speech_to_text
Convert speech to text using a selected ASR model, save transcriptions with optional timestamps and word boosts, and store output files in a specified directory. Includes cost alerts for API usage.
Instructions
Convert speech to text with a given model and save the output text file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
audio_file_path | Yes | ||
boosted_lm_score | No | ||
boosted_lm_words | No | ||
model_name | No | en-NER | |
timestamps | No |