Get Audio Transcription

Get audio transcription

curl --request GET \
  --url https://api.videodb.io/audio/{audio_id}/transcription/ \
  --header 'x-access-token: <api-key>'

const options = {method: 'GET', headers: {'x-access-token': '<api-key>'}};

fetch('https://api.videodb.io/audio/{audio_id}/transcription/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.videodb.io/audio/{audio_id}/transcription/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-access-token: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.videodb.io/audio/{audio_id}/transcription/"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("x-access-token", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.videodb.io/audio/{audio_id}/transcription/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["x-access-token"] = '<api-key>'

response = http.request(request)
puts response.read_body

import Foundation

let url = URL(string: "https://api.videodb.io/audio/{audio_id}/transcription/")!
var request = URLRequest(url: url)
request.httpMethod = "GET"
request.timeoutInterval = 10
request.allHTTPHeaderFields = ["x-access-token": "<api-key>"]

let (data, _) = try await URLSession.shared.data(for: request)
print(String(decoding: data, as: UTF8.self))

using RestSharp;


var options = new RestClientOptions("https://api.videodb.io/audio/{audio_id}/transcription/");
var client = new RestClient(options);
var request = new RestRequest("");
request.AddHeader("x-access-token", "<api-key>");
var response = await client.GetAsync(request);

Console.WriteLine("{0}", response.Content);

using RestSharp;


var options = new RestClientOptions("https://api.videodb.io/audio/{audio_id}/transcription/");
var client = new RestClient(options);
var request = new RestRequest("");
request.AddHeader("x-access-token", "<api-key>");
var response = await client.GetAsync(request);

Console.WriteLine("{0}", response.Content);

const options = {method: 'GET', headers: {'x-access-token': '<api-key>'}};

fetch('https://api.videodb.io/audio/{audio_id}/transcription/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "GET");
curl_easy_setopt(hnd, CURLOPT_WRITEDATA, stdout);
curl_easy_setopt(hnd, CURLOPT_URL, "https://api.videodb.io/audio/{audio_id}/transcription/");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "x-access-token: <api-key>");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

CURLcode ret = curl_easy_perform(hnd);

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "GET");
curl_easy_setopt(hnd, CURLOPT_WRITEDATA, stdout);
curl_easy_setopt(hnd, CURLOPT_URL, "https://api.videodb.io/audio/{audio_id}/transcription/");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "x-access-token: <api-key>");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

CURLcode ret = curl_easy_perform(hnd);

val client = OkHttpClient()

val request = Request.Builder()
  .url("https://api.videodb.io/audio/{audio_id}/transcription/")
  .get()
  .addHeader("x-access-token", "<api-key>")
  .build()

val response = client.newCall(request).execute()

{
  "success": true,
  "status": "completed",
  "data": {
    "transcript": [
      {
        "text": "Hello world",
        "start": 1.5,
        "end": 3.2
      }
    ]
  }
}

{
  "success": false,
  "message": "Error message",
  "error_code": "ERROR_CODE"
}

GET

audio

{audio_id}

transcription

Get audio transcription

curl --request GET \
  --url https://api.videodb.io/audio/{audio_id}/transcription/ \
  --header 'x-access-token: <api-key>'

const options = {method: 'GET', headers: {'x-access-token': '<api-key>'}};

fetch('https://api.videodb.io/audio/{audio_id}/transcription/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.videodb.io/audio/{audio_id}/transcription/",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "x-access-token: <api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.videodb.io/audio/{audio_id}/transcription/"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("x-access-token", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.videodb.io/audio/{audio_id}/transcription/")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["x-access-token"] = '<api-key>'

response = http.request(request)
puts response.read_body

import Foundation

let url = URL(string: "https://api.videodb.io/audio/{audio_id}/transcription/")!
var request = URLRequest(url: url)
request.httpMethod = "GET"
request.timeoutInterval = 10
request.allHTTPHeaderFields = ["x-access-token": "<api-key>"]

let (data, _) = try await URLSession.shared.data(for: request)
print(String(decoding: data, as: UTF8.self))

using RestSharp;


var options = new RestClientOptions("https://api.videodb.io/audio/{audio_id}/transcription/");
var client = new RestClient(options);
var request = new RestRequest("");
request.AddHeader("x-access-token", "<api-key>");
var response = await client.GetAsync(request);

Console.WriteLine("{0}", response.Content);

using RestSharp;


var options = new RestClientOptions("https://api.videodb.io/audio/{audio_id}/transcription/");
var client = new RestClient(options);
var request = new RestRequest("");
request.AddHeader("x-access-token", "<api-key>");
var response = await client.GetAsync(request);

Console.WriteLine("{0}", response.Content);

const options = {method: 'GET', headers: {'x-access-token': '<api-key>'}};

fetch('https://api.videodb.io/audio/{audio_id}/transcription/', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "GET");
curl_easy_setopt(hnd, CURLOPT_WRITEDATA, stdout);
curl_easy_setopt(hnd, CURLOPT_URL, "https://api.videodb.io/audio/{audio_id}/transcription/");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "x-access-token: <api-key>");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

