From eb1bf1e44680d7ce40d4f5096d4a4613c5d290ab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 28 Jan 2026 23:27:32 -0800
Subject: [PATCH 1/5] tts: rename PiperTTSService to PiperHttpTTSService

---
 examples/foundational/01-say-one-thing-piper.py |  4 ++--
 src/pipecat/services/piper/tts.py               |  7 ++++---
 tests/test_piper_tts.py                         | 12 ++++++++----
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/examples/foundational/01-say-one-thing-piper.py b/examples/foundational/01-say-one-thing-piper.py
index 5aa975b31..f6700f886 100644
--- a/examples/foundational/01-say-one-thing-piper.py
+++ b/examples/foundational/01-say-one-thing-piper.py
@@ -16,7 +16,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.piper.tts import PiperTTSService
+from pipecat.services.piper.tts import PiperHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -39,7 +39,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        tts = PiperTTSService(
+        tts = PiperHttpTTSService(
             base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
         )
 
diff --git a/src/pipecat/services/piper/tts.py b/src/pipecat/services/piper/tts.py
index ce47c885e..19d9720f0 100644
--- a/src/pipecat/services/piper/tts.py
+++ b/src/pipecat/services/piper/tts.py
@@ -21,9 +21,10 @@ from pipecat.services.tts_service import TTSService
 from pipecat.utils.tracing.service_decorators import traced_tts
 
 
-# This assumes a running TTS service running: https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/API_HTTP.md
-class PiperTTSService(TTSService):
-    """Piper TTS service implementation.
+# This assumes a running TTS service running:
+# https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/API_HTTP.md
+class PiperHttpTTSService(TTSService):
+    """Piper HTTP TTS service implementation.
 
     Provides integration with Piper's HTTP TTS server for text-to-speech
     synthesis. Supports streaming audio generation with configurable sample
diff --git a/tests/test_piper_tts.py b/tests/test_piper_tts.py
index e52be2d91..8d877099c 100644
--- a/tests/test_piper_tts.py
+++ b/tests/test_piper_tts.py
@@ -21,7 +21,7 @@ from pipecat.frames.frames import (
     TTSStoppedFrame,
     TTSTextFrame,
 )
-from pipecat.services.piper.tts import PiperTTSService
+from pipecat.services.piper.tts import PiperHttpTTSService
 from pipecat.tests.utils import run_test
 
 
@@ -67,8 +67,10 @@ async def test_run_piper_tts_success(aiohttp_client):
     base_url = str(client.make_url("")).rstrip("/")
 
     async with aiohttp.ClientSession() as session:
-        # Instantiate PiperTTSService with our mock server
-        tts_service = PiperTTSService(base_url=base_url, aiohttp_session=session, sample_rate=24000)
+        # Instantiate PiperHttpTTSService with our mock server
+        tts_service = PiperHttpTTSService(
+            base_url=base_url, aiohttp_session=session, sample_rate=24000
+        )
 
         frames_to_send = [
             TTSSpeakFrame(text="Hello world."),
@@ -117,7 +119,9 @@ async def test_run_piper_tts_error(aiohttp_client):
     base_url = str(client.make_url("")).rstrip("/")
 
     async with aiohttp.ClientSession() as session:
-        tts_service = PiperTTSService(base_url=base_url, aiohttp_session=session, sample_rate=24000)
+        tts_service = PiperHttpTTSService(
+            base_url=base_url, aiohttp_session=session, sample_rate=24000
+        )
 
         frames_to_send = [
             TTSSpeakFrame(text="Error case."),

From 875614ff7a43cf7820c8cec3c385683126f313e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 28 Jan 2026 23:29:21 -0800
Subject: [PATCH 2/5] tts: add support for local PiperTTSService

---
 .github/workflows/coverage.yaml               |   9 +-
 .github/workflows/tests.yaml                  |   9 +-
 .../foundational/07zi-interruptible-piper.py  | 132 ++++++++++++++++++
 pyproject.toml                                |   1 +
 scripts/evals/run-release-evals.py            |   1 +
 src/pipecat/services/piper/tts.py             | 122 +++++++++++++++-
 uv.lock                                       |  27 +++-
 7 files changed, 291 insertions(+), 10 deletions(-)
 create mode 100644 examples/foundational/07zi-interruptible-piper.py

diff --git a/.github/workflows/coverage.yaml b/.github/workflows/coverage.yaml
index faca8c03f..ae0cb9c57 100644
--- a/.github/workflows/coverage.yaml
+++ b/.github/workflows/coverage.yaml
@@ -33,7 +33,14 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra livekit --extra websocket
+          uv sync --group dev \
+            --extra anthropic \
+            --extra aws \
+            --extra google \
+            --extra langchain \
+            --extra livekit \
+            --extra piper \
+            --extra websocket
 
       - name: Run tests with coverage
         run: |
diff --git a/.github/workflows/tests.yaml b/.github/workflows/tests.yaml
index 459725da7..cb35a169c 100644
--- a/.github/workflows/tests.yaml
+++ b/.github/workflows/tests.yaml
@@ -37,7 +37,14 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra livekit --extra websocket
+          uv sync --group dev \
+            --extra anthropic \
+            --extra aws \
+            --extra google \
+            --extra langchain \
+            --extra livekit \
+            --extra piper \
+            --extra websocket
 
