Speech to Text

Transcribe audio to text

POST /v1/asr

Speech to Text

cURL

curl --request POST \
  --url https://api.fish.audio/v1/asr \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form audio='@example-file' \
  --form 'language=<string>' \
  --form ignore_timestamps=true

import requests

url = "https://api.fish.audio/v1/asr"

files = { "audio": ("example-file", open("example-file", "rb")) }
payload = {
    "language": "<string>",
    "ignore_timestamps": "true"
}
headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const form = new FormData();
form.append('audio', '<string>');
form.append('language', '<string>');
form.append('ignore_timestamps', 'true');

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

options.body = form;

fetch('https://api.fish.audio/v1/asr', 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.fish.audio/v1/asr",
  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=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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=\"ignore_timestamps\"\r\n\r\ntrue\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.fish.audio/v1/asr"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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=\"ignore_timestamps\"\r\n\r\ntrue\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.fish.audio/v1/asr")
  .header("Authorization", "Bearer <token>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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=\"ignore_timestamps\"\r\n\r\ntrue\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.fish.audio/v1/asr")

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=\"audio\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\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=\"ignore_timestamps\"\r\n\r\ntrue\r\n-----011000010111000001101001--"

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

200

{
  "text": "<string>",
  "duration": 123,
  "segments": [
    {
      "text": "<string>",
      "start": 123,
      "end": 123
    }
  ]
}

{
  "status": 123,
  "message": "<string>"
}

{
  "status": 123,
  "message": "<string>"
}

[
  {
    "loc": [
      "<string>"
    ],
    "type": "<string>",
    "msg": "<string>",
    "ctx": "<string>"
  }
]

This BETA endpoint only accepts application/form-data and application/msgpack.

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-dataapplication/msgpack

audio · file · required

Audio to be converted to text

language · string | null

Language to be used for the speech

ignore_timestamps · boolean · default: true

Whether to return precise timestamps in the text, this will increase the latency in audio shorter than 30 seconds

Response

200

application/json

Request fulfilled, document follows

text · string · required

duration · number · required

Duration of the audio in seconds

segments · ASRSegment · object[] · required

Show child attributes