What languages are supported for Streaming Speech-to-text?
Current Supported Language
By default, Universal-Streaming is set to transcribe English audio. We also have a multilingual streaming model that supports English, Spanish, French, German, Italian, and Portuguese. Check out this section of our documentation to learn more.
Difference from Async STT
It’s important to note that the language_code parameter mentioned in some AssemblyAI documentation applies to the Async STT (Asynchronous Speech-to-Text) feature, not the Streaming Transcription feature. For streaming STT, you would specify the multilingual model using the speech_model parameter as shown here.
Future Language Support
AssemblyAI plans to add support for additional languages in later in 2025 and early in 2026. To stay informed about new features and improvements, including language support updates, you can follow our Changelog.
If you require support for a specific language for streaming transcription, please contact AssemblyAI’s support team. They can pass your request to the Product team for consideration in future updates.
