Question recieved in our inbox:
Hi Kyutai,
At the Github site, one feature of pocket-tts that is highlighted is "Can handle infinitely long text inputs”.
I have been using pocket-tts from the command line, with the syntax like this:
cat text1.txt | pocket-tts generate --voice charles --text -
I get a very nice audio file output, but also warnings, such as:
WARNING: Chunk has 52 tokens (max 50), generation may skip words: '” “The first thing I remember? ” I gave it some th…'
The text files I am inputting (via stdin) are not very long… by the way, is there any other way to indicate that a file of text is to be input? I can’t seem to find any straightforward way to indicate that the input text (to be converted to speech) comes from a file.
I am very sorry for my ignorance, but I believe that an answer to my simple problem will help others as well.
Thank you so much!
Question recieved in our inbox:
Hi Kyutai,
At the Github site, one feature of pocket-tts that is highlighted is "Can handle infinitely long text inputs”.
I have been using pocket-tts from the command line, with the syntax like this:
cat text1.txt | pocket-tts generate --voice charles --text -I get a very nice audio file output, but also warnings, such as:
WARNING: Chunk has 52 tokens (max 50), generation may skip words: '” “The first thing I remember? ” I gave it some th…'
The text files I am inputting (via stdin) are not very long… by the way, is there any other way to indicate that a file of text is to be input? I can’t seem to find any straightforward way to indicate that the input text (to be converted to speech) comes from a file.
I am very sorry for my ignorance, but I believe that an answer to my simple problem will help others as well.
Thank you so much!