Speech-to-Text Transcription Batch Multilingual

POST

api

velma-2-stt-batch

Transcribe audio file with automatic language detection

curl --request POST \
  --url https://platform.modulate.ai/api/velma-2-stt-batch \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-Key: <api-key>' \
  --form upload_file='@example-file' \
  --form speaker_diarization=true \
  --form emotion_signal=false \
  --form accent_signal=false \
  --form deepfake_signal=false \
  --form pii_phi_tagging=false \
  --form 'language=<string>' \
  --form 'config=<string>'

import requests

url = "https://platform.modulate.ai/api/velma-2-stt-batch"

files = { "upload_file": ("example-file", open("example-file", "rb")) }
payload = {
    "speaker_diarization": "true",
    "emotion_signal": "false",
    "accent_signal": "false",
    "deepfake_signal": "false",
    "pii_phi_tagging": "false",
    "language": "<string>",
    "config": "<string>"
}
headers = {"X-API-Key": "<api-key>"}

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

print(response.text)

const form = new FormData();
form.append('upload_file', '<string>');
form.append('speaker_diarization', 'true');
form.append('emotion_signal', 'false');
form.append('accent_signal', 'false');
form.append('deepfake_signal', 'false');
form.append('pii_phi_tagging', 'false');
form.append('language', '<string>');
form.append('config', '<string>');

const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};

options.body = form;

fetch('https://platform.modulate.ai/api/velma-2-stt-batch', 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://platform.modulate.ai/api/velma-2-stt-batch",
  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=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "X-API-Key: <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"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.modulate.ai/api/velma-2-stt-batch"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--")

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

	req.Header.Add("X-API-Key", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.modulate.ai/api/velma-2-stt-batch")
  .header("X-API-Key", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.modulate.ai/api/velma-2-stt-batch")

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

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, how are you? Bonjour, ça va?",
  "duration_ms": 5000,
  "utterances": [
    {
      "utterance_uuid": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "text": "Hello, how are you?",
      "start_ms": 0,
      "duration_ms": 2000,
      "speaker": 1,
      "language": "en",
      "emotion": "Neutral",
      "accent": "American",
      "deepfake_score": null
    },
    {
      "utterance_uuid": "f6a7b8c9-d0e1-2345-fabc-456789012345",
      "text": "Bonjour, ça va?",
      "start_ms": 2500,
      "duration_ms": 2500,
      "speaker": 2,
      "language": "fr",
      "emotion": "Happy",
      "accent": "British",
      "deepfake_score": null
    }
  ]
}

Authorizations

X-API-Key

string

header

required

API key used for authentication and usage tracking.

Body

multipart/form-data

upload_file

file

required

Audio file to transcribe. Supported formats: AAC, AIFF, FLAC, MP3, MP4, MOV, OGG, Opus, WAV, WebM. Maximum file size: 100MB. Empty files are rejected.

speaker_diarization

boolean

default:true

Speaker diarization identifies different speakers in the audio. When enabled, each utterance includes a speaker identifier (e.g., 1, 2).

emotion_signal

boolean

default:false

Emotion detection for each utterance. When enabled, each utterance includes an emotion signal detected from the speaker's voice.

accent_signal

boolean

default:false

Accent detection for each utterance. When enabled, each utterance includes an accent signal detected from the speaker's voice.

deepfake_signal

boolean

default:false

Synthetic voice (deepfake) detection for each utterance. When enabled, each utterance includes a deepfake_score indicating the likelihood that the speech is AI-generated. The score ranges from 0.0 (likely natural) to 1.0 (likely synthetic).

pii_phi_tagging

boolean

default:false

PII/PHI tagging in utterance text. When enabled, personally identifiable information and personal health information are wrapped with appropriate tags in the transcription text.

language

string

Optional language hint as a case-insensitive ISO 639-1 code (e.g. "en", "fr"). BCP 47 region/script subtags (e.g. "en-US") are accepted; only the primary language subtag is used. When omitted, the language is detected automatically for each utterance.

Pattern: ^[A-Za-z]{2,3}([-_][A-Za-z0-9]+)*$

config

string

Optional JSON-encoded STT configuration. When present, a field in this object overrides the matching top-level form parameter; an omitted field falls back to the form parameter. Carries custom_terms plus the per-request STT flags. Sent as a string form field because multipart/form-data has no first-class object type.

Response

Transcription completed successfully

text

string

required

The complete transcribed text from the audio file, containing all utterances concatenated together. This provides a full transcript of the audio content. Always present; may be an empty string when no speech was recognized.

Example:

"Hello everyone. Welcome to the meeting."

duration_ms

integer

required

The total duration of the processed audio in milliseconds. This value represents the actual audio duration and is used for usage tracking and billing purposes.

Required range: x >= 0

Example:

45000

utterances

object[]

required

Array of individual utterances detected in the audio, ordered by start time. Each utterance represents a continuous segment of speech, potentially from a specific speaker if diarization is enabled. Always present; may be an empty array when no speech was recognized.

Show child attributes

⌘I

Transcribe audio file with automatic language detection

curl --request POST \
  --url https://platform.modulate.ai/api/velma-2-stt-batch \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-Key: <api-key>' \
  --form upload_file='@example-file' \
  --form speaker_diarization=true \
  --form emotion_signal=false \
  --form accent_signal=false \
  --form deepfake_signal=false \
  --form pii_phi_tagging=false \
  --form 'language=<string>' \
  --form 'config=<string>'

import requests

url = "https://platform.modulate.ai/api/velma-2-stt-batch"

files = { "upload_file": ("example-file", open("example-file", "rb")) }
payload = {
    "speaker_diarization": "true",
    "emotion_signal": "false",
    "accent_signal": "false",
    "deepfake_signal": "false",
    "pii_phi_tagging": "false",
    "language": "<string>",
    "config": "<string>"
}
headers = {"X-API-Key": "<api-key>"}

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

print(response.text)

const form = new FormData();
form.append('upload_file', '<string>');
form.append('speaker_diarization', 'true');
form.append('emotion_signal', 'false');
form.append('accent_signal', 'false');
form.append('deepfake_signal', 'false');
form.append('pii_phi_tagging', 'false');
form.append('language', '<string>');
form.append('config', '<string>');

const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};

options.body = form;

fetch('https://platform.modulate.ai/api/velma-2-stt-batch', 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://platform.modulate.ai/api/velma-2-stt-batch",
  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=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "X-API-Key: <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"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.modulate.ai/api/velma-2-stt-batch"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--")

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

	req.Header.Add("X-API-Key", "<api-key>")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://platform.modulate.ai/api/velma-2-stt-batch")
  .header("X-API-Key", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://platform.modulate.ai/api/velma-2-stt-batch")

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

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_diarization\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"emotion_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"accent_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"deepfake_signal\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"pii_phi_tagging\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"config\"\r\n\r\n<string>\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, how are you? Bonjour, ça va?",
  "duration_ms": 5000,
  "utterances": [
    {
      "utterance_uuid": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "text": "Hello, how are you?",
      "start_ms": 0,
      "duration_ms": 2000,
      "speaker": 1,
      "language": "en",
      "emotion": "Neutral",
      "accent": "American",
      "deepfake_score": null
    },
    {
      "utterance_uuid": "f6a7b8c9-d0e1-2345-fabc-456789012345",
      "text": "Bonjour, ça va?",
      "start_ms": 2500,
      "duration_ms": 2500,
      "speaker": 2,
      "language": "fr",
      "emotion": "Happy",
      "accent": "British",
      "deepfake_score": null
    }
  ]
}

Velma