Microsoft Text Speech Voice S
- Microsoft Text To Speech Voices For Windows 7
- Microsoft Server Speech Text To Speech Voice (en-us Helen)
To unlock extra Text to Speech voices in Windows 10, do the following. Open the Registry Editor app. Go to the following Registry key. HKEYLOCALMACHINE SOFTWARE Microsoft SpeechOneCore Voices Tokens. See how to go to a Registry key with one click. Here you will see the list of voices installed in your Windows 10.
I am using windows 10 and want to get more voices for Microsoft at the moment I only have two options: microsoft Hazel and microsoft Zira. Does anyone know how I can get more options?
SDsolar2 Answers
Does anyone know how I can get more voices?
You can download some more voices from many free TTS voices (which may not be so good). One of the sources for downloading free Microsoft and LTS TTS voices is Zero2000. You can also purchase very high quality TTS voices for Windows from companies like Ivona, Cepstral or CereProc.
Source Choose Text-to-Speech Voice in Windows 10
DavidPostill♦DavidPostillNarrator for Windows (all versions) has a few built-in options for male and female voices.
To set Narrator voice options (Microsoft)
Here is a good source for more voices:
Best Free Windows Narrator Voices You Can Use (Zero2000.com)
Excerpt:
In the world of today, more and more people use the text to speech computer technology to free their eyes and save time. As a vital component of the text to speech technology, voices, i.e. speech engines, are the core of text to speech software. Because text to speech software need to invoke voices to synthetic speech and output spoken audio.
There are many voices available on the Internet today, such as AT&T Natural Voices, Cepstral voices, IVONA voices, CereProc voices, NeoSpeech voices, etc. But most of these voices are commercial and the prices are even higher than the prices of normal text-to-speech software. For example, the prices of AT&T Natural Voices are $35 (base required) plus $35 per additional voice, and the prices of Cepstral voices are &29.99 per voice.
Fortunately, there are also enough high-quality free voices we can use. Most of them are compatible with the Microsoft SAPI 4 or SAPI 5. Generally, the higher SAPI version, the better quality.
Here is the free voices list sorted by the recommended degree.
Microsoft Mike, Mary and Sam -
Microsoft Sam is the default English male voice shipped with Microsoft Windows 2000 and Windows XP. Though not the default, Microsoft Sam is also available in Windows Vista Home Premium. It is used by Narrator, the screen reader program built into the operating system.
Microsoft Mike and Microsoft Mary are optional male and female voices respectively with better quality, available for download from the Microsoft website or other third party text-to-speech related websites.
The most noticeable feature of these three voices is there are both SAPI 4 and SAPI 5 versions of them. SAPI 5 voices are only available on Windows 2000 and later Windows NT-based operating systems. As an exception, the SAPI 5 versions of these voices cannot be installed on Windows Vista and Windows 7. The SAPI 4 versions are more compatible. They can be installed and used on Windows 98 and all the later Windows operating systems.
Microsoft Anna -
Microsoft Anna is the default English voice shipped with Windows Vista and Windows 7. Microsoft Anna is a SAPI 5-only voice and is designed to sound more natural than the previous system default voice Microsoft Sam.
This excellent female voice is base on the new Microsoft SAPI 5.3/5.4. So you cannot use it on Windows XP directly and also there is no standalone installer of this voice on the Microsoft website. The only way to use this fantastic voice on Windows XP is by the Microsoft Streets & Trips. The Microsoft Streets & Trips 2006 and later versions install the voice and the new Microsoft SAPI onto Windows XP computers for the voice-prompt direction feature.
Some third party text-to-speech related websites supply smaller repacked Microsoft Anna installers for Windows XP users. However, it's incomplete and not working correctly on Windows XP because the SAPI version of Windows XP is 5.1.
Lernout & Hauspie Voices -
Lernout & Hauspie Speech Products, or L&H, was a leading Belgium-based speech recognition technology company. This company released dozens of high-quality SAPI 4 voices across multiple languages, including ten American English voices and two British English voices.
In addition, Lernout & Hauspie Michael and Michelle are also optional male and female voices licensed by Microsoft from Lernout & Hauspie, and available through Microsoft Office XP and Microsoft Office 2003 or Microsoft Reader.
Most of the above voices can be found on the Microsoft's website or downloaded directly from the 2nd Speech Center web site. Click here to download them immediately. Windows xp home edition product key.
Mokubai♦Not the answer you're looking for? Browse other questions tagged windowstext-to-speechtext-to-speech-voicesnarrator or ask your own question.
-->The Speech Services allow you to convert text into synthesized speech and get a list of supported voices for a region using a set of REST APIs. Each available endpoint is associated with a region. A subscription key for the endpoint/region you plan to use is required.
The text-to-speech REST API supports neural and standard text-to-speech voices, each of which supports a specific language and dialect, identified by locale.
- For a complete list of voices, see language support.
- For information about regional availability, see regions.
Important
Costs vary for standard, custom, and neural voices. For more information, see Pricing.
Before using this API, understand:
- The text-to-speech REST API requires an Authorization header. This means that you need to complete a token exchange to access the service. For more information, see Authentication.
Authentication
Each request requires an authorization header. This table illustrates which headers are supported for each service:
| Supported authorization headers | Speech-to-text | Text-to-speech |
|---|---|---|
| Ocp-Apim-Subscription-Key | Yes | No |
| Authorization: Bearer | Yes | Yes |
Microsoft Text To Speech Voices For Windows 7
When using the Ocp-Apim-Subscription-Key header, you're only required to provide your subscription key. For example:
When using the Authorization: Bearer header, you're required to make a request to the issueToken endpoint. In this request, you exchange your subscription key for an access token that's valid for 10 minutes. In the next few sections you'll learn how to get a token, and use a token.
How to get an access token
To get an access token, you'll need to make a request to the issueToken endpoint using the Ocp-Apim-Subscription-Key and your subscription key.
These regions and endpoints are supported:
| Region | Token service endpoint |
|---|---|
| Australia East | https://australiaeast.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| Canada Central | https://canadacentral.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| Central US | https://centralus.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| East Asia | https://eastasia.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| East US | https://eastus.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| East US 2 | https://eastus2.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| France Central | https://francecentral.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| India Central | https://centralindia.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| Japan East | https://japaneast.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| Korea Central | https://koreacentral.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| North Central US | https://northcentralus.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| North Europe | https://northeurope.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| South Central US | https://southcentralus.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| Southeast Asia | https://southeastasia.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| UK South | https://uksouth.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| West Europe | https://westeurope.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| West US | https://westus.api.cognitive.microsoft.com/sts/v1.0/issueToken |
| West US 2 | https://westus2.api.cognitive.microsoft.com/sts/v1.0/issueToken |
Use these 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 Speech Service subscription key. If your subscription isn't in the West US region, replace the Host header with your region's host name.
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 Speech Service subscription key. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to West US.
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 Speech Service subscription key. Make sure to use the correct endpoint for the region that matches your subscription. This example is currently set to West US.
C# sample
This C# class illustrates how to get an access token. Pass your Speech Service subscription key when you instantiate the class. If your subscription isn't in the West US region, change the value of FetchTokenUri to match the region for your subscription.
Python sample
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, however, to minimize network traffic and latency, we recommend using the same token for nine minutes.
Here's a sample HTTP request to the text-to-speech REST API:
Get a list of voices
The voices/list endpoint allows you to get a full list of voices for a specific region/endpoint.
Regions and endpoints
| Region | Endpoint |
|---|---|
| Australia East | https://australiaeast.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Brazil South | https://brazilsouth.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Canada Central | https://canadacentral.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Central US | https://centralus.tts.speech.microsoft.com/cognitiveservices/voices/list |
| East Asia | https://eastasia.tts.speech.microsoft.com/cognitiveservices/voices/list |
| East US | https://eastus.tts.speech.microsoft.com/cognitiveservices/voices/list |
| East US 2 | https://eastus2.tts.speech.microsoft.com/cognitiveservices/voices/list |
| France Central | https://francecentral.tts.speech.microsoft.com/cognitiveservices/voices/list |
| India Central | https://centralindia.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Japan East | https://japaneast.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Korea Central | https://koreacentral.tts.speech.microsoft.com/cognitiveservices/voices/list |
| North Central US | https://northcentralus.tts.speech.microsoft.com/cognitiveservices/voices/list |
| North Europe | https://northeurope.tts.speech.microsoft.com/cognitiveservices/voices/list |
| South Central US | https://southcentralus.tts.speech.microsoft.com/cognitiveservices/voices/list |
| Southeast Asia | https://southeastasia.tts.speech.microsoft.com/cognitiveservices/voices/list |
| UK South | https://uksouth.tts.speech.microsoft.com/cognitiveservices/voices/list |
| West Europe | https://westeurope.tts.speech.microsoft.com/cognitiveservices/voices/list |
| West US | https://westus.tts.speech.microsoft.com/cognitiveservices/voices/list |
| West US 2 | https://westus2.tts.speech.microsoft.com/cognitiveservices/voices/list |
Request headers
This table lists required and optional headers for text-to-speech requests.
| Header | Description | Required / Optional |
|---|---|---|
Authorization | An authorization token preceded by the word Bearer. For more information, see Authentication. | Required |
Request body
A body isn't required for GET requests to this endpoint.
Sample request
This request only requires an authorization header.
Sample response
Microsoft Server Speech Text To Speech Voice (en-us Helen)
This response has been truncated to illustrate the structure of a response.
HTTP status codes
The HTTP status code for each response indicates success or common errors.
| HTTP status code | Description | Possible reason |
|---|---|---|
| 200 | OK | The request was successful. |
| 400 | Bad Request | A required parameter is missing, empty, or null. Or, the value passed to either a required or optional parameter is invalid. A common issue is a header that is too long. |
| 401 | Unauthorized | The request is not authorized. Check to make sure your subscription key or token is valid and in the correct region. |
| 429 | Too Many Requests | You have exceeded the quota or rate of requests allowed for your subscription. |
| 502 | Bad Gateway | Network or server-side issue. May also indicate invalid headers. |
Convert text-to-speech
The v1 endpoint allows you to convert text-to-speech using Speech Synthesis Markup Language (SSML).