       - name: Test with pytest
         run: |
diff --git a/examples/foundational/07zi-interruptible-piper.py b/examples/foundational/07zi-interruptible-piper.py
new file mode 100644
index 000000000..67286741d
--- /dev/null
+++ b/examples/foundational/07zi-interruptible-piper.py
@@ -0,0 +1,132 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.piper.tts import PiperTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = PiperTTSService(voice_id="en_US-ryan-high")
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()
diff --git a/pyproject.toml b/pyproject.toml
index 339b498f6..098ad917b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -95,6 +95,7 @@ rnnoise = [ "pyrnnoise~=0.4.1" ]
 openpipe = [ "openpipe>=4.50.0,<6" ]
 openrouter = []
 perplexity = []
+piper = [ "piper-tts>=1.3.0,<2" ]
 playht = [ "pipecat-ai[websockets-base]" ]
 qwen = []
 remote-smart-turn = []
diff --git a/scripts/evals/run-release-evals.py b/scripts/evals/run-release-evals.py
index d4290be00..239012c36 100644
--- a/scripts/evals/run-release-evals.py
+++ b/scripts/evals/run-release-evals.py
@@ -138,6 +138,7 @@ TESTS_07 = [
     ("07zf-interruptible-gradium.py", EVAL_SIMPLE_MATH),
     ("07zg-interruptible-camb.py", EVAL_SIMPLE_MATH),
     ("07zh-interruptible-hathora.py", EVAL_SIMPLE_MATH),
+    ("07zi-interruptible-piper.py", EVAL_SIMPLE_MATH),
     # Needs a local XTTS docker instance running.
     # ("07i-interruptible-xtts.py", EVAL_SIMPLE_MATH),
     # Needs a Krisp license.
diff --git a/src/pipecat/services/piper/tts.py b/src/pipecat/services/piper/tts.py
index 19d9720f0..ca809f469 100644
--- a/src/pipecat/services/piper/tts.py
+++ b/src/pipecat/services/piper/tts.py
@@ -6,11 +6,14 @@
 
 """Piper TTS service implementation."""
 
-from typing import AsyncGenerator, Optional
+import asyncio
+from pathlib import Path
+from typing import AsyncGenerator, AsyncIterator, Optional
 
 import aiohttp
 from loguru import logger
 
+from pipecat.audio.utils import create_stream_resampler
 from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
@@ -20,6 +23,123 @@ from pipecat.frames.frames import (
 from pipecat.services.tts_service import TTSService
 from pipecat.utils.tracing.service_decorators import traced_tts
 
+try:
+    from piper import PiperVoice
+    from piper.download_voices import download_voice
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Piper, you need to `pip install pipecat-ai[piper]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+class PiperTTSService(TTSService):
+    """Piper TTS service implementation.
+
+    Provides local text-to-speech synthesis using Piper voice models. Automatically
+    downloads voice models if not already present and resamples audio output to
+    match the configured sample rate.
+    """
+
+    def __init__(
+        self,
+        *,
+        voice_id: str,
+        download_dir: Optional[Path] = None,
+        force_redownload: bool = False,
+        use_cuda: bool = False,
+        **kwargs,
+    ):
+        """Initialize the Piper TTS service.
+
+        Args:
+            voice_id: Piper voice model identifier (e.g. `en_US-ryan-high`).
+            download_dir: Directory for storing voice model files. Defaults to
+                the current working directory.
+            force_redownload: Re-download the voice model even if it already exists.
+            use_cuda: Use CUDA for GPU-accelerated inference.
+            **kwargs: Additional arguments passed to the parent `TTSService`.
+        """
+        super().__init__(**kwargs)
+
+        self._voice_id = voice_id
+
+        self._resampler = create_stream_resampler()
+
+        download_dir = download_dir or Path.cwd()
+
+        model_file = f"{voice_id}.onnx"
+        model_path = Path(download_dir) / model_file
+
+        if not model_path.exists():
+            logger.debug(f"Downloading Piper '{voice_id}' model")
+            download_voice(voice_id, download_dir, force_redownload=force_redownload)
+
+        logger.debug(f"Loading Piper '{voice_id}' model from {model_path}")
+
+        self._voice = PiperVoice.load(model_path, use_cuda=use_cuda)
+
+        logger.debug(f"Loaded Piper '{voice_id}' model")
+
+    def can_generate_metrics(self) -> bool:
+        """Check if this service can generate processing metrics.
+
+        Returns:
+            True, as Piper service supports metrics generation.
+        """
+        return True
+
+    @traced_tts
+    async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
+        """Generate speech from text using Piper.
+
+        Args:
+            text: The text to convert to speech.
+
+        Yields:
+            Frame: Audio frames containing the synthesized speech and status frames.
+        """
+
+        def async_next(it):
+            try:
+                return next(it)
+            except StopIteration:
+                return None
+
+        async def async_iterator(iterator, sample_rate: int) -> AsyncIterator[bytes]:
+            while True:
+                item = await asyncio.to_thread(async_next, iterator)
+                if item is None:
+                    return
+
+                audio_data = await self._resampler.resample(
+                    item.audio_int16_bytes, sample_rate, self.sample_rate
+                )
+
+                yield audio_data
+
+        logger.debug(f"{self}: Generating TTS [{text}]")
+
+        try:
+            await self.start_ttfb_metrics()
+
+            await self.start_tts_usage_metrics(text)
+
+            yield TTSStartedFrame()
+
+            async for frame in self._stream_audio_frames_from_iterator(
+                async_iterator(self._voice.synthesize(text), self._voice.config.sample_rate),
+                strip_wav_header=False,
+            ):
+                await self.stop_ttfb_metrics()
+                yield frame
+        except Exception as e:
+            logger.error(f"{self} exception: {e}")
+            yield ErrorFrame(error=f"Unknown error occurred: {e}")
+        finally:
+            logger.debug(f"{self}: Finished TTS [{text}]")
+            await self.stop_ttfb_metrics()
+            yield TTSStoppedFrame()
+
 
