Description:
Currently, generated audio using VibeVoice tends to be continuous, which can sound unnatural, especially for longer content like lectures or podcasts. It would be extremely helpful to have the ability to explicitly define pauses or breaks within the input text to achieve more natural-sounding speech.
Suggested Implementation:
Introduce a simple marker or token (e.g., [pause:500ms]) within the text input, enabling users to define precise pause durations. This implementation could be straightforward to parse and insert corresponding silence in the audio output.
Example usage:
Speaker 1: Welcome to today's lecture. [pause:1000ms] Let's dive right in.
Why this matters:
- Enhances speech naturalness and clarity.
- Provides precise control for content creators.
- Likely simple to implement with substantial benefit to users.
Priority: High (needed ASAP for practical usability improvements)
Thanks for your great work on this project!
Description:
Currently, generated audio using VibeVoice tends to be continuous, which can sound unnatural, especially for longer content like lectures or podcasts. It would be extremely helpful to have the ability to explicitly define pauses or breaks within the input text to achieve more natural-sounding speech.
Suggested Implementation:
Introduce a simple marker or token (e.g.,
[pause:500ms]) within the text input, enabling users to define precise pause durations. This implementation could be straightforward to parse and insert corresponding silence in the audio output.Example usage:
Why this matters:
Priority: High (needed ASAP for practical usability improvements)
Thanks for your great work on this project!