Add model-specific sample rates, transport example, and fix audio buffer alignment

examples/foundational/07zb-interruptible-camb-local.py

@@ -6,11 +6,8 @@
 
 """Camb.ai TTS example with local audio (microphone/speakers).
 
-This example demonstrates:
-- Camb.ai MARS TTS with streaming audio
-- Local audio input/output (no WebRTC or Daily needed)
-- TTFB metrics tracking
-- End-to-end latency measurement (user speech → AI response)
+This is a standalone local example for quick testing without WebRTC/Daily.
+For production use with Daily/Twilio/WebRTC, see 07zb-interruptible-camb.py
 
 Requirements:
 - CAMB_API_KEY environment variable
@@ -108,7 +105,7 @@ DEFAULT_VOICE_ID = 147320
 
 
 async def main(voice_id: int):
-    sample_rate = 48000
+    sample_rate = 22050  # mars-flash uses 22.05kHz
 
     # Local audio transport - uses your microphone and speakers
     # Increase audio_out_10ms_chunks for larger buffer (default is 4 = 40ms)
@@ -124,7 +121,7 @@ async def main(voice_id: int):
     # Deepgram STT for speech recognition
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    # Camb.ai TTS (48kHz output)
+    # Camb.ai TTS
     tts = CambTTSService(
         api_key=os.getenv("CAMB_API_KEY"),
         voice_id=voice_id,

examples/foundational/07zb-interruptible-camb.py

@@ -0,0 +1,123 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+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
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.camb.tts import CambTTSService
+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.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+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("Starting Camb.ai TTS bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CambTTSService(
+        api_key=os.getenv("CAMB_API_KEY"),
+        model="mars-flash",
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful voice assistant powered by Camb.ai text-to-speech. "
+            "Keep your responses concise and conversational since they will be spoken aloud. "
+            "Avoid special characters, emojis, or bullet points.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    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")
+        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("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()