 # This assumes a running TTS service running:
 # https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/API_HTTP.md
diff --git a/uv.lock b/uv.lock
index b35c9f25d..26f0cc202 100644
--- a/uv.lock
+++ b/uv.lock
@@ -2045,7 +2045,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/32/6a/33d1702184d94106d3cdd7bfb788e19723206fce152e303473ca3b946c7b/greenlet-3.3.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:6f8496d434d5cb2dce025773ba5597f71f5410ae499d5dd9533e0653258cdb3d", size = 273658, upload-time = "2025-12-04T14:23:37.494Z" },
     { url = "https://files.pythonhosted.org/packages/d6/b7/2b5805bbf1907c26e434f4e448cd8b696a0b71725204fa21a211ff0c04a7/greenlet-3.3.0-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b96dc7eef78fd404e022e165ec55327f935b9b52ff355b067eb4a0267fc1cffb", size = 574810, upload-time = "2025-12-04T14:50:04.154Z" },
     { url = "https://files.pythonhosted.org/packages/94/38/343242ec12eddf3d8458c73f555c084359883d4ddc674240d9e61ec51fd6/greenlet-3.3.0-cp310-cp310-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:73631cd5cccbcfe63e3f9492aaa664d278fda0ce5c3d43aeda8e77317e38efbd", size = 586248, upload-time = "2025-12-04T14:57:39.35Z" },
-    { url = "https://files.pythonhosted.org/packages/f0/d0/0ae86792fb212e4384041e0ef8e7bc66f59a54912ce407d26a966ed2914d/greenlet-3.3.0-cp310-cp310-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:b299a0cb979f5d7197442dccc3aee67fce53500cd88951b7e6c35575701c980b", size = 597403, upload-time = "2025-12-04T15:07:10.831Z" },
     { url = "https://files.pythonhosted.org/packages/b6/a8/15d0aa26c0036a15d2659175af00954aaaa5d0d66ba538345bd88013b4d7/greenlet-3.3.0-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7dee147740789a4632cace364816046e43310b59ff8fb79833ab043aefa72fd5", size = 586910, upload-time = "2025-12-04T14:25:59.705Z" },
     { url = "https://files.pythonhosted.org/packages/e1/9b/68d5e3b7ccaba3907e5532cf8b9bf16f9ef5056a008f195a367db0ff32db/greenlet-3.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:39b28e339fc3c348427560494e28d8a6f3561c8d2bcf7d706e1c624ed8d822b9", size = 1547206, upload-time = "2025-12-04T15:04:21.027Z" },
     { url = "https://files.pythonhosted.org/packages/66/bd/e3086ccedc61e49f91e2cfb5ffad9d8d62e5dc85e512a6200f096875b60c/greenlet-3.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:b3c374782c2935cc63b2a27ba8708471de4ad1abaa862ffdb1ef45a643ddbb7d", size = 1613359, upload-time = "2025-12-04T14:27:26.548Z" },
@@ -2053,7 +2052,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/1f/cb/48e964c452ca2b92175a9b2dca037a553036cb053ba69e284650ce755f13/greenlet-3.3.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:e29f3018580e8412d6aaf5641bb7745d38c85228dacf51a73bd4e26ddf2a6a8e", size = 274908, upload-time = "2025-12-04T14:23:26.435Z" },
     { url = "https://files.pythonhosted.org/packages/28/da/38d7bff4d0277b594ec557f479d65272a893f1f2a716cad91efeb8680953/greenlet-3.3.0-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a687205fb22794e838f947e2194c0566d3812966b41c78709554aa883183fb62", size = 577113, upload-time = "2025-12-04T14:50:05.493Z" },
     { url = "https://files.pythonhosted.org/packages/3c/f2/89c5eb0faddc3ff014f1c04467d67dee0d1d334ab81fadbf3744847f8a8a/greenlet-3.3.0-cp311-cp311-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4243050a88ba61842186cb9e63c7dfa677ec146160b0efd73b855a3d9c7fcf32", size = 590338, upload-time = "2025-12-04T14:57:41.136Z" },
-    { url = "https://files.pythonhosted.org/packages/80/d7/db0a5085035d05134f8c089643da2b44cc9b80647c39e93129c5ef170d8f/greenlet-3.3.0-cp311-cp311-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:670d0f94cd302d81796e37299bcd04b95d62403883b24225c6b5271466612f45", size = 601098, upload-time = "2025-12-04T15:07:11.898Z" },
     { url = "https://files.pythonhosted.org/packages/dc/a6/e959a127b630a58e23529972dbc868c107f9d583b5a9f878fb858c46bc1a/greenlet-3.3.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6cb3a8ec3db4a3b0eb8a3c25436c2d49e3505821802074969db017b87bc6a948", size = 590206, upload-time = "2025-12-04T14:26:01.254Z" },
     { url = "https://files.pythonhosted.org/packages/48/60/29035719feb91798693023608447283b266b12efc576ed013dd9442364bb/greenlet-3.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:2de5a0b09eab81fc6a382791b995b1ccf2b172a9fec934747a7a23d2ff291794", size = 1550668, upload-time = "2025-12-04T15:04:22.439Z" },
     { url = "https://files.pythonhosted.org/packages/0a/5f/783a23754b691bfa86bd72c3033aa107490deac9b2ef190837b860996c9f/greenlet-3.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4449a736606bd30f27f8e1ff4678ee193bc47f6ca810d705981cfffd6ce0d8c5", size = 1615483, upload-time = "2025-12-04T14:27:28.083Z" },
@@ -2061,7 +2059,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f8/0a/a3871375c7b9727edaeeea994bfff7c63ff7804c9829c19309ba2e058807/greenlet-3.3.0-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:b01548f6e0b9e9784a2c99c5651e5dc89ffcbe870bc5fb2e5ef864e9cc6b5dcb", size = 276379, upload-time = "2025-12-04T14:23:30.498Z" },
