Scribe v2

curl --request POST \
  --url https://api.snapgen.org/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'model=<string>' \
  --form 'audio_url=<string>' \
  --form 'language=<string>' \
  --form diarize=true \
  --form num_speakers=123 \
  --form tag_audio_events=true \
  --form 'timestamps=<string>' \
  --form subtitles=true \
  --form temperature=123 \
  --form 'response_format=<string>' \
  --form file='@example-file'

import requests

url = "https://api.snapgen.org/v1/audio/transcriptions"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "model": "<string>",
    "audio_url": "<string>",
    "language": "<string>",
    "diarize": "true",
    "num_speakers": "123",
    "tag_audio_events": "true",
    "timestamps": "<string>",
    "subtitles": "true",
    "temperature": "123",
    "response_format": "<string>"
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('model', '<string>');
form.append('audio_url', '<string>');
form.append('language', '<string>');
form.append('diarize', 'true');
form.append('num_speakers', '123');
form.append('tag_audio_events', 'true');
form.append('timestamps', '<string>');
form.append('subtitles', 'true');
form.append('temperature', '123');
form.append('response_format', '<string>');
form.append('file', '{
  "fileName": "example-file"
}');

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

options.body = form;

fetch('https://api.snapgen.org/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.snapgen.org/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=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\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.snapgen.org/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=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\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.snapgen.org/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.snapgen.org/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=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--"

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

POST

audio

transcriptions

Scribe v2

curl --request POST \
  --url https://api.snapgen.org/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'model=<string>' \
  --form 'audio_url=<string>' \
  --form 'language=<string>' \
  --form diarize=true \
  --form num_speakers=123 \
  --form tag_audio_events=true \
  --form 'timestamps=<string>' \
  --form subtitles=true \
  --form temperature=123 \
  --form 'response_format=<string>' \
  --form file='@example-file'

import requests

url = "https://api.snapgen.org/v1/audio/transcriptions"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "model": "<string>",
    "audio_url": "<string>",
    "language": "<string>",
    "diarize": "true",
    "num_speakers": "123",
    "tag_audio_events": "true",
    "timestamps": "<string>",
    "subtitles": "true",
    "temperature": "123",
    "response_format": "<string>"
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('model', '<string>');
form.append('audio_url', '<string>');
form.append('language', '<string>');
form.append('diarize', 'true');
form.append('num_speakers', '123');
form.append('tag_audio_events', 'true');
form.append('timestamps', '<string>');
form.append('subtitles', 'true');
form.append('temperature', '123');
form.append('response_format', '<string>');
form.append('file', '{
  "fileName": "example-file"
}');

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

options.body = form;

fetch('https://api.snapgen.org/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.snapgen.org/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=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\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.snapgen.org/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=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\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.snapgen.org/v1/audio/transcriptions")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.snapgen.org/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=\"model\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"diarize\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"num_speakers\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"tag_audio_events\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"timestamps\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"subtitles\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"temperature\"\r\n\r\n123\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"response_format\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n{\r\n  \"fileName\": \"example-file\"\r\n}\r\n-----011000010111000001101001--"

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

scribe-v2 transcribes speech with ElevenLabs Scribe v2 on the OpenAI-compatible transcription endpoint. Upload a file or pass a public URL, and receive JSON with the transcript and, on request, word timings, speaker labels, tagged sounds, and SRT subtitles. One request takes up to two hours of audio.

Property	Value
Model ID	`scribe-v2`
Endpoint	`POST /v1/audio/transcriptions` (multipart file or JSON `audio_url`)
Output	JSON: `text`, `language`, `language_probability`, `duration_seconds`, optional `words` and `srt`
Limits	Up to 7,200 seconds (2 hours) and 50 MB per request
Input formats	WAV, AIFF, MP3, AAC, MP4, M4A, MOV, FLAC, Ogg, and WebM with a readable length
Billed on	Audio length measured by SnapGen, in whole seconds
Price	$0.000092 per second ($0.00552 per minute, $0.3312 per hour)

