Speech-to-text

curl --request POST \
  --url https://api.infery.ai/v1/audio/transcriptions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'model=<string>' \
  --form 'file_base64=<string>' \
  --form filename=audio.mp3 \
  --form 'language=<string>' \
  --form 'prompt=<string>' \
  --form temperature=0.5 \
  --form response_format=json

import requests

url = "https://api.infery.ai/v1/audio/transcriptions"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('model', '<string>');
form.append('file_base64', '<string>');
form.append('filename', 'audio.mp3');
form.append('language', '<string>');
form.append('prompt', '<string>');
form.append('temperature', '0.5');
form.append('response_format', 'json');

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

options.body = form;

fetch('https://api.infery.ai/v1/audio/transcriptions', 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.infery.ai/v1/audio/transcriptions",
  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=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "<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://api.infery.ai/v1/audio/transcriptions")
  .header("Authorization", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/audio/transcriptions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, this is a test transcription.",
  "language": "en",
  "duration": 12.5,
  "segments": [
    {
      "id": 123,
      "start": 123,
      "end": 123,
      "text": "<string>",
      "avg_logprob": 123,
      "compression_ratio": 123,
      "no_speech_prob": 123
    }
  ],
  "credits_used": 3
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

POST

audio

transcriptions

Speech-to-text

curl --request POST \
  --url https://api.infery.ai/v1/audio/transcriptions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'model=<string>' \
  --form 'file_base64=<string>' \
  --form filename=audio.mp3 \
  --form 'language=<string>' \
  --form 'prompt=<string>' \
  --form temperature=0.5 \
  --form response_format=json

import requests

url = "https://api.infery.ai/v1/audio/transcriptions"

payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "multipart/form-data"
}

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

print(response.text)

const form = new FormData();
form.append('model', '<string>');
form.append('file_base64', '<string>');
form.append('filename', 'audio.mp3');
form.append('language', '<string>');
form.append('prompt', '<string>');
form.append('temperature', '0.5');
form.append('response_format', 'json');

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

options.body = form;

fetch('https://api.infery.ai/v1/audio/transcriptions', 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.infery.ai/v1/audio/transcriptions",
  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=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/audio/transcriptions"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")

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

	req.Header.Add("Authorization", "<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://api.infery.ai/v1/audio/transcriptions")
  .header("Authorization", "<api-key>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/audio/transcriptions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_base64\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filename\"\r\n\r\naudio.mp3\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"prompt\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n0.5\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001--"

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

{
  "text": "Hello, this is a test transcription.",
  "language": "en",
  "duration": 12.5,
  "segments": [
    {
      "id": 123,
      "start": 123,
      "end": 123,
      "text": "<string>",
      "avg_logprob": 123,
      "compression_ratio": 123,
      "no_speech_prob": 123
    }
  ],
  "credits_used": 3
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

We accept both multipart and JSON base64 for STT, so the OpenAI SDK works out of the box.

Multipart (OpenAI SDK default)

from openai import OpenAI
client = OpenAI(api_key=API_KEY, base_url="https://api.infery.ai/v1")
tr = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("meeting.mp3", "rb"),
    response_format="verbose_json",
)
print(tr.text)

JSON base64 (light HTTP clients)

curl https://api.infery.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $INFERY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "whisper-1",
    "file_base64": "<base64 audio>",
    "filename": "meeting.mp3",
    "response_format": "json"
  }'

Response formats

json (default), text, srt, verbose_json (with segments), vtt. The response body is always JSON, whichever format you ask for: srt, vtt and text put the rendered document in the text field rather than returning it bare. The OpenAI SDK hands you the raw body for those three, so parse it as JSON and read ["text"] before writing a subtitle file. verbose_json carries segment-level timestamps in segments[]. Word-level timestamps are not supported — timestamp_granularities is dropped before the request reaches the provider, so words comes back empty. There is no /v1/audio/translations endpoint. To translate, transcribe first and pass the text to a chat completion.

Limits

Max 25 MB audio per request
Formats: MP3, MP4, M4A, WAV, WebM, OGG, FLAC

Authorizations

Authorization

string

header

required

API key in format: Bearer inf_***

Body

Either multipart/form-data with a file part — what the OpenAI SDK sends, and the reason it works here unchanged — or JSON carrying the audio as base64 in file_base64. The field names below are the JSON ones; the multipart part is named file and the rest are plain form fields of the same names.

timestamp_granularities is NOT supported: it is not read on either path, so no word-level timestamps are ever returned. verbose_json gives segment-level timestamps and that is the finest granularity available.

model

string

required

Model ID to use for STT

file_base64

string

required

Base64-encoded audio data. JSON path only — send a file part instead on multipart.

filename

string

default:audio.mp3

Original file name. The audio MIME type is derived from its extension, so a wrong extension can mis-declare the upload.

language

string

Language of the audio (ISO-639-1)

prompt

string

Optional transcription hint passed through to the provider

temperature

number

Sampling temperature (0-1)

Required range: 0 <= x <= 1

response_format

enum<string>

default:json

Available options:

json,

text,

srt,

verbose_json,

vtt

Response

Transcription result. Shape depends on response_format: JSON (json, verbose_json) or plain text (text, srt, vtt).

Option 1
Option 2

response_format: json (default) or verbose_json

text

string

Example:

"Hello, this is a test transcription."

language

string

Detected language (verbose_json only)

Example:

"en"

duration

number

Audio duration in seconds (verbose_json only)

Example:

12.5

segments

object[]

Time-stamped segments (verbose_json only)

Show child attributes

credits_used

integer

Example:

3

Overview

Chat Completions

Embeddings

Images

Audio

Video

Music

Files

Models

Capabilities

Workflows

Speech-to-text

Multipart (OpenAI SDK default)

JSON base64 (light HTTP clients)

Response formats

Limits

Authorizations

Body

Response

​Multipart (OpenAI SDK default)

​JSON base64 (light HTTP clients)

​Response formats

​Limits

Authorizations

Body

Response

Multipart (OpenAI SDK default)

JSON base64 (light HTTP clients)

Response formats

Limits