Example
ยท
11/09/2023
393
Input
prompt
Text prompt. Supported languages: English, Chinese, Japanese
Hello, ladies and gentlemen.
audio_with_target_voice
.wav file of Speech of 3~10 seconds long with the target voice. Supported languages: English, Chinese, Japanese
transcript
Transcript of the input audio file
Output
Finished in 27.5 seconds
c6b11e7: Pulling from mjpyeon/valle-x 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 7d36cf857475: Pull complete 8915fc22d7d8: Pull complete 95948670f692: Pull complete 3dddfd6a72ca: Pull complete 25b35548813b: Pull complete 38ea29207376: Pull complete 8dee0f5f91b3: Pull complete b048f75287f6: Pull complete 648f5c8224c9: Pull complete 8ed0b7595f92: Pull complete ec44543bb1af: Pull complete 11ed2b522cb2: Pull complete ce87243ec77f: Pull complete 8770735786d9: Pull complete 61769491ac12: Pull complete Setting up the model... Processing... Transcript not given, using Whisper... Detected language: en are striving forward and to let them know in no uncertain terms that if they want Successful. Prompt saved to ./customs/user.npz synthesize text: [EN]Hello, ladies and gentlemen.[EN] VALL-E EOS [372 -> 555] Finished.
prompt
Text prompt. Supported languages: English, Chinese, Japanese
Hello, ladies and gentlemen.
audio_with_target_voice
.wav file of Speech of 3~10 seconds long with the target voice. Supported languages: English, Chinese, Japanese
transcript
Transcript of the input audio file
Finished in 27.5 seconds
c6b11e7: Pulling from mjpyeon/valle-x 578acb154839: Already exists ac65017cfc56: Already exists 146269b80f9c: Already exists b51bc62cc3ca: Already exists 4ba34dd48a55: Already exists 7d36cf857475: Pull complete 8915fc22d7d8: Pull complete 95948670f692: Pull complete 3dddfd6a72ca: Pull complete 25b35548813b: Pull complete 38ea29207376: Pull complete 8dee0f5f91b3: Pull complete b048f75287f6: Pull complete 648f5c8224c9: Pull complete 8ed0b7595f92: Pull complete ec44543bb1af: Pull complete 11ed2b522cb2: Pull complete ce87243ec77f: Pull complete 8770735786d9: Pull complete 61769491ac12: Pull complete Setting up the model... Processing... Transcript not given, using Whisper... Detected language: en are striving forward and to let them know in no uncertain terms that if they want Successful. Prompt saved to ./customs/user.npz synthesize text: [EN]Hello, ladies and gentlemen.[EN] VALL-E EOS [372 -> 555] Finished.