🚀 Upgraded Automatic Language Detection + Latest Tutorials

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

Share Your AI Insights & Earn a $20 Gift Card! Are you the founder of a company or building a new product? AssemblyAI is exploring AI trends across industries and are inviting founders, product, and engineering leaders to help inform our research. Start survey

Automatic Language Detection with High Accuracy

This week, we launched major updates to our Automatic Language Detection (ALD) model, delivering industry-leading accuracy and expanded language support. AssemblyAI's ALD now supports 17 languages in our Best Tier, including new additions like Chinese, Finnish, and Hindi. In recent tests, our model outperformed four leading competitors, achieving the highest accuracy in 15 out of 17 languages.

We’ve also introduced customizable confidence thresholds, allowing you to set minimum confidence levels for language detection. This feature lets you define your quality standards, receive alerts for detections below your threshold, and manage low-confidence cases to ensure consistent output quality.

Here’s how easy it is to implement ALD with just a few lines of code:

import assemblyai as aai
aai.settings.api_key = "ASSEMBLYAI_API_KEY"
audio_url = "https://github.com/AssemblyAI-Community/audio-examples/raw/main/20230607_me_canadian_wildfires.mp3"
config = aai.TranscriptionConfig(
language_detection = True,
language_confidence_threshold = 0.4
)
transcriber = aai.Transcriber(config=config)
transcript = transcriber.transcribe(audio_url)

Learn more in our ALD docs.

Fresh From Our Blog

Analyze Audio from Zoom Calls with AssemblyAI and Node.js: Discover how to analyze audio from Zoom calls using AssemblyAI and Node.js. Read more>>

Detect scam calls using Go with LeMUR and Twilio: Learn how to detect scam attempts in phone calls, using LeMUR. Read more>>

Build an AI-powered video conferencing app with Next.js and Stream: Develop a Next.js video conferencing app that supports video calls with live transcriptions and an LLM-powered meeting assistant. Read more>>

Real-Time Medical Transcription Analysis Using AI - Python Tutorial: Discover how to analyse medical audio using AssemblyAI’s Real-Time Transcription and Claude 3.5 Sonnet via LeMUR.

Real-time Speech Recognition in 15 minutes with AssemblyAI: Learn how to do real-time speech recognition with AssemblyAI's Streaming end point.

Build a Chatbot with Claude 3.5 Sonnet and Audio Data (in Python): Build an advanced chatbot using the Claude 3.5 Sonnet model and AssemblyAI's Speech-to-Text API.