examples(quickstart): allow Daily transport

Hotfix: Correct Gemini Live API class to fix 1007 payload error.

CHANGELOG.md

@@ -11,19 +11,31 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Updated `daily-python` to 0.19.6.
 
+- Changed `TavusVideoService` to send audio or video frames only after the
+  transport is ready, preventing warning messages at startup.
+
 ### Fixed
 
 - Fixed an issue in `LiveKitTransport` where empty `AudioRawFrame`s were pushed
   down the pipeline. This resulted in warnings by the STT processor.
+- Fixed `PiperTTSService` to send text as a JSON object in the request body,
+  resolving compatibility with Piper's HTTP API.
 
 - Fixed an issue with the `TavusVideoService` where an error was thrown due to
   missing transcription callbacks.
 
+- Fixed an issue in `SpeechmaticsSTTService` where the `user_id` was set to
+  `None` when diarization is not enabled.
+
 ### Performance
 
 - Fixed an issue in `TaskObserver` (a proxy to all observers) that was degrading
   global performance.
 
+### Other
+
+- Allow Daily transport to quickstart bot example.
+
 ## [0.0.77] - 2025-07-31
 
 ### Added

examples/foundational/13h-speechmatics-transcription.py

@@ -49,7 +49,7 @@ async def run_bot(transport: BaseTransport):
     This example will use diarization within our STT service and output the words spoken by
     each individual speaker and wrap them with XML tags.
 
-    If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
+    If you do not wish to use diarization, then set the `enable_diarization` parameter
     to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
 
     By default, this example will use our ENHANCED operating point, which is optimized for

examples/foundational/43a-heygen-video-service.py

@@ -4,6 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+# /// script
+# dependencies = [
+#   "pipecat-ai[daily,webrtc,websocket,runner,silero,deepgram,google,cartesia,heygen]>=0.0.77",
+# ]
+# ///
 
 import os
 

examples/quickstart/bot.py

@@ -32,12 +32,13 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
-from pipecat.runner.types import RunnerArguments
+from pipecat.runner.types import DailyRunnerArguments, RunnerArguments, SmallWebRTCRunnerArguments
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -108,16 +109,33 @@ async def run_bot(transport: BaseTransport):
 async def bot(runner_args: RunnerArguments):
     """Main bot entry point for the bot starter."""
 
-    transport = SmallWebRTCTransport(
-        params=TransportParams(
-            audio_in_enabled=True,
-            audio_out_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
-        ),
-        webrtc_connection=runner_args.webrtc_connection,
-    )
+    transport = None
 
-    await run_bot(transport)
+    if isinstance(runner_args, SmallWebRTCRunnerArguments):
+        transport = SmallWebRTCTransport(
+            params=TransportParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+            webrtc_connection=runner_args.webrtc_connection,
+        )
+    elif isinstance(runner_args, DailyRunnerArguments):
+        transport = DailyTransport(
+            runner_args.room_url,
+            runner_args.token,
+            "Pipecat Quickstart",
+            params=DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+    else:
+        logger.warning("Unsupported transport")
+
+    if transport:
+        await run_bot(transport)
 
 
 if __name__ == "__main__":

src/pipecat/services/gemini_multimodal_live/gemini.py

@@ -983,17 +983,14 @@ class GeminiMultimodalLiveLLMService(LLMService):
         with audio and video inputs, preventing temporal misalignment that can occur
         when different modalities are processed through separate API pathways.
 
-        After sending the text, we signal turn completion to trigger a model response
-        for text-only interactions.
+        For realtimeInput, turn completion is automatically inferred by the API based
+        on user activity, so no explicit turnComplete signal is needed.
 
         Args:
             text: The text to send as user input.
         """
         evt = events.TextInputMessage.from_text(text)
         await self.send_client_event(evt)
-        # After sending text, we need to signal that the turn is complete.
-        evt = events.ClientContentMessage.model_validate({"clientContent": {"turnComplete": True}})
-        await self.send_client_event(evt)
 
     async def _send_user_video(self, frame):
         """Send user video frame to Gemini Live API."""

src/pipecat/services/piper/tts.py

@@ -84,7 +84,9 @@ class PiperTTSService(TTSService):
         try:
             await self.start_ttfb_metrics()
 
-            async with self._session.post(self._base_url, json=text, headers=headers) as response:
+            async with self._session.post(
+                self._base_url, json={"text": text}, headers=headers
+            ) as response:
                 if response.status != 200:
                     error = await response.text()
                     logger.error(

src/pipecat/services/speechmatics/stt.py

@@ -191,7 +191,7 @@ class SpeakerFragments:
             passive_format = active_format
         return {
             "text": self._format_text(active_format if self.is_active else passive_format),
-            "user_id": self.speaker_id,
+            "user_id": self.speaker_id or "",
             "timestamp": self.timestamp,
             "language": self.language,
             "result": [frag.result for frag in self.fragments],

src/pipecat/services/tavus/video.py

@@ -24,6 +24,7 @@ from pipecat.frames.frames import (
     Frame,
     OutputAudioRawFrame,
     OutputImageRawFrame,
+    OutputTransportReadyFrame,
     StartFrame,
     StartInterruptionFrame,
     TTSAudioRawFrame,
@@ -81,6 +82,7 @@ class TavusVideoService(AIService):
         self._send_task: Optional[asyncio.Task] = None
         # This is the custom track destination expected by Tavus
         self._transport_destination: Optional[str] = "stream"
+        self._transport_ready = False
 
     async def setup(self, setup: FrameProcessorSetup):
         """Set up the Tavus video service.
@@ -145,7 +147,8 @@ class TavusVideoService(AIService):
             format=video_frame.color_format,
         )
         frame.transport_source = video_source
-        await self.push_frame(frame)
+        if self._transport_ready:
+            await self.push_frame(frame)
 
     async def _on_participant_audio_data(
         self, participant_id: str, audio: AudioData, audio_source: str
@@ -157,7 +160,8 @@ class TavusVideoService(AIService):
             num_channels=audio.num_channels,
         )
         frame.transport_source = audio_source
-        await self.push_frame(frame)
+        if self._transport_ready:
+            await self.push_frame(frame)
 
     def can_generate_metrics(self) -> bool:
         """Check if this service can generate processing metrics.
@@ -221,6 +225,9 @@ class TavusVideoService(AIService):
             await self.push_frame(frame, direction)
         elif isinstance(frame, TTSAudioRawFrame):
             await self._handle_audio_frame(frame)
+        elif isinstance(frame, OutputTransportReadyFrame):
+            self._transport_ready = True
+            await self.push_frame(frame, direction)
         else:
             await self.push_frame(frame, direction)