Transcribe a file
curl --request POST \
--url https://stt.eu.mihu.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-file \
--form model=umay \
--form language=tr \
--form normalize=true \
--form dialect_correction=true \
--form place_correction=true \
--form abbreviations=false \
--form mode=fast \
--form 'hint_context=<string>' \
--form 'hints=<string>' \
--form hints_score=2 \
--form gender_detection=false \
--form diarize=false \
--form max_speakers=8 \
--form speaker_lock=false \
--form lock_threshold=123 \
--form voice_isolation=false \
--form 'reference_voiceprint=<string>' \
--form response_format=json \
--form 'webhook_url=<string>' \
--form 'webhook_secret=<string>' \
--form 'webhook_metadata=<string>' \
--form 'file_url=<string>'import requests
url = "https://stt.eu.mihu.ai/v1/audio/transcriptions"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"model": "umay",
"language": "tr",
"normalize": "true",
"dialect_correction": "true",
"place_correction": "true",
"abbreviations": "false",
"mode": "fast",
"hint_context": "<string>",
"hints": "<string>",
"hints_score": "2",
"gender_detection": "false",
"diarize": "false",
"max_speakers": "8",
"speaker_lock": "false",
"lock_threshold": "123",
"voice_isolation": "false",
"reference_voiceprint": "<string>",
"response_format": "json",
"webhook_url": "<string>",
"webhook_secret": "<string>",
"webhook_metadata": "<string>",
"file_url": "<string>"
}
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('model', 'umay');
form.append('language', 'tr');
form.append('normalize', 'true');
form.append('dialect_correction', 'true');
form.append('place_correction', 'true');
form.append('abbreviations', 'false');
form.append('mode', 'fast');
form.append('hint_context', '<string>');
form.append('hints', '<string>');
form.append('hints_score', '2');
form.append('gender_detection', 'false');
form.append('diarize', 'false');
form.append('max_speakers', '8');
form.append('speaker_lock', 'false');
form.append('lock_threshold', '123');
form.append('voice_isolation', 'false');
form.append('reference_voiceprint', '<string>');
form.append('response_format', 'json');
form.append('webhook_url', '<string>');
form.append('webhook_secret', '<string>');
form.append('webhook_metadata', '<string>');
form.append('file_url', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://stt.eu.mihu.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://stt.eu.mihu.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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\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://stt.eu.mihu.ai/v1/audio/transcriptions"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\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://stt.eu.mihu.ai/v1/audio/transcriptions")
.header("Authorization", "Bearer <token>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://stt.eu.mihu.ai/v1/audio/transcriptions")
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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"text": "Adresiniz Şirinyer Mahallesi, Cumhuriyet Caddesi No: 17.",
"model": "umay",
"language": "tr",
"duration": 7.2,
"processing_time": 0.16,
"speakers": [
{
"speaker": "S1",
"gender": "female",
"percent": 97,
"speech_seconds": 6.8
}
]
}{
"id": "6f1d2c3b-9a4e-4b7c-8d2f-1e0a5b9c7d36",
"object": "transcription.job",
"status": "queued",
"duration": 3600,
"created_at": 1793145600,
"source": {
"type": "upload",
"filename": "call-1042.wav",
"size_bytes": 115200044
},
"request": {
"model": "umay",
"language": "tr",
"response_format": "json",
"language_model": false,
"normalize": true,
"diarize": true,
"gender_detection": false,
"speaker_lock": false,
"voice_isolation": false,
"hints": false,
"max_speakers": 8
}
}Transcription
Transcribe a file
Native or OpenAI-compatible by model. With webhook_url the job runs asynchronously and answers 202. For OpenAI model names see OpenAI-compatible API.
