Pipecat uplift

docs/integrations-and-sdks/index.mdx

@@ -39,7 +39,7 @@ Choose an integration to build accurate, low-latency voice agents rapidly with t
     title="Pipecat"
     description="Open-source framework with full control of the voice pipeline in code. Complex agents. Best for: power builders."
     icon={<img src="/img/integration-logos/pipecat.png" alt="Pipecat logo" width="28px" height="28px" />}
-    href="/integrations-and-sdks/pipecat"
+    href="/integrations-and-sdks/pipecat/"
   />
 
 </Grid>

docs/integrations-and-sdks/pipecat/assets/main.py

@@ -0,0 +1,126 @@
+import os
+
+import aiohttp
+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.openai.llm import OpenAILLMService
+from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.turns.user_stop.turn_analyzer_user_turn_stop_strategy import (
+    TurnAnalyzerUserTurnStopStrategy,
+)
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
+
+load_dotenv(override=True)
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = SpeechmaticsSTTService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            params=SpeechmaticsSTTService.InputParams(
+                turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.EXTERNAL,
+            ),
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o-mini",
+        )
+
+        tts = SpeechmaticsTTSService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            voice_id="sarah",
+            aiohttp_session=session,
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful voice assistant. Be concise and friendly.",
+            },
+        ]
+
+        context = LLMContext(messages)
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(
+                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(
+                            turn_analyzer=LocalSmartTurnAnalyzerV3()
+                        )
+                    ]
+                ),
+            ),
+        )
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                stt,
+                user_aggregator,
+                llm,
+                tts,
+                transport.output(),
+                assistant_aggregator,
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+        )
+
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info("Client connected")
+            await task.queue_frames([LLMRunFrame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info("Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    transport_params = {
+        "webrtc": lambda: TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+        ),
+    }
+
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

docs/integrations-and-sdks/pipecat/assets/stt-full-example.py

@@ -0,0 +1,35 @@
+from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+
+stt = SpeechmaticsSTTService(
+    params=SpeechmaticsSTTService.InputParams(
+        # Service options
+        language="en",
+        operating_point=SpeechmaticsSTTService.OperatingPoint.ENHANCED,
+
+        # Turn detection
+        turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.EXTERNAL,
+        max_delay=1.5,
+        include_partials=True,
+
+        # Diarization
+        enable_diarization=True,
+        speaker_sensitivity=0.6,
+        max_speakers=4,
+        prefer_current_speaker=True,
+
+        # Speaker focus
+        focus_speakers=["S1", "S2"],
+        focus_mode=SpeechmaticsSTTService.SpeakerFocusMode.RETAIN,
+        ignore_speakers=[],
+
+        # Output formatting
+        speaker_active_format="[{speaker_id}]: {text}",
+        speaker_passive_format="[{speaker_id} (background)]: {text}",
+
+        # Custom vocabulary
+        additional_vocab=[
+            SpeechmaticsSTTService.AdditionalVocabEntry(content="Speechmatics"),
+            SpeechmaticsSTTService.AdditionalVocabEntry(content="Pipecat", sounds_like=["pipe cat"]),
+        ],
+    ),
+)

docs/integrations-and-sdks/pipecat/index.mdx

@@ -0,0 +1,88 @@
+---
+ description: Build a local voice bot with Speechmatics STT and TTS using Pipecat.
+---
+
+import CodeBlock from '@theme/CodeBlock'
+import pipecatQuickstartMainPy from "./assets/main.py?raw"
+
+# Pipecat quickstart
+
+Build a local voice bot with Speechmatics and Pipecat in minutes.
+
+[Pipecat](https://docs.pipecat.ai/) is a framework for building real-time voice bots using a pipeline architecture. In this quickstart, you’ll run a local WebRTC server and connect to your bot from your browser.
+
+## Features
+
+- **Real-time transcription** — Low-latency speech-to-text as users speak
+- **Natural text to speech** — Give your bot a clear, natural voice
+- **Local web client** — Test your bot in a browser at `http://localhost:7860/client`
+- **No infrastructure** — No cloud deployment or room setup required
+
+## Prerequisites
+
+- Python 3.10+
+- [Speechmatics API key](https://portal.speechmatics.com)
+- [OpenAI API key](https://platform.openai.com) (for the LLM)
+
+## Setup
+
+### 1. Create project
+
+```bash
+mkdir voice-agent && cd voice-agent
+```
+
+### 2. Install dependencies
+
+Create a `requirements.txt` file:
+
+```text title="requirements.txt"
+pipecat-ai[local-smart-turn-v3,silero,speechmatics,webrtc,openai,runner]
+pipecat-ai-small-webrtc-prebuilt
+python-dotenv
+loguru
+```
+
+Install with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv venv
+source .venv/bin/activate
+uv pip install -r requirements.txt
+```
+
+### 3. Configure environment
+
+Create a `.env` file:
+
+```text title=".env"
+SPEECHMATICS_API_KEY=your_speechmatics_key
+OPENAI_API_KEY=your_openai_key
+```
+
+### 4. Create your bot
+
+Create a `main.py` file:
+
+<CodeBlock language="python" title="main.py">
+  {pipecatQuickstartMainPy}
+</CodeBlock>
+
+### 5. Run your bot
+
+```bash
+python main.py
+```
+
+Open `http://localhost:7860/client` in your browser and allow microphone access.
+
+:::note
+The first run can take a little longer while dependencies and models load.
+:::
+
+## Next steps
+
+- [Speech to text](/integrations-and-sdks/pipecat/stt) — Configure diarization, turn detection, and more
+- [Text to speech](/integrations-and-sdks/pipecat/tts) — Choose voices and adjust settings
+- [Speechmatics Academy](https://github.com/speechmatics/speechmatics-academy/tree/main/integrations/pipecat) — Full working examples
+- [Pipecat quickstart](https://docs.pipecat.ai/getting-started/quickstart) — Learn more patterns and deployment options

docs/integrations-and-sdks/pipecat/sidebar.ts

@@ -0,0 +1,23 @@
+export default {
+  type: "category",
+  label: "Pipecat",
+  collapsible: true,
+  collapsed: true,
+  items: [
+    {
+      type: "doc",
+      id: "integrations-and-sdks/pipecat/index",
+      label: "Quickstart",
+    },
+    {
+      type: "doc",
+      id: "integrations-and-sdks/pipecat/stt",
+      label: "STT",
+    },
+    {
+      type: "doc",
+      id: "integrations-and-sdks/pipecat/tts",
+      label: "TTS",
+    },
+  ],
+} as const;