工具 API

speech_to_text

Transcribe speech from an audio file. By default, returns the transcription text directly. When save_transcript_to_file=True: Uploads file to server and returns accessible URL. When return_transcript_to_client_directly=True (default), always returns text directly regardless of output mode. ⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user. Args: input_file_url: URL of the audio file to transcribe. The file will be downloaded to a temporary location. language_code: ISO 639-3 language code for transcription. If not provided, the language will be detected automatically. diarize: Whether to diarize the audio file. If True, which speaker is currently speaking will be annotated in the transcription. save_transcript_to_file: Whether to save the transcript to a file. Defaults to False (only return text). return_transcript_to_client_directly: Whether to return the transcript to the client directly. Defaults to True. output_directory: Directory where files should be saved (only used when save_transcript_to_file=True). Defaults to $HOME/Desktop if not provided. Returns: TextContent containing the transcription text directly (default), or MCP resource with transcript file when save_transcript_to_file=True.