Update CHANGELOG.md with daily_room_properties addition

- Allow custom DailyRoomProperties to be passed to configure()
- Falls back to default room properties if not provided
- Enables more flexible room configuration for advanced use cases

CHANGELOG.md

@@ -5,6 +5,20 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- Added `daily_room_properties` parameter to `configure()` function in 
+  `pipecat.runner.daily`, allowing custom `DailyRoomProperties` to be passed 
+  for more flexible room configuration.
+
+### Fixed
+
+- Fixed an issue where `RimeHttpTTSService` and `PiperTTSService` could generate
+  incorrectly 16-bit aligned audio frames, potentially leading to internal
+  errors or static audio.
+
 ## [0.0.90] - 2025-10-10
 
 ### Added

README.md

@@ -3,6 +3,7 @@
 </div></h1>
 
 [![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/pipecat-ai/pipecat)
+[![](https://getmanta.ai/api/badges?text=Manta%20Graph&link=manta)](https://getmanta.ai/pipecat)
 
 # 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
 

src/pipecat/runner/daily.py

@@ -42,6 +42,7 @@ from typing import Dict, List, Optional
 import aiohttp
 from loguru import logger
 from pydantic import BaseModel
+from typing_extensions import Literal
 
 from pipecat.transports.daily.utils import (
     DailyRESTHelper,
@@ -82,6 +83,8 @@ async def configure(
     sip_enable_video: Optional[bool] = False,
     sip_num_endpoints: Optional[int] = 1,
     sip_codecs: Optional[Dict[str, List[str]]] = None,
+    enable_recording: Optional[Literal["cloud", "local", "raw-tracks"]] = None,
+    daily_room_properties: Optional[DailyRoomProperties] = None,
 ) -> DailyRoomConfig:
     """Configure Daily room URL and token with optional SIP capabilities.
 
@@ -99,6 +102,9 @@ async def configure(
         sip_num_endpoints: Number of allowed SIP endpoints.
         sip_codecs: Codecs to support for audio and video. If None, uses Daily defaults.
             Example: {"audio": ["OPUS"], "video": ["H264"]}
+        enable_recording: Recording mode for the room. One of "cloud", "local", or "raw-tracks".
+        daily_room_properties: Custom room properties to use instead of default configuration.
+            If provided, overrides all other property settings.
 
     Returns:
         DailyRoomConfig: Object with room_url, token, and optional sip_endpoint.
@@ -155,8 +161,7 @@ async def configure(
 
     # Create room properties
     room_properties = DailyRoomProperties(
-        exp=expiration_time,
-        eject_at_room_exp=True,
+        exp=expiration_time, eject_at_room_exp=True, enable_recording=enable_recording
     )
 
     # Add SIP configuration if enabled
@@ -173,7 +178,10 @@ async def configure(
         room_properties.start_video_off = not sip_enable_video  # Voice-only by default
 
     # Create room parameters
-    room_params = DailyRoomParams(name=room_name, properties=room_properties)
+    if daily_room_properties:
+        room_params = DailyRoomParams(name=room_name, properties=daily_room_properties)
+    else:
+        room_params = DailyRoomParams(name=room_name, properties=room_properties)
 
     try:
         room_response = await daily_rest_helper.create_room(room_params)

src/pipecat/services/piper/tts.py

@@ -14,7 +14,6 @@ from loguru import logger
 from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
-    TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
@@ -99,16 +98,15 @@ class PiperTTSService(TTSService):
 
                 await self.start_tts_usage_metrics(text)
 
+                yield TTSStartedFrame()
+
                 CHUNK_SIZE = self.chunk_size
 
-                yield TTSStartedFrame()
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    # remove wav header if present
-                    if chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        yield TTSAudioRawFrame(chunk, self.sample_rate, 1)
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE), strip_wav_header=True
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
         except Exception as e:
             logger.error(f"Error in run_tts: {e}")
             yield ErrorFrame(error=str(e))

src/pipecat/services/rime/tts.py

@@ -553,15 +553,13 @@ class RimeHttpTTSService(TTSService):
 
                 CHUNK_SIZE = self.chunk_size
 
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                        need_to_strip_wav_header = False
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE),
+                    strip_wav_header=need_to_strip_wav_header,
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
 
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)
-                        yield frame
         except Exception as e:
             logger.exception(f"Error generating TTS: {e}")
             yield ErrorFrame(error=f"Rime TTS error: {str(e)}")

src/pipecat/services/tts_service.py

@@ -8,7 +8,17 @@
 
 import asyncio
 from abc import abstractmethod
-from typing import Any, AsyncGenerator, Dict, List, Mapping, Optional, Sequence, Tuple
+from typing import (
+    Any,
+    AsyncGenerator,
+    AsyncIterator,
+    Dict,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
 from loguru import logger
 
@@ -374,6 +384,36 @@ class TTSService(AIService):
         ):
             await self._stop_frame_queue.put(frame)
 
+    async def _stream_audio_frames_from_iterator(
+        self, iterator: AsyncIterator[bytes], *, strip_wav_header: bool
+    ) -> AsyncGenerator[Frame, None]:
+        buffer = bytearray()
+        need_to_strip_wav_header = strip_wav_header
+        async for chunk in iterator:
+            if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
+                chunk = chunk[44:]
+                need_to_strip_wav_header = False
+
+            # Append to current buffer.
+            buffer.extend(chunk)
+
+            # Round to nearest even number.
+            aligned_length = len(buffer) & ~1  # 111111111...11110
+            if aligned_length > 0:
+                aligned_chunk = buffer[:aligned_length]
+                buffer = buffer[aligned_length:]  # keep any leftover byte
+
+                if len(aligned_chunk) > 0:
+                    frame = TTSAudioRawFrame(bytes(aligned_chunk), self.sample_rate, 1)
+                    yield frame
+
+        if len(buffer) > 0:
+            # Make sure we don't need an extra padding byte.
+            if len(buffer) % 2 == 1:
+                buffer.extend(b"\x00")
+            frame = TTSAudioRawFrame(bytes(buffer), self.sample_rate, 1)
+            yield frame
+
     async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         self._processing_text = False
         await self._text_aggregator.handle_interruption()