diff options
Diffstat (limited to 'CHANGELOG.md')
| -rw-r--r-- | CHANGELOG.md | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index 9eb1ee5..a2a3635 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -84,8 +84,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 selected model reports audio input (`architecture.input_modalities` from the router, or the per-model "Accepts audio" setting); the clip is captured at 16 kHz mono, sent as an `input_audio` content part, and discarded after - send, leaving only a `voice-note Ns` marker in history. Capture needs - QtMultimedia from PySide6-Addons and is absent without it. + send, leaving only a `voice-note Ns` marker in history. Audio-capable + models show a microphone (🎙) in the picker beside their name, as vision + models show an eye. Capture needs QtMultimedia from PySide6-Addons and is + absent without it. ### Fixed |