Text to speech REST API

The Speech service allows you to convert text into synthesized speech and get a list of supported voices for a region by using a REST API. In this article, you learn about authorization options, query options, how to structure a request, and how to interpret a response.

The text to speech REST API supports neural text to speech voices in many locales. Each available endpoint is associated with a region. A Speech resource key for the endpoint or region that you plan to use is required. Here are links to more information:

• For a complete list of voices, see Language and voice support for the Speech service.
• For information about regional availability, see Speech service supported regions.
• For Microsoft Azure operated by 21Vianet endpoints, see this article about sovereign cloud.

Before you use the text to speech REST API, understand that you need to complete a token exchange as part of authentication to access the service. For more information, see Authentication.

Get a list of voices

You can use the tts.speech.azure.cn/cognitiveservices/voices/list endpoint to get a full list of voices for a specific region or endpoint. Prefix the voices list endpoint with a region to get a list of voices for that region. For example, to get a list of voices for the chinanorth2 region, use the https://chinanorth2.tts.speech.azure.cn/cognitiveservices/voices/list endpoint. For a list of all supported regions, see the regions documentation.

Request headers

This table lists required and optional headers for text to speech requests:

Request body

A body isn't required for GET requests to this endpoint.

Sample request

This request requires only an authorization header:

GET /cognitiveservices/voices/list HTTP/1.1

Host: chinaeast2.tts.speech.azure.cn
Ocp-Apim-Subscription-Key: YOUR_RESOURCE_KEY

Here's an example curl command:

curl --location --request GET 'https://YOUR_RESOURCE_REGION.tts.speech.azure.cn/cognitiveservices/voices/list' \
--header 'Ocp-Apim-Subscription-Key: YOUR_RESOURCE_KEY'

Sample response

You should receive a response with a JSON body that includes all supported locales, voices, gender, styles, and other details. The WordsPerMinute property for each voice can be used to estimate the length of the output speech. This JSON example shows partial results to illustrate the structure of a response:

[  
    // Redacted for brevity
    {
        "Name": "Microsoft Server Speech Text to Speech Voice (en-US, JennyNeural)",
        "DisplayName": "Jenny",
        "LocalName": "Jenny",
        "ShortName": "en-US-JennyNeural",
        "Gender": "Female",
        "Locale": "en-US",
        "LocaleName": "English (United States)",
        "StyleList": [
          "assistant",
          "chat",
          "customerservice",
          "newscast",
          "angry",
          "cheerful",
          "sad",
          "excited",
          "friendly",
          "terrified",
          "shouting",
          "unfriendly",
          "whispering",
          "hopeful"
        ],
        "SampleRateHertz": "24000",
        "VoiceType": "Neural",
        "Status": "GA",
        "ExtendedPropertyMap": {
          "IsHighQuality48K": "True"
        },
        "WordsPerMinute": "152"
    },
    // Redacted for brevity
    {
        "Name": "Microsoft Server Speech Text to Speech Voice (en-US, JennyMultilingualNeural)",
        "DisplayName": "Jenny Multilingual",
        "LocalName": "Jenny Multilingual",
        "ShortName": "en-US-JennyMultilingualNeural",
        "Gender": "Female",
        "Locale": "en-US",
        "LocaleName": "English (United States)",
        "SecondaryLocaleList": [
          "de-DE",
          "en-AU",
          "en-CA",
          "en-GB",
          "es-ES",
          "es-MX",
          "fr-CA",
          "fr-FR",
          "it-IT",
          "ja-JP",
          "ko-KR",
          "pt-BR",
          "zh-cn"
        ],
        "SampleRateHertz": "24000",
        "VoiceType": "Neural",
        "Status": "GA",
        "WordsPerMinute": "190"
    },
    // Redacted for brevity
    {
        "Name": "Microsoft Server Speech Text to Speech Voice (ga-IE, OrlaNeural)",
        "DisplayName": "Orla",
        "LocalName": "Orla",
        "ShortName": "ga-IE-OrlaNeural",
        "Gender": "Female",
        "Locale": "ga-IE",
        "LocaleName": "Irish (Ireland)",
        "SampleRateHertz": "24000",
        "VoiceType": "Neural",
        "Status": "GA",
        "WordsPerMinute": "139"
    },
    // Redacted for brevity
    {
        "Name": "Microsoft Server Speech Text to Speech Voice (zh-cn, YunxiNeural)",
        "DisplayName": "Yunxi",
        "LocalName": "云希",
        "ShortName": "zh-cn-YunxiNeural",
        "Gender": "Male",
        "Locale": "zh-cn",
        "LocaleName": "Chinese (Mandarin, Simplified)",
        "StyleList": [
          "narration-relaxed",
          "embarrassed",
          "fearful",
          "cheerful",
          "disgruntled",
          "serious",
          "angry",
          "sad",
          "depressed",
          "chat",
          "assistant",
          "newscast"
        ],
        "SampleRateHertz": "24000",
        "VoiceType": "Neural",
        "Status": "GA",
        "RolePlayList": [
          "Narrator",
          "YoungAdultMale",
          "Boy"
        ],
        "WordsPerMinute": "293"
    },
    // Redacted for brevity
]

HTTP status codes

The HTTP status code for each response indicates success or common errors.

