Closed rmangino closed 1 year ago
the name of the file is directly tied to their backend and is used to track the audio file in the history tab of the dashboard. I'll look into making it more editable in the future.
Thanks @StephenHodgson.
I generally use ElevenLab's Python package to generate the audio data directly which allows me to save it where ever I want, in different formats, etc. Here's a simplified example. I was hoping it would be a similar process using your package.
from elevenlabs import generate, save
raw_audio_data = generate(text=text, voice=voice)
save(raw_audio_data , r "C:\temp\temp.wav")
...
If I call TextToSpeechEndpoint() like:
var clipPath = await _elevenlabs_client.TextToSpeechEndpoint.TextToSpeechAsync(text, voice, defaultVoiceSettings, null, @"C:\temp");
The audio file is actually saved in:
C:\temp\ElevenLabs\TextToSpeech\Rachel\x.mp3
Is there a way to specify a save directory and have the api actually save it in that location?