For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundChangelogSign In
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
OverviewAPI ReferencePre-recorded STTStreaming STTVoice AgentsSpeech UnderstandingGuardrailsLLM GatewayFAQ
  • Overview
      • Can I use speaker diarization with Streaming Speech-to-Text?
      • How accurate is your Streaming transcription compared to Async transcription?
      • How does automatically scaling concurrency for Streaming STT work?
      • How does Universal Streaming session-based pricing work?
      • What languages are supported for Streaming Speech-to-text?
      • Resolving SSL Certificate Verification Error When Trying to Use Streaming STT
      • I am getting a "Model deprecated. See docs for new model information" error message. What does it mean?
LogoLogo
PlaygroundChangelogSign In
On this page
  • Available Models and Language Support
  • Choosing the Right Model
  • Difference From Pre-recorded STT
OverviewStreaming audio

What languages are supported for Streaming Speech-to-text?

Was this page helpful?
Previous

Resolving SSL Certificate Verification Error When Trying to Use Streaming STT

Next
Built with

Language support for Streaming STT depends on the model you select. AssemblyAI offers several streaming models with different language capabilities:

Available Models and Language Support

ModelLanguages Supported
Universal-3 Pro StreamingEnglish, Spanish, German, French, Portuguese, Italian (native code switching)
Universal-Streaming EnglishEnglish only
Universal-Streaming MultilingualEnglish, Spanish, German, French, Portuguese, Italian (per turn)
Whisper Streaming99+ languages (auto-detected)

Choosing the Right Model

  • If you need the highest accuracy with multilingual code switching support, use Universal-3 Pro Streaming (u3-rt-pro).
  • If you only need English transcription at the lowest cost, use Universal-Streaming English (universal-streaming-english).
  • If you need multilingual support at a lower cost, use Universal-Streaming Multilingual (universal-streaming-multilingual).
  • If you need support for languages beyond the six listed above, use Whisper Streaming (whisper-rt), which supports 99+ languages.

For more details on model selection, see the Model selection page.

Difference From Pre-recorded STT

It’s important to note that the language_code parameter mentioned in some AssemblyAI documentation applies to the Pre-recorded STT feature, not the Streaming Transcription feature. For streaming STT, you specify the model using the speech_model parameter.

To stay informed about new features and improvements, including language support updates, you can follow our Changelog.