diarize_speech
Transcribe audio files to text with speaker identification, saving results to a specified directory. Supports custom models, maximum speaker limits, and word boosting for accurate recognition. Uses Whissle API for processing.
Instructions
Convert speech to text with speaker diarization 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.
⚠️ COST WARNING: This tool makes an API call to Whissle which may incur costs. Only use when explicitly requested by the user.
Args:
audio_file_path (str): Path to the audio file to transcribe
model_name (str, optional): The name of the ASR model to use. Defaults to "en-NER"
max_speakers (int, optional): Maximum number of speakers to identify
boosted_lm_words (List[str], optional): Words to boost in recognition
boosted_lm_score (int, optional): Score for boosted words (0-100)
output_directory (str, optional): Directory where files should be saved.
Defaults to $HOME/Desktop if not provided.
Returns:
TextContent with the diarized transcription and path to the output file.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| audio_file_path | Yes | ||
| boosted_lm_score | No | ||
| boosted_lm_words | No | ||
| max_speakers | No | ||
| model_name | No | en-NER |
Input Schema (JSON Schema)
{
"properties": {
"audio_file_path": {
"title": "Audio File Path",
"type": "string"
},
"boosted_lm_score": {
"default": 80,
"title": "Boosted Lm Score",
"type": "integer"
},
"boosted_lm_words": {
"default": null,
"items": {
"type": "string"
},
"title": "Boosted Lm Words",
"type": "array"
},
"max_speakers": {
"default": 2,
"title": "Max Speakers",
"type": "integer"
},
"model_name": {
"default": "en-NER",
"title": "Model Name",
"type": "string"
}
},
"required": [
"audio_file_path"
],
"title": "diarize_speechArguments",
"type": "object"
}