     { url = "https://files.pythonhosted.org/packages/43/ab/7ebfe34dce8b87be0d11dae91acbf76f7b8246bf9d6b319c741f99fa59c6/greenlet-3.3.0-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:349345b770dc88f81506c6861d22a6ccd422207829d2c854ae2af8025af303e3", size = 597294, upload-time = "2025-12-04T14:50:06.847Z" },
     { url = "https://files.pythonhosted.org/packages/a4/39/f1c8da50024feecd0793dbd5e08f526809b8ab5609224a2da40aad3a7641/greenlet-3.3.0-cp312-cp312-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:e8e18ed6995e9e2c0b4ed264d2cf89260ab3ac7e13555b8032b25a74c6d18655", size = 607742, upload-time = "2025-12-04T14:57:42.349Z" },
-    { url = "https://files.pythonhosted.org/packages/77/cb/43692bcd5f7a0da6ec0ec6d58ee7cddb606d055ce94a62ac9b1aa481e969/greenlet-3.3.0-cp312-cp312-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:c024b1e5696626890038e34f76140ed1daf858e37496d33f2af57f06189e70d7", size = 622297, upload-time = "2025-12-04T15:07:13.552Z" },
     { url = "https://files.pythonhosted.org/packages/75/b0/6bde0b1011a60782108c01de5913c588cf51a839174538d266de15e4bf4d/greenlet-3.3.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:047ab3df20ede6a57c35c14bf5200fcf04039d50f908270d3f9a7a82064f543b", size = 609885, upload-time = "2025-12-04T14:26:02.368Z" },
     { url = "https://files.pythonhosted.org/packages/49/0e/49b46ac39f931f59f987b7cd9f34bfec8ef81d2a1e6e00682f55be5de9f4/greenlet-3.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2d9ad37fc657b1102ec880e637cccf20191581f75c64087a549e66c57e1ceb53", size = 1567424, upload-time = "2025-12-04T15:04:23.757Z" },
     { url = "https://files.pythonhosted.org/packages/05/f5/49a9ac2dff7f10091935def9165c90236d8f175afb27cbed38fb1d61ab6b/greenlet-3.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:83cd0e36932e0e7f36a64b732a6f60c2fc2df28c351bae79fbaf4f8092fe7614", size = 1636017, upload-time = "2025-12-04T14:27:29.688Z" },
@@ -2069,7 +2066,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/02/2f/28592176381b9ab2cafa12829ba7b472d177f3acc35d8fbcf3673d966fff/greenlet-3.3.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:a1e41a81c7e2825822f4e068c48cb2196002362619e2d70b148f20a831c00739", size = 275140, upload-time = "2025-12-04T14:23:01.282Z" },
     { url = "https://files.pythonhosted.org/packages/2c/80/fbe937bf81e9fca98c981fe499e59a3f45df2a04da0baa5c2be0dca0d329/greenlet-3.3.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9f515a47d02da4d30caaa85b69474cec77b7929b2e936ff7fb853d42f4bf8808", size = 599219, upload-time = "2025-12-04T14:50:08.309Z" },
     { url = "https://files.pythonhosted.org/packages/c2/ff/7c985128f0514271b8268476af89aee6866df5eec04ac17dcfbc676213df/greenlet-3.3.0-cp313-cp313-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7d2d9fd66bfadf230b385fdc90426fcd6eb64db54b40c495b72ac0feb5766c54", size = 610211, upload-time = "2025-12-04T14:57:43.968Z" },
-    { url = "https://files.pythonhosted.org/packages/79/07/c47a82d881319ec18a4510bb30463ed6891f2ad2c1901ed5ec23d3de351f/greenlet-3.3.0-cp313-cp313-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:30a6e28487a790417d036088b3bcb3f3ac7d8babaa7d0139edbaddebf3af9492", size = 624311, upload-time = "2025-12-04T15:07:14.697Z" },
     { url = "https://files.pythonhosted.org/packages/fd/8e/424b8c6e78bd9837d14ff7df01a9829fc883ba2ab4ea787d4f848435f23f/greenlet-3.3.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:087ea5e004437321508a8d6f20efc4cfec5e3c30118e1417ea96ed1d93950527", size = 612833, upload-time = "2025-12-04T14:26:03.669Z" },
     { url = "https://files.pythonhosted.org/packages/b5/ba/56699ff9b7c76ca12f1cdc27a886d0f81f2189c3455ff9f65246780f713d/greenlet-3.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ab97cf74045343f6c60a39913fa59710e4bd26a536ce7ab2397adf8b27e67c39", size = 1567256, upload-time = "2025-12-04T15:04:25.276Z" },
     { url = "https://files.pythonhosted.org/packages/1e/37/f31136132967982d698c71a281a8901daf1a8fbab935dce7c0cf15f942cc/greenlet-3.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5375d2e23184629112ca1ea89a53389dddbffcf417dad40125713d88eb5f96e8", size = 1636483, upload-time = "2025-12-04T14:27:30.804Z" },
@@ -2077,7 +2073,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d7/7c/f0a6d0ede2c7bf092d00bc83ad5bafb7e6ec9b4aab2fbdfa6f134dc73327/greenlet-3.3.0-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:60c2ef0f578afb3c8d92ea07ad327f9a062547137afe91f38408f08aacab667f", size = 275671, upload-time = "2025-12-04T14:23:05.267Z" },
     { url = "https://files.pythonhosted.org/packages/44/06/dac639ae1a50f5969d82d2e3dd9767d30d6dbdbab0e1a54010c8fe90263c/greenlet-3.3.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0a5d554d0712ba1de0a6c94c640f7aeba3f85b3a6e1f2899c11c2c0428da9365", size = 646360, upload-time = "2025-12-04T14:50:10.026Z" },
     { url = "https://files.pythonhosted.org/packages/e0/94/0fb76fe6c5369fba9bf98529ada6f4c3a1adf19e406a47332245ef0eb357/greenlet-3.3.0-cp314-cp314-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:3a898b1e9c5f7307ebbde4102908e6cbfcb9ea16284a3abe15cab996bee8b9b3", size = 658160, upload-time = "2025-12-04T14:57:45.41Z" },
