Skip to main content Home Business intelligence Community, Social, and Gaming Customer Support Education Internal Communications Live and Remote Communications Readiness and Training Web Localization and Ecommerce More Solutions Text Translation Document Translation Custom Translator Translator Apps Office SharePoint Yammer Visual Studio Speech Translation Computer Vision Conversational Language Understanding More Languages Blog FAQ Text Translation Document Translation Custom Translator Other Cognitive Services Support Contact Confidentiality Attribution Machine Translation Customers Partners Partner Program Community Partners Try for free now Microsoft 365 Azure Copilot Windows Surface XBOX Deals Small Business Support Windows Apps Outlook OneDrive Microsoft Teams OneNote Microsoft Edge Moving from Skype to Teams Computers Shop XBOX Accessories VR & mixed reality Certified Refurbished Trade-in for cash XBOX Game Pass Ultimate PC Game Pass XBOX games PC games Microsoft AI Microsoft Security Dynamics 365 Microsoft 365 for business Microsoft Power Platform Windows 365 Small Business Digital Sovereignty Azure Microsoft Developer Microsoft Learn Support for AI marketplace apps Microsoft Tech Community Microsoft Marketplace Software companies Visual Studio Microsoft Rewards Free downloads & security Education Gift cards Licensing Unlocked stories View Sitemap

Microsoft Translator Blog

Customizable speech transcription, translation, and synthesis now available in the unified Speech service

Integrate speech into your apps, workflows, and websites using the unified Speech service, announced this week at Microsoft Build. Speech combines the capabilities of the existing Translator Speech API, Bing Speech API, and Custom Speech Service (preview) into a unified and fully customizable service.

You can now use the speech to text, speech translation, and text to speech services with the same subscription. All three services can be customized using the preview of the new custom speech, translator and voice features, also announced this week at //build:

  • Speech to Text (Speech Transcription) – converting spoken audio to text with default or custom models tailored to specific vocabulary or speaking styles of users (language model customization), or to better match the expected environment, such as with background noise (acoustic model customization). Speech to text technology enables a wide range of use cases like voice commands, real-time transcriptions, and call center log analysis.
  • Text to Speech (Speech Synthesis) – Bringing voice to any app by converting text to audio in near real time with the choice of over 75 default voices, or with the new custom voice models, creating a unique and recognizable brand voice tuned to your own recordings.
  • Speech Translation – providing real-time speech translation capabilities with models based on neural machine translation (NMT) technologies. Three elements of the Speech Translation pipeline can now be customized: speech recognition, text to speech and machine translation.

Neural translations with the newest version of the Translator text API (version 3), can also use custom systems built using the new Translator Custom feature.

The unified Speech service is currently offered as a preview. For speech translation requiring a service in General Availability, developers should continue to use the Microsoft Translator Speech API. Please follow the Microsoft Translator blog and Twitter page for continuing, up to date Microsoft Translator service announcements.

Learn more on the Cognitive Services blog.

 

Learn More

Microsoft Translator Speech Translation


English (United States)
Your Privacy Choices Opt-Out Icon Your Privacy Choices
Consumer Health Privacy Contact us Privacy Manage cookies Terms of use Trademarks About our ads