POST
/
v1
/
audio
/
transcriptions
Transcribe a file
curl --request POST \
--url https://stt.eu.mihu.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=@example-file \
--form model=umay \
--form language=tr \
--form normalize=true \
--form dialect_correction=true \
--form place_correction=true \
--form abbreviations=false \
--form mode=fast \
--form 'hint_context=<string>' \
--form 'hints=<string>' \
--form hints_score=2 \
--form gender_detection=false \
--form diarize=false \
--form max_speakers=8 \
--form speaker_lock=false \
--form lock_threshold=123 \
--form voice_isolation=false \
--form 'reference_voiceprint=<string>' \
--form response_format=json \
--form 'webhook_url=<string>' \
--form 'webhook_secret=<string>' \
--form 'webhook_metadata=<string>' \
--form 'file_url=<string>'import requests
url = "https://stt.eu.mihu.ai/v1/audio/transcriptions"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"model": "umay",
"language": "tr",
"normalize": "true",
"dialect_correction": "true",
"place_correction": "true",
"abbreviations": "false",
"mode": "fast",
"hint_context": "<string>",
"hints": "<string>",
"hints_score": "2",
"gender_detection": "false",
"diarize": "false",
"max_speakers": "8",
"speaker_lock": "false",
"lock_threshold": "123",
"voice_isolation": "false",
"reference_voiceprint": "<string>",
"response_format": "json",
"webhook_url": "<string>",
"webhook_secret": "<string>",
"webhook_metadata": "<string>",
"file_url": "<string>"
}
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('model', 'umay');
form.append('language', 'tr');
form.append('normalize', 'true');
form.append('dialect_correction', 'true');
form.append('place_correction', 'true');
form.append('abbreviations', 'false');
form.append('mode', 'fast');
form.append('hint_context', '<string>');
form.append('hints', '<string>');
form.append('hints_score', '2');
form.append('gender_detection', 'false');
form.append('diarize', 'false');
form.append('max_speakers', '8');
form.append('speaker_lock', 'false');
form.append('lock_threshold', '123');
form.append('voice_isolation', 'false');
form.append('reference_voiceprint', '<string>');
form.append('response_format', 'json');
form.append('webhook_url', '<string>');
form.append('webhook_secret', '<string>');
form.append('webhook_metadata', '<string>');
form.append('file_url', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://stt.eu.mihu.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://stt.eu.mihu.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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\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://stt.eu.mihu.ai/v1/audio/transcriptions"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\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://stt.eu.mihu.ai/v1/audio/transcriptions")
.header("Authorization", "Bearer <token>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://stt.eu.mihu.ai/v1/audio/transcriptions")
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=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\numay\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\ntr\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"normalize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"dialect_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"place_correction\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"abbreviations\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"mode\"\r\n\r\nfast\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hint_context\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"hints_score\"\r\n\r\n2\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"gender_detection\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"max_speakers\"\r\n\r\n8\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"speaker_lock\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lock_threshold\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"voice_isolation\"\r\n\r\nfalse\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"reference_voiceprint\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_secret\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"webhook_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"text": "Adresiniz Şirinyer Mahallesi, Cumhuriyet Caddesi No: 17.",
"model": "umay",
"language": "tr",
"duration": 7.2,
"processing_time": 0.16,
"speakers": [
{
"speaker": "S1",
"gender": "female",
"percent": 97,
"speech_seconds": 6.8
}
]
}{
"id": "6f1d2c3b-9a4e-4b7c-8d2f-1e0a5b9c7d36",
"object": "transcription.job",
"status": "queued",
"duration": 3600,
"created_at": 1793145600,
"source": {
"type": "upload",
"filename": "call-1042.wav",
"size_bytes": 115200044
},
"request": {
"model": "umay",
"language": "tr",
"response_format": "json",
"language_model": false,
"normalize": true,
"diarize": true,
"gender_detection": false,
"speaker_lock": false,
"voice_isolation": false,
"hints": false,
"max_speakers": 8
}
}Authorizations
Your API key
Body
multipart/form-data
The audio. Any common format (WAV, MP3, ...).
umay (most accurate; files), or an OpenAI name such as whisper-1, gpt-4o-transcribe, gpt-4o-transcribe-diarize.
Example:
"umay"
Language of the speech.
Available options:
tr, en, de, fr, it, ru, es Example:
"tr"
Inverse text normalisation on the final text: "bin iki yüz elli lira" becomes "1.250 TL". false returns the spoken words.
Turkish, with normalize=true: regional and colloquial forms in standard Turkish.
Turkish, with normalize=true: misheard or split place names corrected.
Turkish, with normalize=true: false writes units out ("43 dakika"), true abbreviates ("43 dk").
normal: files with model=umay use the language model where the model has one. fast: never.
Available options:
fast, normal Built-in hint lists (Turkish): mugla, izmir, manisa, aydin, denizli; comma-separated for several.
Own phrases (names, places) to favour, comma or newline separated; phrase :3 gives one phrase its own boost.
Boost for phrases without their own.
Gender of the speaker(s) with a confidence percent (50-100).
Speaker label per segment (S1, S2, ...).
Upper bound for diarization.
Only the first speaker's speech becomes text; other voices come as ignored.
With speaker_lock: the similarity a segment needs to count as S1 (0-1). Default 0.5, or 0.55 with reference_voiceprint.
Removes other voices before recognition (tr, de, fr, it, es, ru); switches on only after another voice is heard.
Id or token of a stored voiceprint: with voice_isolation, speaker_lock or diarize, speaker S1 is that person from the first second.
With OpenAI model names.
Available options:
json, text, srt, vtt, verbose_json, diarized_json https:// URL that receives the result (POST, JSON). With it the request answers 202 at once. Must resolve to a public address.
Optional, 1-256 characters: the webhook is signed with it (X-Mihu-Signature).
Optional, up to 4 KB: echoed back as metadata.
Instead of file: https:// URL the server downloads the audio from (up to 1 GB, 10 minutes, public addresses only).
Response
Transcription