-    { url = "https://files.pythonhosted.org/packages/93/79/d2c70cae6e823fac36c3bbc9077962105052b7ef81db2f01ec3b9bf17e2b/greenlet-3.3.0-cp314-cp314-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:dcd2bdbd444ff340e8d6bdf54d2f206ccddbb3ccfdcd3c25bf4afaa7b8f0cf45", size = 671388, upload-time = "2025-12-04T15:07:15.789Z" },
     { url = "https://files.pythonhosted.org/packages/b8/14/bab308fc2c1b5228c3224ec2bf928ce2e4d21d8046c161e44a2012b5203e/greenlet-3.3.0-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5773edda4dc00e173820722711d043799d3adb4f01731f40619e07ea2750b955", size = 660166, upload-time = "2025-12-04T14:26:05.099Z" },
     { url = "https://files.pythonhosted.org/packages/4b/d2/91465d39164eaa0085177f61983d80ffe746c5a1860f009811d498e7259c/greenlet-3.3.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ac0549373982b36d5fd5d30beb8a7a33ee541ff98d2b502714a09f1169f31b55", size = 1615193, upload-time = "2025-12-04T15:04:27.041Z" },
     { url = "https://files.pythonhosted.org/packages/42/1b/83d110a37044b92423084d52d5d5a3b3a73cafb51b547e6d7366ff62eff1/greenlet-3.3.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:d198d2d977460358c3b3a4dc844f875d1adb33817f0613f663a656f463764ccc", size = 1683653, upload-time = "2025-12-04T14:27:32.366Z" },
@@ -2085,7 +2080,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a0/66/bd6317bc5932accf351fc19f177ffba53712a202f9df10587da8df257c7e/greenlet-3.3.0-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:d6ed6f85fae6cdfdb9ce04c9bf7a08d666cfcfb914e7d006f44f840b46741931", size = 282638, upload-time = "2025-12-04T14:25:20.941Z" },
     { url = "https://files.pythonhosted.org/packages/30/cf/cc81cb030b40e738d6e69502ccbd0dd1bced0588e958f9e757945de24404/greenlet-3.3.0-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d9125050fcf24554e69c4cacb086b87b3b55dc395a8b3ebe6487b045b2614388", size = 651145, upload-time = "2025-12-04T14:50:11.039Z" },
     { url = "https://files.pythonhosted.org/packages/9c/ea/1020037b5ecfe95ca7df8d8549959baceb8186031da83d5ecceff8b08cd2/greenlet-3.3.0-cp314-cp314t-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:87e63ccfa13c0a0f6234ed0add552af24cc67dd886731f2261e46e241608bee3", size = 654236, upload-time = "2025-12-04T14:57:47.007Z" },
-    { url = "https://files.pythonhosted.org/packages/69/cc/1e4bae2e45ca2fa55299f4e85854606a78ecc37fead20d69322f96000504/greenlet-3.3.0-cp314-cp314t-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2662433acbca297c9153a4023fe2161c8dcfdcc91f10433171cf7e7d94ba2221", size = 662506, upload-time = "2025-12-04T15:07:16.906Z" },
     { url = "https://files.pythonhosted.org/packages/57/b9/f8025d71a6085c441a7eaff0fd928bbb275a6633773667023d19179fe815/greenlet-3.3.0-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3c6e9b9c1527a78520357de498b0e709fb9e2f49c3a513afd5a249007261911b", size = 653783, upload-time = "2025-12-04T14:26:06.225Z" },
     { url = "https://files.pythonhosted.org/packages/f6/c7/876a8c7a7485d5d6b5c6821201d542ef28be645aa024cfe1145b35c120c1/greenlet-3.3.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:286d093f95ec98fdd92fcb955003b8a3d054b4e2cab3e2707a5039e7b50520fd", size = 1614857, upload-time = "2025-12-04T15:04:28.484Z" },
     { url = "https://files.pythonhosted.org/packages/4f/dc/041be1dff9f23dac5f48a43323cd0789cb798342011c19a248d9c9335536/greenlet-3.3.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6c10513330af5b8ae16f023e8ddbfb486ab355d04467c4679c5cfe4659975dd9", size = 1676034, upload-time = "2025-12-04T14:27:33.531Z" },
@@ -4426,6 +4420,9 @@ openai = [
 openpipe = [
     { name = "openpipe" },
 ]
+piper = [
+    { name = "piper-tts" },
+]
 playht = [
     { name = "websockets" },
 ]
@@ -4602,6 +4599,7 @@ requires-dist = [
     { name = "pipecat-ai", extras = ["websockets-base"], marker = "extra == 'websocket'" },
     { name = "pipecat-ai-krisp", marker = "extra == 'krisp'", specifier = "~=0.4.0" },
     { name = "pipecat-ai-small-webrtc-prebuilt", marker = "extra == 'runner'", specifier = ">=2.0.4" },
+    { name = "piper-tts", marker = "extra == 'piper'", specifier = ">=1.3.0,<2" },
     { name = "protobuf", specifier = "~=5.29.3" },
     { name = "pvkoala", marker = "extra == 'koala'", specifier = "~=2.0.3" },
     { name = "pyaudio", marker = "extra == 'local'", specifier = "~=0.2.14" },
@@ -4631,7 +4629,7 @@ requires-dist = [
     { name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1" },
     { name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" },
 ]
-provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "local-smart-turn-v3", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "playht", "qwen", "remote-smart-turn", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"]
+provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "camb", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "gradium", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "local-smart-turn-v3", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "noisereduce", "nvidia", "openai", "rnnoise", "openpipe", "openrouter", "perplexity", "piper", "playht", "qwen", "remote-smart-turn", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"]
 
