diff options
| author | Danilo M. <danix@danix.xyz> | 2026-09-18 20:42:10 +0200 |
|---|---|---|
| committer | Danilo M. <danix@danix.xyz> | 2026-09-18 20:42:10 +0200 |
| commit | 309c0dd8b0fc294f67af8a82b78830a7610b700f (patch) | |
| tree | d090c70e2ef1534dfd31b194d078e9f305d70cbe /README.md | |
| parent | ddd2715e2c49d02db7ece5b0ae32c589cfd1e4db (diff) | |
| download | llamachat-309c0dd8b0fc294f67af8a82b78830a7610b700f.tar.gz llamachat-309c0dd8b0fc294f67af8a82b78830a7610b700f.zip | |
feat: mark audio-capable models in the picker
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 5 |
1 files changed, 3 insertions, 2 deletions
@@ -519,8 +519,9 @@ short default instruction so the request always carries a text part. Capability comes from the router: llama-server's model router reports each model's accepted inputs in `/v1/models` (`architecture.input_modalities`), and -a model listing `"audio"` there gets the control. Cloud models, whose -endpoints do not report modalities, can be marked by hand with the +a model listing `"audio"` there gets the control and a microphone (🎙) beside +its name in the picker, the way a vision model gets an eye. Cloud models, +whose endpoints do not report modalities, can be marked by hand with the **Accepts audio** box in the model settings dialog. Recording is 16 kHz mono WAV, the format speech encoders expect. The clip is |