CURLcode ret = curl_easy_perform(hnd);

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "GET");
curl_easy_setopt(hnd, CURLOPT_WRITEDATA, stdout);
curl_easy_setopt(hnd, CURLOPT_URL, "https://api.videodb.io/audio/{audio_id}/transcription/");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "x-access-token: <api-key>");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

CURLcode ret = curl_easy_perform(hnd);

val client = OkHttpClient()

val request = Request.Builder()
  .url("https://api.videodb.io/audio/{audio_id}/transcription/")
  .get()
  .addHeader("x-access-token", "<api-key>")
  .build()

val response = client.newCall(request).execute()

{
  "success": true,
  "status": "completed",
  "data": {
    "transcript": [
      {
        "text": "Hello world",
        "start": 1.5,
        "end": 3.2
      }
    ]
  }
}

{
  "success": false,
  "message": "Error message",
  "error_code": "ERROR_CODE"
}

Retrieve the transcription data for a specific audio file, including word-level timestamps.

import videodb

conn = videodb.connect(api_key="your_api_key")
coll = conn.get_collection()
audio = coll.get_audio("audio_id")

# Get full transcript with timestamps
transcript = audio.get_transcript()

# Get transcript for a time range
transcript = audio.get_transcript(start=10, end=60)

# Segment by sentence
transcript = audio.get_transcript(segmenter="sentence")

# Group every 10 words
transcript = audio.get_transcript(segmenter="word", length=10)

# Fixed-duration audio segments (e.g., 5-second chunks)
transcript = audio.get_transcript(segmenter="time", length=5)

# Get plain text transcript
text = audio.get_transcript_text()

import { connect } from 'videodb';

const conn = connect({ apiKey: 'your_api_key' });
const coll = await conn.getCollection();
const audio = await coll.getAudio('audio_id');

// Get full transcript with timestamps
const transcript = await audio.getTranscript();

// Get transcript for a time range
const rangeTranscript = await audio.getTranscript({ start: 10, end: 60 });

// Segment by sentence
const sentenceTranscript = await audio.getTranscript({ segmenter: 'sentence' });

// Group every 10 words
const wordGroups = await audio.getTranscript({ segmenter: 'word', length: 10 });

// Fixed-duration audio segments
const timeTranscript = await audio.getTranscript({ segmenter: 'time', length: 5 });

// Get plain text transcript
const text = await audio.getTranscriptText();

Audio segmentation

Audio transcription can be segmented independently from any video frame or scene segmentation.

Parameter	Type	Default	Description
`segmenter`	str	`"word"`	How to split the transcript: `"word"`, `"sentence"`, or `"time"`
`length`	int	`1`	Group size: words for `word`, sentences for `sentence`, or seconds for `time`
`start`	float	—	Start time in seconds
`end`	float	—	End time in seconds

Use start and end parameters to retrieve a specific time range
Use segmenter="word" with length=1 for word-level timestamps
SDK helpers return timestamp entries with start, end, and text
The raw API response wraps those entries as data.word_timestamps plus data.text
The engine parameter selects which transcription engine’s output to retrieve

Raw response shape

{
  "success": true,
  "status": "completed",
  "data": {
    "text": "Welcome to VideoDB.",
    "word_timestamps": [
      {"start": 0.2, "end": 0.7, "text": "Welcome"},
      {"start": 0.7, "end": 0.9, "text": "to"},
      {"start": 0.9, "end": 1.4, "text": "VideoDB."}
    ]
  }
}

Silence ranges may be included with text: "-".

Create Transcription

Generate a new transcription

Get Audio

Retrieve audio file details

Authorizations

x-access-token

string

header

required

API key for authentication (sk-xxx format)

Path Parameters

audio_id

string

required

Pattern: ^a-

Example:

"a-12345"

Query Parameters

engine

string

Example:

"default"

start

number

default:0

Example:

0

end

number

default:-1

Example:

60

Response

Audio transcription data

success

boolean

Example:

true

status

enum<string>

Available options:

completed,

processing,

failed

Example:

"completed"

data

object

Show child attributes

⌘I

Overview

Authentication

Collections

Videos

Streaming & Playback

Transcription

Search V2 & Ask

Indexing & Search

Scene & Frame Analysis

Advanced Operations

Audio

Images

AI Generation

Timeline & Compilation

Billing

Downloads

Utilities

Assets

Editor

Transcode

Meeting

Capture

RTStream

RTStream Transcription

RTStream Scene Indexing

RTStream Events & Alerts

Audio segmentation

Raw response shape

Create Transcription

Get Audio

Authorizations

Path Parameters

Query Parameters

Response

​Audio segmentation

​Raw response shape

Create Transcription

Get Audio

Authorizations

Path Parameters

Query Parameters

Response

Audio segmentation

Raw response shape