Speech To Text

curl --request POST \
  --url https://api.sunbird.ai/tasks/stt \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form audio='@example-file' \
  --form language=lug \
  --form adapter=lug \
  --form recognise_speakers=false \
  --form whisper=false

import requests

url = "https://api.sunbird.ai/tasks/stt"

files = { "audio": ("example-file", open("example-file", "rb")) }
payload = {
    "language": "lug",
    "adapter": "lug",
    "recognise_speakers": "false",
    "whisper": "false"
}
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('audio', '<string>');
form.append('language', 'lug');
form.append('adapter', 'lug');
form.append('recognise_speakers', 'false');
form.append('whisper', 'false');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.sunbird.ai/tasks/stt', 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.sunbird.ai/tasks/stt",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.sunbird.ai/tasks/stt"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.sunbird.ai/tasks/stt")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.sunbird.ai/tasks/stt")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "audio_transcription": "<string>",
  "diarization_output": {},
  "formatted_diarization_output": "<string>",
  "audio_transcription_id": 123,
  "audio_url": "<string>",
  "language": "<string>",
  "was_audio_trimmed": false,
  "original_duration_minutes": 123
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Legacy Speech to Text

Speech to Text

deprecated

Upload an audio file and get the transcription text.

Upload an audio file for transcription. Supports various audio formats including MP3, WAV, OGG, M4A, and AAC.

Limitations:

Maximum audio duration: Files longer than 10 minutes will be trimmed
Supported formats: MP3, WAV, OGG, M4A, AAC
Large files are supported but only first 10 minutes will be transcribed

Note:

For files larger than 100MB, please use chunked upload or consider splitting the audio file.

Args:

request: The FastAPI request object. audio: The uploaded audio file. language: Target language for transcription. Defaults to Luganda. adapter: Language adapter to use. Defaults to Luganda. recognise_speakers: Enable speaker diarization. Defaults to False. whisper: Use Whisper model for transcription. Defaults to False. db: Database session. current_user: The authenticated user. service: The STT service instance.

Returns:

STTTranscript containing the transcription results.

Raises:

ValidationError: If audio file validation fails. BadRequestError: If audio processing fails. ExternalServiceError: If transcription service fails.

POST

tasks

stt

Speech To Text

curl --request POST \
  --url https://api.sunbird.ai/tasks/stt \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form audio='@example-file' \
  --form language=lug \
  --form adapter=lug \
  --form recognise_speakers=false \
  --form whisper=false

import requests

url = "https://api.sunbird.ai/tasks/stt"

files = { "audio": ("example-file", open("example-file", "rb")) }
payload = {
    "language": "lug",
    "adapter": "lug",
    "recognise_speakers": "false",
    "whisper": "false"
}
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('audio', '<string>');
form.append('language', 'lug');
form.append('adapter', 'lug');
form.append('recognise_speakers', 'false');
form.append('whisper', 'false');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.sunbird.ai/tasks/stt', 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.sunbird.ai/tasks/stt",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: multipart/form-data"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.sunbird.ai/tasks/stt"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.sunbird.ai/tasks/stt")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.sunbird.ai/tasks/stt")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"adapter\"\r\n\r\nlug\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"recognise_speakers\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"whisper\"\r\n\r\nfalse\r\n-----011000010111000001101001--"

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

{
  "audio_transcription": "<string>",
  "diarization_output": {},
  "formatted_diarization_output": "<string>",
  "audio_transcription_id": 123,
  "audio_url": "<string>",
  "language": "<string>",
  "was_audio_trimmed": false,
  "original_duration_minutes": 123
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

multipart/form-data

audio

file

required

Audio file to transcribe

language

enum<string>

default:lug

Supported languages for Speech-to-Text transcription.

This enum defines the language codes supported by the STT service. Each value represents an ISO 639-3 language code.

Attributes: acholi: Acholi language (ach). ateso: Ateso language (teo). english: English language (eng). luganda: Luganda language (lug). lugbara: Lugbara language (lgg). runyankole: Runyankole language (nyn). swahili: Swahili language (swa). kinyarwanda: Kinyarwanda language (kin). lusoga: Lusoga language (xog). lumasaba: Lumasaba language (myx).

Available options:

ach,

teo,

eng,

lug,

lgg,

nyn,

swa,

kin,

xog,

myx

adapter

enum<string>

default:lug

Supported languages for Speech-to-Text transcription.

This enum defines the language codes supported by the STT service. Each value represents an ISO 639-3 language code.

Available options:

ach,

teo,

eng,

lug,

lgg,

nyn,

swa,

kin,

xog,

myx

recognise_speakers

boolean

default:false

whisper

boolean

default:false

Response

Successful Response

Response model for speech-to-text transcription results.

This model represents the output of an STT transcription request, including the transcribed text, diarization data, and metadata.

Attributes: audio_transcription: The transcribed text from the audio. diarization_output: Speaker diarization data as a dictionary. formatted_diarization_output: Human-readable diarization output. audio_transcription_id: Database ID of the saved transcription. audio_url: URL or path to the processed audio file. language: The language code used for transcription. was_audio_trimmed: Whether the audio was trimmed to max duration. original_duration_minutes: Original duration if audio was trimmed.

audio_transcription

string | null

The transcribed text from the audio

diarization_output

Diarization Output · object | null

Speaker diarization data

formatted_diarization_output

string | null

Human-readable diarization output

audio_transcription_id

integer | null

Database ID of the saved transcription

audio_url

string | null

URL or path to the processed audio file

language

string | null

The language code used for transcription

was_audio_trimmed

boolean | null

default:false

Whether the audio was trimmed to max duration

original_duration_minutes

number | null

Original duration in minutes if audio was trimmed

Legacy API (Deprecated)Transcribe Audio (Modal Whisper)

Overview

Legacy Speech to Text

Legacy Text to Speech

Legacy AI

Speech to Text

Authorizations

Body

Response