You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 793b65c
Browse filesBrowse the repository at this point in the historyBrowse files
authored
.Net: Add AudioTimestamp Property to GeminiPromptExecutionSettings (#9526)
### Motivation and Context
**Why is this change required?**
This change is required to enhance the functionality of audio processing
in the Semantic Kernel by allowing the inclusion of timestamps in audio
responses.
**What problem does it solve?**
It resolves the limitation of missing audio timestamp support in the
`GeminiPromptExecutionSettings`, which has been a significant blocker
for developers trying to utilize audio prompts effectively.
**What scenario does it contribute to?**
This contribution is particularly useful for applications that require
precise audio response management, enabling better synchronization and
analysis of audio data in real-time scenarios.
If it fixes an open issue, please link to the issue here.
#9500
### Description
This contribution adds a new feature that allows audio responses to
include timestamps, a crucial element for many applications. Here’s a
quick overview of what’s been implemented:
**New Property:** The `AudioTimestamp` property indicates whether the
audio response should include timestamps. When enabled, this property
will ensure that audio timestamps are included in requests to the model,
providing developers with the precise control they need for their
applications.
**Seamless Integration:** I conducted a thorough review of the existing
codebase to ensure that this new feature integrates smoothly without
disrupting current functionalities. This change is designed to be
backward-compatible, making it easier for developers to adopt.
**Future-Proofing:** By adding this property, we’re not just solving an
immediate need; we’re also paving the way for future enhancements in
audio processing capabilities within the Semantic Kernel framework.
### Contribution Checklist
- [Y] The code builds clean without any errors or warnings
- [Y] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [Y] All unit tests pass, and I have added new tests where possible
- [Y] I didn't break anyone 😄
---------
Co-authored-by: Adit Sheth <[email protected]>
Co-authored-by: Mark Wallace <[email protected]>
Co-authored-by: Roger Barreto <[email protected]>
0 commit comments