Confirm live rates on the SnapGen models page. Failed requests are not charged.

string

required

Set to scribe-v2.

file

The audio file, in a multipart field named file, up to 50 MB. Send file or audio_url, not both.

string

Public http or https URL of the audio. The gateway downloads it, up to 50 MB. Send audio_url or file, not both.

string

Language of the audio as an ISO 639 code of two or three lowercase letters, such as en. Omit it to detect the language automatically.

boolean

Labels who speaks each word in words[].speaker.

integer

The most speakers in the audio, from 1 to 32. Helps speaker labeling.

boolean

Tags sounds such as laughter or footsteps in the transcript.

string

none, word, or character. word and character add words with word-level timings.

boolean

true adds SubRip subtitles in srt. The gateway turns on speaker labels and word timings at the provider, which subtitles need.

number

Randomness, from 0 to 2. Higher values give more varied output.

string

default:"json"

json or verbose_json. verbose_json adds words unless timestamps is none. Both return the SnapGen JSON shape, not OpenAI’s verbose schema.

Request

Upload a local file as multipart/form-data:

curl https://api.snapgen.org/v1/audio/transcriptions \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -F model=scribe-v2 \
  -F file=@interview.mp3 \
  -F diarize=true \
  -F subtitles=true

Or send JSON with a public audio_url:

curl https://api.snapgen.org/v1/audio/transcriptions \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "scribe-v2",
    "audio_url": "https://example.com/interview.mp3",
    "diarize": true,
    "subtitles": true
  }'

Response

{
  "text": "Welcome to the show. Thanks for having me.",
  "language": "eng",
  "language_probability": 0.99,
  "duration_seconds": 12.34,
  "srt": "1\n00:00:00,120 --> 00:00:01,480\nWelcome to the show.\n\n2\n00:00:01,900 --> 00:00:03,020\nThanks for having me.\n"
}

The OpenAI SDKs send the same multipart upload, so a basic transcription works unchanged. Read text from the result; the extra fields in this response don’t follow OpenAI’s verbose schema.

import os

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["SNAPGEN_API_KEY"],
    base_url="https://api.snapgen.org/v1",
)

with open("interview.mp3", "rb") as audio:
    transcript = client.audio.transcriptions.create(model="scribe-v2", file=audio)

print(transcript.text)

const fs = require("node:fs");
const OpenAI = require("openai");

async function main() {
  const client = new OpenAI({
    apiKey: process.env.SNAPGEN_API_KEY,
    baseURL: "https://api.snapgen.org/v1",
  });

  const transcript = await client.audio.transcriptions.create({
    model: "scribe-v2",
    file: fs.createReadStream("interview.mp3"),
  });

  console.log(transcript.text);
}

main();

Words, speakers, and subtitles

You want	Send	You get
Plain text	Nothing extra	`text`, `language`, `duration_seconds`
Word timings	`timestamps: "word"`	`words[]` with `start` and `end` in seconds
Who said what	`diarize: true` and `timestamps: "word"`	`words[].speaker`, such as `speaker_0`
Subtitles	`subtitles: true`	`srt`, ready to save as a `.srt` file
Subtitles and word timings	`subtitles: true` and `timestamps: "word"`	`srt` and `words[]`
Sound tags	`tag_audio_events: true`	Tagged sounds in `text` and `words[]`

Price examples

Length	Price
1 minute	$0.00552
10 minutes	$0.0552
1 hour	$0.3312
2 hours	$0.6624

The gateway measures the audio from the file itself and rounds up to whole seconds after a 0.1-second allowance, with a minimum of 1 second. Options such as subtitles or diarize don’t change the price.

Synchronous audio endpoints reject Idempotency-Key. If a request times out, check your Console request logs before you retry. See Speech to text for every response field and error.

Overview

Text Series

Image Series

Video Series

Audio Series

Endpoint Reference

Task Management

Scribe v2

Request

Words, speakers, and subtitles

Price examples

​Request

​Words, speakers, and subtitles

​Price examples

Request

Words, speakers, and subtitles

Price examples