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
Introduce bidirectional streaming capabilities to Strands SDK, enabling real-time voice and audio conversations with AI models through persistent streaming connections.
Bidirectional streaming moves beyond traditional request-response patterns by maintaining long-running conversations where users can interrupt, provide continuous input, and receive real-time audio responses. This implementation is marked as experimental as we refine the API based on user feedback and evolving model capabilities.
---------
Co-authored-by: Murat Kaan Meral <murmeral@amazon.nl>
Co-authored-by: Patrick Gray <pgrayy@amazon.com>
Copy file name to clipboardExpand all lines: README.md
+68Lines changed: 68 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -197,6 +197,74 @@ agent("What is the square root of 1764")
197
197
198
198
It's also available on GitHub via [strands-agents/tools](https://github.com/strands-agents/tools).
199
199
200
+
### Bidirectional Streaming
201
+
202
+
> **⚠️ Experimental Feature**: Bidirectional streaming is currently in experimental status. APIs may change in future releases as we refine the feature based on user feedback and evolving model capabilities.
203
+
204
+
Build real-time voice and audio conversations with persistent streaming connections. Unlike traditional request-response patterns, bidirectional streaming maintains long-running conversations where users can interrupt, provide continuous input, and receive real-time audio responses. Get started with your first BidiAgent by following the [Quickstart](https://strandsagents.com/latest/documentation/docs/user-guide/concepts/experimental/bidirectional-streaming/quickstart) guide.
205
+
206
+
**Supported Model Providers:**
207
+
- Amazon Nova Sonic (`amazon.nova-sonic-v1:0`)
208
+
- Google Gemini Live (`gemini-2.5-flash-native-audio-preview-09-2025`)
209
+
- OpenAI Realtime API (`gpt-realtime`)
210
+
211
+
**Quick Example:**
212
+
213
+
```python
214
+
import asyncio
215
+
from strands.experimental.bidi import BidiAgent
216
+
from strands.experimental.bidi.models import BidiNovaSonicModel
217
+
from strands.experimental.bidi.io import BidiAudioIO, BidiTextIO
218
+
from strands.experimental.bidi.tools import stop_conversation
0 commit comments