Convert text to speech

The cognitiveservices/v1 endpoint allows you to convert text to speech by using Speech Synthesis Markup Language (SSML).

Regions and endpoints

These regions are supported for text to speech through the REST API. Be sure to select the endpoint that matches your Speech resource region.

Prebuilt neural voices

Use this table to determine availability of neural voices by region or endpoint:

Request headers

This table lists required and optional headers for text to speech requests:

Request body

The body of each POST request is sent as SSML. SSML allows you to choose the voice and language of the synthesized speech that the text-to-speech feature returns. For a complete list of supported voices, see Language and voice support for the Speech service.

Sample request

This HTTP request uses SSML to specify the voice and language. If the body length is long, and the resulting audio exceeds 10 minutes, it's truncated to 10 minutes. In other words, the audio length can't exceed 10 minutes.

POST /cognitiveservices/v1 HTTP/1.1

X-Microsoft-OutputFormat: riff-24khz-16bit-mono-pcm
Content-Type: application/ssml+xml
Host: chinaeast2.tts.speech.azure.cn
Content-Length: <Length>
Authorization: Bearer [Base64 access_token]
User-Agent: <Your application name>

<speak version='1.0' xml:lang='en-US'><voice xml:lang='en-US' xml:gender='Male'
    name='en-US-ChristopherNeural'>
        I'm excited to try text to speech!
</voice></speak>

^* For the Content-Length, you should use your own content length. In most cases, this value is calculated automatically.

HTTP status codes

The HTTP status code for each response indicates success or common errors:

If the HTTP status is 200 OK, the body of the response contains an audio file in the requested format. This file can be played as it's transferred, saved to a buffer, or saved to a file.

Audio outputs

The supported streaming and nonstreaming audio formats are sent in each request as the X-Microsoft-OutputFormat header. Each format incorporates a bit rate and encoding type. The Speech service supports 48-kHz, 24-kHz, 16-kHz, and 8-kHz audio outputs. Each prebuilt neural voice model is available at 24kHz and high-fidelity 48kHz.

amr-wb-16000hz
audio-16khz-16bit-32kbps-mono-opus
audio-16khz-32kbitrate-mono-mp3
audio-16khz-64kbitrate-mono-mp3
audio-16khz-128kbitrate-mono-mp3
audio-24khz-16bit-24kbps-mono-opus
audio-24khz-16bit-48kbps-mono-opus
audio-24khz-48kbitrate-mono-mp3
audio-24khz-96kbitrate-mono-mp3
audio-24khz-160kbitrate-mono-mp3
audio-48khz-96kbitrate-mono-mp3
audio-48khz-192kbitrate-mono-mp3
ogg-16khz-16bit-mono-opus
ogg-24khz-16bit-mono-opus
ogg-48khz-16bit-mono-opus
raw-8khz-8bit-mono-alaw
raw-8khz-8bit-mono-mulaw
raw-8khz-16bit-mono-pcm
raw-16khz-16bit-mono-pcm
raw-16khz-16bit-mono-truesilk
raw-22050hz-16bit-mono-pcm
raw-24khz-16bit-mono-pcm
raw-24khz-16bit-mono-truesilk
raw-44100hz-16bit-mono-pcm
raw-48khz-16bit-mono-pcm
webm-16khz-16bit-mono-opus
webm-24khz-16bit-24kbps-mono-opus
webm-24khz-16bit-mono-opus

riff-8khz-8bit-mono-alaw
riff-8khz-8bit-mono-mulaw
riff-8khz-16bit-mono-pcm
riff-22050hz-16bit-mono-pcm
riff-24khz-16bit-mono-pcm
riff-44100hz-16bit-mono-pcm
riff-48khz-16bit-mono-pcm

Authentication

Each request requires an authorization header. This table illustrates which headers are supported for each feature:

When you're using the Ocp-Apim-Subscription-Key header, only your resource key must be provided. For example:

'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'

When you're using the Authorization: Bearer header, you need to make a request to the issueToken endpoint. In this request, you exchange your resource key for an access token that's valid for 10 minutes.

Another option is to use Microsoft Entra authentication that also uses the Authorization: Bearer header, but with a token issued via Microsoft Entra ID. See Use Microsoft Entra authentication.

How to get an access token

To get an access token, you need to make a request to the issueToken endpoint by using Ocp-Apim-Subscription-Key and your resource key.

The issueToken endpoint has this format:

https://<REGION_IDENTIFIER>.api.cognitive.azure.cn/sts/v1.0/issueToken

Replace <REGION_IDENTIFIER> with the identifier that matches the region of your subscription.

