Skip to content

Clarification about using file as input text #179

@gabrieldemarmiesse

Description

@gabrieldemarmiesse

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!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions