What is pcm_audio in the API #301
-
|
I'm using the given API commands: `reference_clips = [utils.audio.load_audio(p, 22050) for p in clips_paths] tts = api.TextToSpeech() pcm_audio = tts.tts_with_preset("your text here", voice_samples=reference_clips, preset='fast')` It finishes the transforming into audio step and should be returning the audio to pcm_audio, but im not sure what it is exactly. I'm also basically a noob, I tried playing it somehow with sounddevice but its not working out. |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
I've solved this... |
Beta Was this translation helpful? Give feedback.
I've solved this...
If anyone has a similar issue, then you just import pytorch and use the following command:
torchaudio.save(os.path.join(OUTPUT_DIRECTORY, NAME), pcm_audio.squeeze(0).cpu(), 24000)