first index leading back into word mode. A full page carries next_start_frame. Indices are positions in the whole transcript and stable across pages. speakers adds who was talking on each row, from what the speakers tool found. An empty result usually means untranscribed, not silent: transcribe_media with timeline_id writes the words onto the clips. For one library item, transcribe_media with ref. Free.

POST

/

tools

/

get_transcript

get transcript

curl --request POST \
  --url https://eversince.ai/api/v1/tools/get_transcript \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "timeline_id": "<string>"
}
'

import requests

url = "https://eversince.ai/api/v1/tools/get_transcript"

payload = { "timeline_id": "<string>" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({timeline_id: '<string>'})
};

fetch('https://eversince.ai/api/v1/tools/get_transcript', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "ok": true,
  "data": {},
  "meta": {
    "request_id": "<string>",
    "cost": {},
    "cloud_processing": {
      "ran_on": "cloud",
      "minutes": 123,
      "queued_minutes": 123,
      "left_minutes": 123,
      "bought_minutes": 123,
      "note": "<string>"
    }
  },
  "media": [
    {}
  ]
}

{
  "ok": false,
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "suggested_action": "<string>",
    "cloud_processing": {
      "ran_on": "cloud",
      "minutes": 123,
      "queued_minutes": 123,
      "left_minutes": 123,
      "bought_minutes": 123,
      "note": "<string>"
    }
  }
}

Authorizations

Authorization

string

header

required

An API key (es_live_…) from Settings, under API keys, or an OAuth access token.

Headers

Idempotency-Key

string

Retry a paid dispatch safely: the same key returns the job already dispatched instead of charging again.

x-workspace-id

string

The workspace this one call acts in, when it is not the key's own.

Body

application/json

timeline_id

string

required

The timeline id.

start_frame

integer

end_frame

integer

granularity

enum<string>

words: every word with its frames, the indices remove_words takes. sentences: a fraction of the size, each row carrying the index of its first word for a cut.

Available options:

words,

sentences

source

enum<string>

Which speech: voiceover (narration), dialogue, music (lyrics); all reads every stream clip by clip with a passages list. Default picks whichever the timeline has.

Available options:

voiceover,

dialogue,

music,

auto,

all

speakers

boolean

Carry who is talking on every row, and the stretches each speaker holds. Read from what the speakers tool found; files nobody has been picked out of are left out rather than listened to now.

Response

Done, or a job started for work that runs longer (follow it with get_jobs).

ok

any

required

data

object

required

meta

object

required

Show child attributes

media

object[]

get transcript

curl --request POST \
  --url https://eversince.ai/api/v1/tools/get_transcript \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "timeline_id": "<string>"
}
'

import requests

url = "https://eversince.ai/api/v1/tools/get_transcript"

payload = { "timeline_id": "<string>" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({timeline_id: '<string>'})
};

fetch('https://eversince.ai/api/v1/tools/get_transcript', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "ok": true,
  "data": {},
  "meta": {
    "request_id": "<string>",
    "cost": {},
    "cloud_processing": {
      "ran_on": "cloud",
      "minutes": 123,
      "queued_minutes": 123,
      "left_minutes": 123,
      "bought_minutes": 123,
      "note": "<string>"
    }
  },
  "media": [
    {}
  ]
}

{
  "ok": false,
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryable": true,
    "suggested_action": "<string>",
    "cloud_processing": {
      "ran_on": "cloud",
      "minutes": 123,
      "queued_minutes": 123,
      "left_minutes": 123,
      "bought_minutes": 123,
      "note": "<string>"
    }
  }
}