This bot is designed to work for any user by simply plugging this bot in an existing or new task to convert Speech to Text using Google Speech API. This bot provides possible alternative text from an audio file.
This bot only supports a maximum of 1 minute long audio files. Please refer to Google documentation for supported languages.
Inputs:
- Google API Key, Audio File Path, Encoding (not needed for .flac or .wav)
- Language Code (us-En for US English)
- Sample Rate Hertz (not needed for .flac or .wav)
Output: Text output
Key use cases:
- Text extraction from audio files
- Adding subtitles