Transcribers

List Transcribers

curl --request GET \
  --url https://api.vocily.ai/v1/transcribers \
  --header 'Authorization: Bearer <token>'

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

fetch('https://api.vocily.ai/v1/transcribers', 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.vocily.ai/v1/transcribers",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.vocily.ai/v1/transcribers"

	req, _ := http.NewRequest("GET", url, nil)

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

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.vocily.ai/v1/transcribers")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

[
  {
    "provider": "soniox",
    "model": "soniox",
    "label": "Soniox",
    "languages": [
      "bn-IN",
      "de-DE"
    ],
    "response_speed_seconds": {
      "fast": 0.45,
      "responsive": 0.75,
      "balanced": 1.05,
      "patient": 1.65
    }
  },
  {
    "provider": "deepgram",
    "model": "nova-2",
    "label": "Nova 2",
    "languages": [
      "de-DE",
      "en-GB"
    ],
    "response_speed_seconds": {
      "fast": 0.6,
      "responsive": 0.65,
      "balanced": 0.75,
      "patient": 0.85
    }
  }
]

{
  "detail": "Invalid API key",
  "code": "UNAUTHORIZED"
}

{
  "detail": {
    "code": "validation_error",
    "message": "<string>",
    "errors": [
      {
        "field": "<string>",
        "message": "<string>",
        "type": "<string>"
      }
    ]
  },
  "code": "VALIDATION_ERROR"
}

{
  "code": "rate_limited"
}

List Transcribers

curl --request GET \
  --url https://api.vocily.ai/v1/transcribers \
  --header 'Authorization: Bearer <token>'

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

fetch('https://api.vocily.ai/v1/transcribers', 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.vocily.ai/v1/transcribers",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.vocily.ai/v1/transcribers"

	req, _ := http.NewRequest("GET", url, nil)

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

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.vocily.ai/v1/transcribers")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

[
  {
    "provider": "soniox",
    "model": "soniox",
    "label": "Soniox",
    "languages": [
      "bn-IN",
      "de-DE"
    ],
    "response_speed_seconds": {
      "fast": 0.45,
      "responsive": 0.75,
      "balanced": 1.05,
      "patient": 1.65
    }
  },
  {
    "provider": "deepgram",
    "model": "nova-2",
    "label": "Nova 2",
    "languages": [
      "de-DE",
      "en-GB"
    ],
    "response_speed_seconds": {
      "fast": 0.6,
      "responsive": 0.65,
      "balanced": 0.75,
      "patient": 0.85
    }
  }
]

{
  "detail": "Invalid API key",
  "code": "UNAUTHORIZED"
}

{
  "detail": {
    "code": "validation_error",
    "message": "<string>",
    "errors": [
      {
        "field": "<string>",
        "message": "<string>",
        "type": "<string>"
      }
    ]
  },
  "code": "VALIDATION_ERROR"
}

{
  "code": "rate_limited"
}

response_speed_seconds gives the typical wait from the caller’s last word to text in hand, per preset, for that model — the same preset costs more on one engine than another. It is null on a model that answers on confidence rather than on a clock: the preset still applies there and still matters, but no number describes it, so none is given. Check for null before reading a preset off it. Its four keys are the four presets conversation.response_eagerness accepts, and nothing else is a valid value:

Preset	Send as	Meaning
Fast	`1`	Least patient. Short answers and quick confirmations.
Responsive	`0.75`	Everyday conversations.
Balanced	`0.5`	The default.
Patient	`0`	Callers who pause mid-sentence, or read out numbers and addresses.

The field is a number because that is what it is stored as, but only these four numbers exist — a value like 0.3 is rejected rather than rounded, so what you send is always what the call does. languages is what the model can recognise. Every language in an agent’s set must be covered, or the agent is refused on save.

Authorizations

Authorization

string

header

required

Your API key as a Bearer token, e.g. Authorization: Bearer vk_….

Response

Speech models you can put in transcriber.model.

provider

enum<string>

Available options:

sarvam,

deepgram,

soniox

model

string

What goes in transcriber.model.

label

string

languages

string[]

Every language in an agent's set must be covered, or the agent is refused on save.

response_speed_seconds

object | null

Typical caller-stops-to-text seconds per response_eagerness preset, for THIS model. Null on a model that answers on confidence rather than on a clock — the preset still applies there, but no number describes it, so none is given. Check for null before reading a preset off it.

Show child attributes

Calls

Chats

Phone Numbers

Knowledge Bases

Agents

Catalogues

Integrations

Custom Analysis

Memory

Widget

Webhooks

Authorizations

Response