Newsletter

Improvements to Real-Time Transcription

We're excited to announce some new features to our Python SDK, to improve your experience with building with real-time transcription.

Improvements to Real-Time Transcription

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

⚡️New Features in our Python SDK for Real-Time Transcription

We're excited to announce some new features to our Python SDK, to improve your experience with building with real-time transcription. Here's what's new:  

  • Temporary Authentication Support for Real-Time: We've introduced temporary authentication support for Real-Time transcription. With the new token parameter in RealtimeTranscriber and the create_temporary_token() function, developers can use a token as an alternative authentication method to avoid exposing their API key to the client. 
# Create a temporary token:
token = aai.RealtimeTranscriber.create_temporary_token(
    expires_in=3000
)

# Use the token
transcriber = aai.RealtimeTranscriber(
    sample_rate=16_000,
    token=token
)
  • Mu-law Support for Real-Time: Introducing Mu-law support for real-time transcription, which increases the types of audio encodings we handle. With the new encoding parameter in RealtimeTranscriber, transcribe Mu-law encoded audio in just a few lines of code.
# Use Mu-law encoding
transcriber = aai.RealtimeTranscriber(
    sample_rate=16_000,
    encoding=aai.AudioEncoding.pcm_mulaw
)

 Check out our real-time docs for more information.

Real-Time Transcription With AssemblyAI

AssemblyAI makes it possible to achieve real-time speech-to-text with microphone input in just a few lines of code. With real-time transcription, you can develop features such as voice-bots, automated subtitles for live speeches, language learning tools, and customer support chatbots. Explore the following tutorials to start using real-time speech-to-text in your applications:

Start building applications with our real-time speech-to-text docs.

Fresh From Our Blog

How to do Speech-To-Text with Go: Develop seamless integration of Speech Recognition into your Go application with just a few lines of code. Read more>>

How to Get YouTube Video Transcripts: Discover an easy-to-follow Python tutorial to obtain transcripts for YouTube videos effortlessly.  Read more>>

Extract phone call insights with LLMs in Python: Learn how to automatically extract insights from customer calls with Large Language Models (LLMs) and Python. Read more>>

How Graph Neural Networks Are Transforming Industries: This video highlights the impactful applications of GNNs in science and industry, and the most recent research highlights, focusing on applied use cases. 

How to Index Podcasts with Keywords like on Huberman's Website: Learn to build an application that indexes podcast episodes based on keywords using Speech-to-Text. 

The Physics of Generative AI - How AI models use physics to generate novel data: Modern Generative AI is capable of generating entire stories and photorealistic images, but how do these models actually work?