Newsletter #33: Make.com Speech AI Integration and Streaming STT Updates

Hey 👋, this weekly update contains the latest info on our new product features, tutorials, and our community.

🚀 Speech AI Automation with AssemblyAI & Make.com

We’ve launched our integration with Make.com, which enables users to use AssemblyAI’s Speech AI in another popular low-code/no-code service. The new integration makes it easy to automate audio data processing—whether that’s through transcription, analysis, or creating new features using our advanced AI models. 

For instance, imagine automatically handling audio files uploaded to Google Drive: transcribing them, applying PII redaction, summarizing them, and then storing the processed files back in Drive. This is just one of the many powerful scenarios enabled by our integration.  

For a deeper look at these features and to see how you can use them, visit our documentation or follow our guides for specific applications like PII redaction.

Updates to Streaming Speech-to-Text Features

Last week we rolled out important updates to enhance your experience:  

Streaming Session Duration Tracking: Accurately track the total audio duration in streaming sessions for precise billing. Disable Partial Transcripts: Option to disable partial transcripts, receiving only the final formatted versions, simplifying output for applications that require complete data only. 

For additional information and setup details, please visit our docs.

Fresh From Our Blog

Redact PII in Audio with Make and AssemblyAI: Create a Make scenario using the AssemblyAI app that watches a Google Drive folder for new audio files, and then creates both a transcript and an audio file in which PII is redacted. 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

Build an AI Lecture Assistant with Python | Full tutorial: Develop an application that summarizes your lectures, and lets you ask questions about the lecture with responses with Python and Streamlit.

Speech Recognition In Java | Convert Speech To Text: Learn how to set up and use the AssemblyAI Java SDK to integrate AssemblyAI’s Universal-1 speech-to-text model into your audio apps.

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.

Source: Read More