diff --git a/CHANGELOG.md b/CHANGELOG.md index 6ced4feab..51a2a8600 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -29,6 +29,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Added `14w-function-calling-mistal.py` using `MistralLLMService`. +- Added `13j-azure-transcription.py` using `AzureSTTService`. + ## [0.0.80] - 2025-08-13 ### Added diff --git a/examples/foundational/13j-azure-transcription.py b/examples/foundational/13j-azure-transcription.py new file mode 100644 index 000000000..66834a30b --- /dev/null +++ b/examples/foundational/13j-azure-transcription.py @@ -0,0 +1,88 @@ +# +# 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.frames.frames import Frame, TranscriptionFrame +from pipecat.pipeline.pipeline import Pipeline +from pipecat.pipeline.runner import PipelineRunner +from pipecat.pipeline.task import PipelineTask +from pipecat.processors.frame_processor import FrameDirection, FrameProcessor +from pipecat.runner.types import RunnerArguments +from pipecat.runner.utils import create_transport +from pipecat.services.azure.stt import AzureSTTService +from pipecat.transports.base_transport import BaseTransport, TransportParams +from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams +from pipecat.transports.services.daily import DailyParams + +load_dotenv(override=True) + + +class TranscriptionLogger(FrameProcessor): + async def process_frame(self, frame: Frame, direction: FrameDirection): + await super().process_frame(frame, direction) + + if isinstance(frame, TranscriptionFrame): + print(f"Transcription: {frame.text}") + + +transport_params = { + "daily": lambda: DailyParams( + audio_in_enabled=True, + vad_analyzer=SileroVADAnalyzer(), + ), + "twilio": lambda: FastAPIWebsocketParams( + audio_in_enabled=True, + vad_analyzer=SileroVADAnalyzer(), + ), + "webrtc": lambda: TransportParams( + audio_in_enabled=True, + vad_analyzer=SileroVADAnalyzer(), + ), +} + + +async def run_bot(transport: BaseTransport, runner_args: RunnerArguments): + logger.info(f"Starting bot") + + stt = AzureSTTService( + api_key=os.getenv("AZURE_SPEECH_API_KEY"), + region=os.getenv("AZURE_SPEECH_REGION"), + ) + + tl = TranscriptionLogger() + + pipeline = Pipeline([transport.input(), stt, tl]) + + task = PipelineTask( + pipeline, + idle_timeout_secs=runner_args.pipeline_idle_timeout_secs, + ) + + @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/uv.lock b/uv.lock index 51c246e94..bbe6a1ca8 100644 --- a/uv.lock +++ b/uv.lock @@ -3099,12 +3099,12 @@ name = "mlx-lm" version = "0.26.3" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "jinja2" }, - { name = "mlx" }, - { name = "numpy" }, - { name = "protobuf" }, - { name = "pyyaml" }, - { name = "transformers" }, + { name = "jinja2", marker = "sys_platform == 'darwin'" }, + { name = "mlx", marker = "sys_platform == 'darwin'" }, + { name = "numpy", marker = "sys_platform == 'darwin'" }, + { name = "protobuf", marker = "sys_platform == 'darwin'" }, + { name = "pyyaml", marker = "sys_platform == 'darwin'" }, + { name = "transformers", marker = "sys_platform == 'darwin'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/af/4b/ed8ec01f182203b0897415a9d20f0cd8a141def77ad43deea18ffaba4c9c/mlx_lm-0.26.3.tar.gz", hash = "sha256:06cd74ee3eea920335c528e68feb854eede45fe4e5f149b464ac100c1dbeaded", size = 172096, upload-time = "2025-08-06T21:48:22.762Z" } wheels = [ @@ -3598,7 +3598,7 @@ name = "nvidia-cudnn-cu12" version = "9.5.1.17" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/2a/78/4535c9c7f859a64781e43c969a3a7e84c54634e319a996d43ef32ce46f83/nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_x86_64.whl", hash = "sha256:30ac3869f6db17d170e0e556dd6cc5eee02647abc31ca856634d5a40f82c15b2", size = 570988386, upload-time = "2024-10-25T19:54:26.39Z" }, @@ -3609,7 +3609,7 @@ name = "nvidia-cufft-cu12" version = "11.3.0.4" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/8f/16/73727675941ab8e6ffd86ca3a4b7b47065edcca7a997920b831f8147c99d/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ccba62eb9cef5559abd5e0d54ceed2d9934030f51163df018532142a8ec533e5", size = 200221632, upload-time = "2024-11-20T17:41:32.357Z" }, @@ -3638,9 +3638,9 @@ name = "nvidia-cusolver-cu12" version = "11.7.1.2" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12" }, - { name = "nvidia-cusparse-cu12" }, - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, + { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/f0/6e/c2cf12c9ff8b872e92b4a5740701e51ff17689c4d726fca91875b07f655d/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e9e49843a7707e42022babb9bcfa33c29857a93b88020c4e4434656a655b698c", size = 158229790, upload-time = "2024-11-20T17:43:43.211Z" }, @@ -3652,7 +3652,7 @@ name = "nvidia-cusparse-cu12" version = "12.5.4.2" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/06/1e/b8b7c2f4099a37b96af5c9bb158632ea9e5d9d27d7391d7eb8fc45236674/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7556d9eca156e18184b94947ade0fba5bb47d69cec46bf8660fd2c71a4b48b73", size = 216561367, upload-time = "2024-11-20T17:44:54.824Z" }, @@ -4483,7 +4483,7 @@ requires-dist = [ { name = "websockets", marker = "extra == 'soniox'", specifier = ">=13.1,<15.0" }, { name = "websockets", marker = "extra == 'websocket'", specifier = ">=13.1,<15.0" }, ] -provides-extras = ["anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "deepseek", "daily", "deepgram", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "inworld", "krisp", "koala", "langchain", "livekit", "lmnt", "local", "mcp", "mem0", "mlx-whisper", "moondream", "nim", "neuphonic", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "rime", "riva", "runner", "sambanova", "sentry", "local-smart-turn", "remote-smart-turn", "silero", "simli", "soniox", "soundfile", "speechmatics", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "whisper"] +provides-extras = ["anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "deepseek", "daily", "deepgram", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "inworld", "krisp", "koala", "langchain", "livekit", "lmnt", "local", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "nim", "neuphonic", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "rime", "riva", "runner", "sambanova", "sentry", "local-smart-turn", "remote-smart-turn", "silero", "simli", "soniox", "soundfile", "speechmatics", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "whisper"] [package.metadata.requires-dev] dev = [ @@ -7050,7 +7050,7 @@ name = "triton" version = "3.3.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "setuptools" }, + { name = "setuptools", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/76/04/d54d3a6d077c646624dc9461b0059e23fd5d30e0dbe67471e3654aec81f9/triton-3.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fad99beafc860501d7fcc1fb7045d9496cbe2c882b1674640304949165a916e7", size = 156441993, upload-time = "2025-04-09T20:27:25.107Z" }, @@ -7562,8 +7562,8 @@ name = "xformers" version = "0.0.30" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "numpy" }, - { name = "torch" }, + { name = "numpy", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, + { name = "torch", marker = "(platform_machine != 'aarch64' and sys_platform == 'linux') or (sys_platform != 'darwin' and sys_platform != 'linux')" }, ] sdist = { url = "https://files.pythonhosted.org/packages/bf/f7/dd2269cce89fd1221947dd7cc3a60707ffe721ef55c1803ac3b1a1f7ae5c/xformers-0.0.30.tar.gz", hash = "sha256:a12bf3eb39e294cdbe8a7253ac9b665f41bac61d6d98df174e34ef7bdb6f2fc4", size = 10214139, upload-time = "2025-04-28T20:51:02.045Z" } wheels = [