 [package.metadata.requires-dev]
 dev = [
@@ -4679,6 +4677,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/9c/6e/332b78d1c7888ff426bd528b150aad0da05024f4f91e56502c359726c07b/pipecat_ai_small_webrtc_prebuilt-2.0.4-py3-none-any.whl", hash = "sha256:054b3cee843fe69191859dbb0693560d9ca08f7d57a9ff0457d0bc741f36f4df", size = 585606, upload-time = "2025-12-30T19:14:50.595Z" },
 ]
 
+[[package]]
+name = "piper-tts"
+version = "1.3.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "onnxruntime" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9b/c0/d9b5f64869274be3ebc6dc483f13791a3c6ebbc0e37fad4e237a76d5365b/piper_tts-1.3.0-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:0af0c90aeddf762555ed940de1ac576acbefb3623e6d5ca4fb1a70359ee7e65d", size = 13819597, upload-time = "2025-07-10T21:07:22.893Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/17/6a059c0a45e582fadd4545ed092294fd0add7c679f6c09440af5cd2678b5/piper_tts-1.3.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:810c91a084d335d32b42928b1ef69d6480cf7e3a5a8b15eff98edd2ef55f2791", size = 13828403, upload-time = "2025-07-10T21:07:25.386Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/92/f37e5111440fc6c6336f42f8dab88afaa545394784dc930f808a68883c48/piper_tts-1.3.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8d39f85c3f4b6ade512976849579344fc72595ec613f374dbcf8521716398907", size = 13836863, upload-time = "2025-07-10T21:07:27.616Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/73/3d29175cfd93e791baaef3335819778d3f8c8898e2fe16cd0cc8b8163f84/piper_tts-1.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:234c25474655b26f3418b84522c815c43e9b1bc8a1fdb13c2b28514290c165f0", size = 13836748, upload-time = "2025-07-10T21:07:29.912Z" },
+    { url = "https://files.pythonhosted.org/packages/10/a5/d782d469fc19db9bf19f1725d4a6ef77d2413515b61f5017340688f5d093/piper_tts-1.3.0-cp39-abi3-win_amd64.whl", hash = "sha256:dc6b5be4e15f3c0f4a6067b515bc6202ddf3e2b0c6cbd6c8bdeccab2453c89c7", size = 13826773, upload-time = "2025-07-10T21:07:31.95Z" },
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.5.1"

From 11daa43b1b898493d7118233c577ad7ee25321e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 28 Jan 2026 23:54:17 -0800
Subject: [PATCH 3/5] TTSService: resample _stream_audio_frames_from_iterator()
 input audio if needed

---
 src/pipecat/services/tts_service.py | 42 ++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/src/pipecat/services/tts_service.py b/src/pipecat/services/tts_service.py
index e04c4b649..37aad0372 100644
--- a/src/pipecat/services/tts_service.py
+++ b/src/pipecat/services/tts_service.py
@@ -24,6 +24,7 @@ from typing import (
 
 from loguru import logger
 
+from pipecat.audio.utils import create_stream_resampler
 from pipecat.frames.frames import (
     AggregatedTextFrame,
     AggregationType,
@@ -202,6 +203,8 @@ class TTSService(AIService):
                 )
             self._text_filters = [text_filter]
 
+        self._resampler = create_stream_resampler()
+
         self._stop_frame_task: Optional[asyncio.Task] = None
         self._stop_frame_queue: asyncio.Queue = asyncio.Queue()
 
@@ -505,12 +508,40 @@ 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
+        self,
+        iterator: AsyncIterator[bytes],
+        *,
+        strip_wav_header: bool = False,
+        in_sample_rate: Optional[int] = None,
     ) -> AsyncGenerator[Frame, None]:
+        """Stream audio frames from an async byte iterator with optional resampling.
+
+        For WAV data, use `strip_wav_header=True` to strip the header and
+        auto-detect the source sample rate. For raw PCM data, pass
+        `in_sample_rate` directly. Audio is resampled to `self.sample_rate` when
+        the source rate differs.
+
+        Args:
+            iterator: Async iterator yielding audio bytes.
+            strip_wav_header: Strip WAV header and parse source sample rate from it.
+            in_sample_rate: Source sample rate for raw PCM data. Overrides
+                WAV-detected rate if both are provided.
+
+        """
         buffer = bytearray()
+        source_sample_rate = in_sample_rate
         need_to_strip_wav_header = strip_wav_header
+
+        async def maybe_resample(audio: bytes) -> bytes:
+            if source_sample_rate and source_sample_rate != self.sample_rate:
+                return await self._resampler.resample(audio, source_sample_rate, self.sample_rate)
+            return audio
+
         async for chunk in iterator:
             if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
+                # Parse sample rate from WAV header (bytes 24-28, little-endian uint32).
+                if len(chunk) >= 44 and source_sample_rate is None:
+                    source_sample_rate = int.from_bytes(chunk[24:28], "little")
                 chunk = chunk[44:]
                 need_to_strip_wav_header = False
 
@@ -520,19 +551,18 @@ class TTSService(AIService):
             # Round to nearest even number.
             aligned_length = len(buffer) & ~1  # 111111111...11110
             if aligned_length > 0:
-                aligned_chunk = buffer[:aligned_length]
+                aligned_chunk = await maybe_resample(bytes(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
+                    yield TTSAudioRawFrame(aligned_chunk, self.sample_rate, 1)
 
         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
+            audio = await maybe_resample(bytes(buffer))
+            yield TTSAudioRawFrame(audio, self.sample_rate, 1)
 
     async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         self._processing_text = False

From 5a85e27cc52393ba633b39095aec24308c2a9311 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 28 Jan 2026 23:55:07 -0800
Subject: [PATCH 4/5] PiperHttpTTSService: allow passing a voice id

---
 src/pipecat/services/piper/tts.py | 41 +++++++++++++++----------------
 1 file changed, 20 insertions(+), 21 deletions(-)

diff --git a/src/pipecat/services/piper/tts.py b/src/pipecat/services/piper/tts.py
index ca809f469..1de1688b1 100644
--- a/src/pipecat/services/piper/tts.py
+++ b/src/pipecat/services/piper/tts.py
@@ -13,7 +13,6 @@ from typing import AsyncGenerator, AsyncIterator, Optional
 import aiohttp
 from loguru import logger
 
-from pipecat.audio.utils import create_stream_resampler
 from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
@@ -63,8 +62,6 @@ class PiperTTSService(TTSService):
 
         self._voice_id = voice_id
 
-        self._resampler = create_stream_resampler()
-
         download_dir = download_dir or Path.cwd()
 
         model_file = f"{voice_id}.onnx"
@@ -105,17 +102,12 @@ class PiperTTSService(TTSService):
             except StopIteration:
                 return None
 
-        async def async_iterator(iterator, sample_rate: int) -> AsyncIterator[bytes]:
+        async def async_iterator(iterator) -> AsyncIterator[bytes]:
             while True:
                 item = await asyncio.to_thread(async_next, iterator)
                 if item is None:
                     return
-
-                audio_data = await self._resampler.resample(
-                    item.audio_int16_bytes, sample_rate, self.sample_rate
-                )
-
-                yield audio_data
+                yield item.audio_int16_bytes
 
         logger.debug(f"{self}: Generating TTS [{text}]")
 
@@ -127,8 +119,8 @@ class PiperTTSService(TTSService):
             yield TTSStartedFrame()
 
             async for frame in self._stream_audio_frames_from_iterator(
-                async_iterator(self._voice.synthesize(text), self._voice.config.sample_rate),
-                strip_wav_header=False,
+                async_iterator(self._voice.synthesize(text)),
+                in_sample_rate=self._voice.config.sample_rate,
             ):
                 await self.stop_ttfb_metrics()
                 yield frame
@@ -143,6 +135,12 @@ class PiperTTSService(TTSService):
 
 # This assumes a running TTS service running:
 # https://github.com/OHF-Voice/piper1-gpl/blob/main/docs/API_HTTP.md
+#
+# Usage:
+#
+#  $ uv pip install "piper-tts[http]"
+#  $ uv run python -m piper.http_server -m en_US-ryan-high
+#
 class PiperHttpTTSService(TTSService):
     """Piper HTTP TTS service implementation.
 
@@ -156,9 +154,7 @@ class PiperHttpTTSService(TTSService):
         *,
         base_url: str,
         aiohttp_session: aiohttp.ClientSession,
-        # When using Piper, the sample rate of the generated audio depends on the
-        # voice model being used.
-        sample_rate: Optional[int] = None,
+        voice_id: Optional[str] = None,
         **kwargs,
     ):
         """Initialize the Piper TTS service.
@@ -166,10 +162,10 @@ class PiperHttpTTSService(TTSService):
         Args:
             base_url: Base URL for the Piper TTS HTTP server.
             aiohttp_session: aiohttp ClientSession for making HTTP requests.
-            sample_rate: Output sample rate. If None, uses the voice model's native rate.
+            voice_id: Piper voice model identifier (e.g. `en_US-ryan-high`).
             **kwargs: Additional arguments passed to the parent TTSService.
         """
-        super().__init__(sample_rate=sample_rate, **kwargs)
+        super().__init__(**kwargs)
 
         if base_url.endswith("/"):
             logger.warning("Base URL ends with a slash, this is not allowed.")
@@ -177,7 +173,7 @@ class PiperHttpTTSService(TTSService):
 
         self._base_url = base_url
         self._session = aiohttp_session
-        self._settings = {"base_url": base_url}
+        self._model_id = voice_id
 
     def can_generate_metrics(self) -> bool:
         """Check if this service can generate processing metrics.
@@ -204,9 +200,12 @@ class PiperHttpTTSService(TTSService):
         try:
             await self.start_ttfb_metrics()
 
-            async with self._session.post(
-                self._base_url, json={"text": text}, headers=headers
-            ) as response:
+            data = {
+                "text": text,
+                "voice": self._model_id,
+            }
+
+            async with self._session.post(self._base_url, json=data, headers=headers) as response:
                 if response.status != 200:
                     error = await response.text()
                     yield ErrorFrame(

From bd005870920a6598dfaa5d471dfa770619b2a49c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Wed, 28 Jan 2026 23:59:37 -0800
Subject: [PATCH 5/5] changelog: add files for 3585

---
 changelog/3585.added.md | 1 +
 changelog/3585.fixed.md | 1 +
 2 files changed, 2 insertions(+)
 create mode 100644 changelog/3585.added.md
 create mode 100644 changelog/3585.fixed.md

diff --git a/changelog/3585.added.md b/changelog/3585.added.md
new file mode 100644
index 000000000..7335d2c18
--- /dev/null
+++ b/changelog/3585.added.md
@@ -0,0 +1 @@
+- Added local `PiperTTSService` for offline text-to-speech using Piper voice models. The existing HTTP-based service has been renamed to `PiperHttpTTSService`.
diff --git a/changelog/3585.fixed.md b/changelog/3585.fixed.md
new file mode 100644
index 000000000..4993ed2f7
--- /dev/null
+++ b/changelog/3585.fixed.md
@@ -0,0 +1 @@
+- Fixed `PiperHttpTTSService` (olf `PiperTTSService`) to resample audio output based on the model's sample rate parsed from the WAV header.