AssemblyAI has introduced its latest speech recognition model, Universal-1, designed to achieve near-human transcription accuracy in challenging audio environments. This model is now accessible via the same web API as previous ASR models. Alongside the launch of Universal-1, AssemblyAI has introduced two new pricing tiers: Best and Nano.
The Best tier is optimized for maximum accuracy, while the Nano tier offers a cost-effective solution supporting transcription in 99 different languages. To make the transcription process easier, AssemblyAI offers an official Python SDK. Developers can install the SDK using the command: `pip install –upgrade assemblyai`.
After installation, users need to sign up for an AssemblyAI account to obtain an API key, necessary to authorize API calls in Python scripts. For transcriptions, developers can create a Python script where the SDK uses the Best tier by default. The process involves importing the SDK, configuring the API client with the API key, and specifying the audio file URL or local path.
Running the script will output the transcription results in the terminal. The Nano tier offers an affordable alternative, and developers can switch by adjusting the TranscriptionConfig object to use the Nano model. AssemblyAI’s offerings extend beyond basic transcription, providing advanced features such as entity detection, content moderation, PII redaction, and the application of large language models to audio data.
Developers interested in leveraging these features can explore AssemblyAI’s documentation and research resources.
Source
<p>The post Master Audio Transcription with AssemblyAI’s Ultimate-1: Unveiling New Pricing Tiers and Python Integration first appeared on CoinBuzzFeed.</p>