docs: voice quickstart also needs sounddevice (#4250)

This commit is contained in:
Coleby Pearson
2026-08-06 20:32:26 -04:00
committed by GitHub
parent 0342746cf8
commit 2ec632fef3
+6
View File
@@ -8,6 +8,12 @@ Make sure you've followed the base [quickstart instructions](../quickstart.md) f
pip install 'openai-agents[voice]'
```
The demo code below also uses [`sounddevice`](https://pypi.org/project/sounddevice/) for microphone and speaker I/O, which is not part of the `voice` extra:
```bash
pip install sounddevice
```
## Concepts
The main concept to know about is a [`VoicePipeline`][agents.voice.pipeline.VoicePipeline], which is a 3 step process: