Speech Studio FAQ¶
Frequently asked questions about Speech Studio.
General¶
What is Speech Studio?¶
Speech Studio is a Windows desktop application that converts text to natural-sounding speech using Azure Cognitive Services. It offers 603 AI voices across 80+ languages, speech-to-text transcription, video dubbing, and advanced SSML control.
Does Speech Studio require an internet connection?¶
Yes. Text-to-speech and speech-to-text features require an internet connection to communicate with Azure Cognitive Services. However, your data is not stored on any external server -- once the audio is generated, the text is discarded.
What operating systems are supported?¶
Speech Studio runs on Windows 10 and later (64-bit). macOS and Linux are not currently supported.
Is there a free trial?¶
Yes. Speech Studio includes a free trial that lets you explore the features before purchasing. Visit the Speech Studio product page to download.
Voices and Languages¶
How many voices are available?¶
Speech Studio provides access to 603 AI neural voices from Azure Cognitive Services.
What languages are supported?¶
Over 80 languages and regional dialects are supported, including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, Hindi, Portuguese, and many more. See the Supported Languages guide for details.
Can I use multiple voices in one document?¶
Yes. Using SSML, you can switch between different voices within a single document. See SSML Support for instructions.
Do all voices support styles and emotions?¶
No. Style and emotion support varies by voice. Generally, the newest neural voices for major languages offer the widest range of styles. Check the Voice Styles & Emotions guide for details.
Privacy and Security¶
Is my text stored on external servers?¶
No. Your text is sent to Azure Cognitive Services for processing, but it is not stored, logged, or used for training purposes. Once the audio is generated, the text data is discarded.
Do I need my own Azure account?¶
No. Speech Studio includes Azure API keys with your license. You do not need to create a separate Azure account or manage API keys.
Licensing¶
How many devices can I activate on?¶
Each license key supports activation on a limited number of devices. If you need to switch devices, deactivate the license on the old machine first. See Activate License.
Can I use Speech Studio for commercial projects?¶
Yes. Audio generated with Speech Studio can be used for commercial purposes, including videos, podcasts, presentations, and other content. Review the End User License Agreement for full terms.
What happens when my license expires?¶
If your license has an expiration date, the app will continue to function in a limited capacity after expiration. Renew your license to restore full functionality.
Technical¶
What audio formats are supported for export?¶
Speech Studio exports audio in MP3, WAV, and OGG formats. See Audio Export Formats for details.
What video formats are supported for dubbing?¶
Video dubbing supports MP4, AVI, MKV, and MOV formats.
Can I process long documents?¶
Yes, though very long texts may take longer to convert. For best results with documents over several pages, consider using Batch Conversion to split the work into manageable segments.