Use the following samples to create your access token request.

HTTP sample

This example is a simple HTTP request to get a token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. If your subscription isn't in the China East 2 region, replace the Host header with your region's host name.

POST /sts/v1.0/issueToken HTTP/1.1
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY
Host: chinaeast2.api.cognitive.azure.cn
Content-type: application/x-www-form-urlencoded
Content-Length: 0

The body of the response contains the access token in JSON Web Token (JWT) format.

PowerShell sample

This example is a simple PowerShell script to get an access token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to China East 2.

$FetchTokenHeader = @{
  'Content-type'='application/x-www-form-urlencoded';
  'Content-Length'= '0';
  'Ocp-Apim-Subscription-Key' = 'YOUR_SUBSCRIPTION_KEY'
}

$OAuthToken = Invoke-RestMethod -Method POST -Uri https://chinaeast2.api.cognitive.azure.cn/sts/v1.0/issueToken
 -Headers $FetchTokenHeader

# show the token received
$OAuthToken

cURL sample

cURL is a command-line tool available in Linux (and in the Windows Subsystem for Linux). This cURL command illustrates how to get an access token. Replace YOUR_SUBSCRIPTION_KEY with your resource key for the Speech service. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to China East 2.

curl -v -X POST \
 "https://chinaeast2.api.cognitive.azure.cn/sts/v1.0/issueToken" \
 -H "Content-type: application/x-www-form-urlencoded" \
 -H "Content-Length: 0" \
 -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

C# sample

This C# class illustrates how to get an access token. Pass your resource key for the Speech service when you instantiate the class. If your subscription isn't in the China East 2 region, change the value of FetchTokenUri to match the region for your subscription.

public class Authentication
{
    public static readonly string FetchTokenUri =
        "https://chinaeast2.api.cognitive.azure.cn/sts/v1.0/issueToken";
    private string subscriptionKey;
    private string token;

    public Authentication(string subscriptionKey)
    {
        this.subscriptionKey = subscriptionKey;
        this.token = FetchTokenAsync(FetchTokenUri, subscriptionKey).Result;
    }

    public string GetAccessToken()
    {
        return this.token;
    }

    private async Task<string> FetchTokenAsync(string fetchUri, string subscriptionKey)
    {
        using (var client = new HttpClient())
        {
            client.DefaultRequestHeaders.Add("Ocp-Apim-Subscription-Key", subscriptionKey);
            UriBuilder uriBuilder = new UriBuilder(fetchUri);

            var result = await client.PostAsync(uriBuilder.Uri.AbsoluteUri, null);
            Console.WriteLine("Token Uri: {0}", uriBuilder.Uri.AbsoluteUri);
            return await result.Content.ReadAsStringAsync();
        }
    }
}

Python sample

# Request module must be installed.
# Run pip install requests if necessary.
import requests

subscription_key = 'REPLACE_WITH_YOUR_KEY'


def get_token(subscription_key):
    fetch_token_url = 'https://chinaeast2.api.cognitive.azure.cn/sts/v1.0/issueToken'
    headers = {
        'Ocp-Apim-Subscription-Key': subscription_key
    }
    response = requests.post(fetch_token_url, headers=headers)
    access_token = str(response.text)
    print(access_token)

How to use an access token

The access token should be sent to the service as the Authorization: Bearer <TOKEN> header. Each access token is valid for 10 minutes. You can get a new token at any time, but to minimize network traffic and latency, we recommend using the same token for nine minutes.

Here's a sample HTTP request to the Speech to text REST API for short audio:

POST /cognitiveservices/v1 HTTP/1.1
Authorization: Bearer YOUR_ACCESS_TOKEN
Host: chinaeast2.stt.speech.azure.cn
Content-type: application/ssml+xml
Content-Length: 199
Connection: Keep-Alive

// Message body here...

Use Microsoft Entra authentication

To use Microsoft Entra authentication with the Speech to text REST API for short audio, you need to create an access token. The steps to obtain the access token consisting of Resource ID and Microsoft Entra access token are the same as when using the Speech SDK. Follow the steps here Use Microsoft Entra authentication

After the resource ID and the Microsoft Entra access token were obtained, the actual access token can be constructed following this format:

aad#YOUR_RESOURCE_ID#YOUR_MICROSOFT_ENTRA_ACCESS_TOKEN

You need to include the "aad#" prefix and the "#" (hash) separator between resource ID and the access token.

Here's a sample HTTP request to the Speech to text REST API for short audio:

POST /cognitiveservices/v1 HTTP/1.1
Authorization: Bearer YOUR_ACCESS_TOKEN
Host: chinanorth.stt.speech.azure.cn
Content-type: application/ssml+xml
Content-Length: 199
Connection: Keep-Alive

// Message body here...

To learn more about Microsoft Entra access tokens, including token lifetime, visit Access tokens in the Microsoft identity platform.

Next steps

• Create a Azure account