From a3038afa023b4a609fb62dffec21f4da3e780078 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 7 May 2025 11:39:36 -0700
Subject: [PATCH] DailyTransport: fix multiple audio/video sources

---
 CHANGELOG.md                             |  3 +++
 src/pipecat/transports/services/daily.py | 17 +++++++++--------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 319dce632..16da15420 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -39,6 +39,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Fixed a `DailyTransport` issue that was causing issues when multiple audio or
+  video sources where being captured.
+
 - Fixed a `UltravoxSTTService` issue that would cause the service to generate
   all tokens as one word.
 
diff --git a/src/pipecat/transports/services/daily.py b/src/pipecat/transports/services/daily.py
index 5d00e76bc..9118b2107 100644
--- a/src/pipecat/transports/services/daily.py
+++ b/src/pipecat/transports/services/daily.py
@@ -700,7 +700,7 @@ class DailyTransportClient(EventHandler):
 
         await self.update_subscriptions(participant_settings={participant_id: media})
 
-        self._audio_renderers[participant_id] = {audio_source: callback}
+        self._audio_renderers.setdefault(participant_id, {})[audio_source] = callback
 
         self._client.set_audio_renderer(
             participant_id,
@@ -724,7 +724,7 @@ class DailyTransportClient(EventHandler):
 
         await self.update_subscriptions(participant_settings={participant_id: media})
 
-        self._video_renderers[participant_id] = {video_source: callback}
+        self._video_renderers.setdefault(participant_id, {})[video_source] = callback
 
         self._client.set_video_renderer(
             participant_id,
@@ -1061,12 +1061,13 @@ class DailyInputTransport(BaseInputTransport):
         video_source: str = "camera",
         color_format: str = "RGB",
     ):
-        self._video_renderers[participant_id] = {
-            video_source: {
-                "framerate": framerate,
-                "timestamp": 0,
-                "render_next_frame": [],
-            }
+        if participant_id not in self._video_renderers:
+            self._video_renderers[participant_id] = {}
+
+        self._video_renderers[participant_id][video_source] = {
+            "framerate": framerate,
+            "timestamp": 0,
+            "render_next_frame": [],
         }
 
         await self._client.capture_participant_video(