Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community.
New Streaming Speech-to-Text Features
- Streaming Session Duration Tracking: We've introduced a SessionInformation message, which includes the audio_duration_seconds field. This addition allows you to accurately track the total audio duration processed in a streaming session, a crucial feature for precise billing calculations based on the audio duration for end-users.
- Disable Partial Transcripts: Users can now disable Partial Transcript messages during Streaming sessions, choosing to receive only the final and formatted transcripts. This is particularly useful for applications that do not require visibility of partial utterances.
Check out our changelog to learn more about these features.
Compliance Updates: PCI DSS and GDPR
AssemblyAI has achieved PCI DSS certification, ensuring secure credit card data handling. GDPR compliance has also been attained to protect EU user data. Signed NDA partners can access our Trust Portal for compliance details.
Fresh From Our Blog
Transcribe an audio file with Universal-1 in Ruby: Unlock unparalleled transcription accuracy in your Ruby apps using our Universal-1 model - the cutting-edge in speech-to-text technology. Read more>>
Transcribe an audio file with Universal-1 using Go: Dive into transcribing audio files in your Go applications using our flagship Universal-1 model, delivering industry-leading speech recognition performance. Read more>>
Transcribe audio and video files with Python and Universal-1: Discover how to leverage Universal-1 to transcribe both audio and video files with high accuracy in your Python applications. Read more>>
Our Trending YouTube Tutorials
How to make video sections (timestamps + titles) AUTOMATICALLY with Python: Use AI to automatically segment a video into video sections, like YouTube's "Chapters" feature, which are useful for many reasons, such as meeting reviews, media consumption, and sales coaching.
Automatically extract phone call insights with LLMs and Python | Full tutorial: Build an app that extracts phone calls automatically with LLMs and Python.
Unmatched Accuracy and Lightning Speed in Python for Speech Recognition: AssemblyAI is building the best API platform for developers to transform and understand voice data with AI. Learn to transcribe voice data with Universal-1 in Python.