Regions and endpoints
These regions are supported for text-to-speech using the REST API. Make sure that you select the endpoint that matches your subscription region.
Standard and neural voices
Use this table to determine availability of standard and neural voices by region/endpoint:
| Region | Endpoint | Standard Voices | Neural Voices |
|---|---|---|---|
| Australia East | https://australiaeast.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| Canada Central | https://canadacentral.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| Central US | https://centralus.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| East Asia | https://eastasia.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| East US | https://eastus.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| East US 2 | https://eastus2.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| France Central | https://francecentral.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| India Central | https://centralindia.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| Japan East | https://japaneast.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| Korea Central | https://koreacentral.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| North Central US | https://northcentralus.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| North Europe | https://northeurope.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| South Central US | https://southcentralus.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| Southeast Asia | https://southeastasia.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| UK South | https://uksouth.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| West Europe | https://westeurope.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
| West US | https://westus.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | No |
| West US 2 | https://westus2.tts.speech.microsoft.com/cognitiveservices/v1 | Yes | Yes |
Custom voices
If you've created a custom voice font, use the endpoint that you've created. You can also use the endpoints listed below, replacing the {deploymentId} with the deployment ID for your voice model.
| Region | Endpoint |
|---|---|
| Australia East | https://australiaeast.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| Canada Central | https://canadacentral.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| Central US | https://centralus.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| East Asia | https://eastasia.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| East US | https://eastus.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| East US 2 | https://eastus2.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| France Central | https://francecentral.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| India Central | https://centralindia.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| Japan East | https://japaneast.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| Korea Central | https://koreacentral.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| North Central US | https://northcentralus.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| North Europe | https://northeurope.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| South Central US | https://southcentralus.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| Southeast Asia | https://southeastasia.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| UK South | https://uksouth.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| West Europe | https://westeurope.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| West US | https://westus.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
| West US 2 | https://westus2.voice.speech.microsoft.com/cognitiveservices/v1?deploymentId={deploymentId} |
Request headers
This table lists required and optional headers for text-to-speech requests.
| Header | Description | Required / Optional |
|---|---|---|
Authorization | An authorization token preceded by the word Bearer. For more information, see Authentication. | Required |
Content-Type | Specifies the content type for the provided text. Accepted value: application/ssml+xml. | Required |
X-Microsoft-OutputFormat | Specifies the audio output format. For a complete list of accepted values, see audio outputs. | Required |
User-Agent | The application name. The value provided must be less than 255 characters. | Required |
Audio outputs
This is a list of supported audio formats that are sent in each request as the X-Microsoft-OutputFormat header. Each incorporates a bitrate and encoding type. The Speech Services supports 24 kHz, 16 kHz, and 8 kHz audio outputs.
raw-16khz-16bit-mono-pcm | raw-8khz-8bit-mono-mulaw |
riff-8khz-8bit-mono-alaw | riff-8khz-8bit-mono-mulaw |
riff-16khz-16bit-mono-pcm | audio-16khz-128kbitrate-mono-mp3 |
audio-16khz-64kbitrate-mono-mp3 | audio-16khz-32kbitrate-mono-mp3 |
raw-24khz-16bit-mono-pcm | riff-24khz-16bit-mono-pcm |
audio-24khz-160kbitrate-mono-mp3 | audio-24khz-96kbitrate-mono-mp3 |
audio-24khz-48kbitrate-mono-mp3 |
Note
If your selected voice and output format have different bit rates, the audio is resampled as necessary. However, 24 kHz voices do not support audio-16khz-16kbps-mono-siren and riff-16khz-16kbps-mono-siren output formats.
Request body
The body of each POST request is sent as Speech Synthesis Markup Language (SSML). SSML allows you to choose the voice and language of the synthesized speech returned by the text-to-speech service. For a complete list of supported voices, see language support.
Note
If using a custom voice, the body of a request can be sent as plain text (ASCII or UTF-8).
Sample request
This HTTP request uses SSML to specify the voice and language. The body cannot exceed 1,000 characters.
See our quickstarts for language-specific examples:
HTTP status codes
The HTTP status code for each response indicates success or common errors.
| HTTP status code | Description | Possible reason |
|---|---|---|
| 200 | OK | The request was successful; the response body is an audio file. |
| 400 | Bad Request | A required parameter is missing, empty, or null. Or, the value passed to either a required or optional parameter is invalid. A common issue is a header that is too long. |
| 401 | Unauthorized | The request is not authorized. Check to make sure your subscription key or token is valid and in the correct region. |
| 413 | Request Entity Too Large | The SSML input is longer than 1024 characters. |
| 415 | Unsupported Media Type | It's possible that the wrong Content-Type was provided. Content-Type should be set to application/ssml+xml. |
| 429 | Too Many Requests | You have exceeded the quota or rate of requests allowed for your subscription. |
| 502 | Bad Gateway | Network or server-side issue. May also indicate invalid headers. |
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.