async_text_to_speech
Convert text to speech with customizable speaker, audio format, speed, and pitch settings. Save synthesized audio files to a specified directory or default location.
Instructions
Async version of text_to_speech. Convert text to speech with a given speaker and save the output audio file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop. You can choose speaker by providing speaker parameter. If speaker is not provided, the default speaker(xiaoyi_meet) will be used.
Input Schema
Name | Required | Description | Default |
---|---|---|---|
audio_type | No | mp3 | |
output_directory | No | ||
pitch | No | ||
rate | No | ||
speaker | No | xiaoyi_meet | |
speed | No | ||
streaming | No | ||
text | Yes | ||
volume | No |