Merge pull request #337 from pipecat-ai/aleix/audio-video-sync-and-gs…

…treamer

audio/video sync and gstreamer

CHANGELOG.md

@@ -9,6 +9,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added new `GStreamerPipelineSource`. This processor can generate image or
+  audio frames from a GStreamer pipeline (e.g. reading an MP4 file, and RTP
+  stream or anything supported by GStreamer).
+
+- Added `TransportParams.audio_out_is_live`. This flag is False by default and
+  it is useful to indicate we should not synchronize audio with sporadic images.
+
 - Added new `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame` control
   frames. These frames are pushed upstream and they should wrap
   `BotSpeakingFrame`.
@@ -44,6 +51,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Other
 
+- Added examples `foundational/18-gstreamer-filesrc.py` and
+  `foundational/18a-gstreamer-videotestsrc.py` that show how to use
+  `GStreamerPipelineSource`
+
 - Remove `requests` library usage.
 
 - Cleanup examples and use `DailyRESTHelper`.

examples/foundational/18-gstreamer-filesrc.py

@@ -0,0 +1,78 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import argparse
+import sys
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.gstreamer.pipeline_source import GStreamerPipelineSource
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure_with_args
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
+        parser.add_argument(
+            "-i",
+            "--input",
+            type=str,
+            required=True,
+            help="Input video file")
+
+        (room_url, _, args) = await configure_with_args(session, parser)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "GStreamer",
+            DailyParams(
+                audio_out_enabled=True,
+                audio_out_is_live=True,
+                camera_out_enabled=True,
+                camera_out_width=1280,
+                camera_out_height=720,
+                camera_out_is_live=True,
+            )
+        )
+
+        gst = GStreamerPipelineSource(
+            pipeline=f"filesrc location={args.input}",
+            out_params=GStreamerPipelineSource.OutputParams(
+                video_width=1280,
+                video_height=720,
+                audio_sample_rate=16000,
+                audio_channels=1,
+            )
+        )
+
+        pipeline = Pipeline([
+            gst,                 # GStreamer file source
+            transport.output(),  # Transport bot output
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/18a-gstreamer-videotestsrc.py

@@ -0,0 +1,64 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import sys
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.gstreamer.pipeline_source import GStreamerPipelineSource
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "GStreamer",
+            DailyParams(
+                camera_out_enabled=True,
+                camera_out_width=1280,
+                camera_out_height=720,
+                camera_out_is_live=True,
+            )
+        )
+
+        gst = GStreamerPipelineSource(
+            pipeline="videotestsrc ! capsfilter caps=\"video/x-raw,width=1280,height=720,framerate=30/1\"",
+            out_params=GStreamerPipelineSource.OutputParams(
+                video_width=1280,
+                video_height=720,
+                clock_sync=False))
+
+        pipeline = Pipeline([
+            gst,                 # GStreamer file source
+            transport.output(),  # Transport bot output
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/runner.py

@@ -12,7 +12,15 @@
 
 
 async def configure(aiohttp_session: aiohttp.ClientSession):
-    parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
+    (url, token, _) = await configure_with_args(aiohttp_session)
+    return (url, token)
+
+
+async def configure_with_args(
+        aiohttp_session: aiohttp.ClientSession,
+        parser: argparse.ArgumentParser | None = None):
+    if not parser:
+        parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
     parser.add_argument(
         "-u",
         "--url",
@@ -50,4 +58,4 @@ async def configure(aiohttp_session: aiohttp.ClientSession):
 
     token = await daily_rest_helper.get_token(url, expiry_time)
 
-    return (url, token)
+    return (url, token, args)

src/pipecat/frames/frames.py

@@ -101,7 +101,7 @@ def __str__(self):
 class SpriteFrame(Frame):
     """An animated sprite. Will be shown by the transport if the transport's
     camera is enabled. Will play at the framerate specified in the transport's
-    `fps` constructor parameter.
+    `camera_out_framerate` constructor parameter.
 
     """
     images: List[ImageRawFrame]