speechmatics-voice 0.1.0__tar.gz

speechmatics_voice-0.1.0/PKG-INFO

@@ -0,0 +1,140 @@
+Metadata-Version: 2.4
+Name: speechmatics-voice
+Version: 0.1.0
+Summary: Speechmatics Voice Agent Python client for Real-Time API
+Author-email: Speechmatics <support@speechmatics.com>
+License-Expression: MIT
+Project-URL: homepage, https://github.com/speechmatics/speechmatics-python-sdk
+Project-URL: documentation, https://docs.speechmatics.com/
+Project-URL: repository, https://github.com/speechmatics/speechmatics-python-sdk
+Project-URL: issues, https://github.com/speechmatics/speechmatics-python-sdk/issues
+Keywords: speechmatics,conversational-ai,voice,agents,websocket,real-time,pipecat,livekit
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: websockets>=10.0
+Provides-Extra: dev
+Requires-Dist: black; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: pre-commit; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: pytest-mock; extra == "dev"
+Requires-Dist: build; extra == "dev"
+
+# Voice Agent Python client for Speechmatics Real-Time API
+
+[![License](https://img.shields.io/badge/license-MIT-yellow.svg)](https://github.com/speechmatics/speechmatics-python-voice/blob/master/LICENSE)
+
+An SDK for working with the Speechmatics Real-Time API optimised for use in voice agents or transcription services.
+
+This uses the Python Real-Time API to process the transcription results from the STT engine and combine them into manageable segments of audio. Taking advantage of speaker diarization, the transcription is grouped into individual speakers, with advanced options to focus on and/or ignore specific speakers.
+
+See [OVERVIEW.md](OVERVIEW.md) for more information.
+
+## Installation
+
+```bash
+pip install speechmatics-voice
+```
+
+## Requirements
+
+You must have a valid Speechmatics API key to use this SDK. You can get one from the [Speechmatics Console](https://console.speechmatics.com).
+
+Store this as `SPEECHMATICS_API_KEY` environment variable in your `.env` file or use `export SPEECHMATICS_API_KEY="your_api_key_here"` in your terminal.
+
+## Quick Start
+
+Below is a basic example of how to use the SDK to transcribe audio from a microphone.
+
+```python
+import asyncio
+from speechmatics.rt import Microphone
+from speechmatics.voice import (
+    VoiceAgentClient,
+    VoiceAgentConfig,
+    EndOfUtteranceMode,
+    AgentServerMessageType,
+    SpeakerSegment,
+)
+
+async def main():
+    # Configure the voice agent
+    config = VoiceAgentConfig(
+        end_of_utterance_silence_trigger=0.5,
+        enable_diarization=True,
+        end_of_utterance_mode=EndOfUtteranceMode.ADAPTIVE,
+    )
+
+    # Initialize microphone
+    mic = Microphone(
+        sample_rate=16000,
+        chunk_size=160,
+    )
+
+    if not mic.start():
+        print("Microphone not available")
+        return
+
+    # Create client and register event handlers
+    async with VoiceAgentClient(config=config) as client:
+
+        # Handle interim transcription segments
+        @client.on(AgentServerMessageType.ADD_INTERIM_SEGMENTS)
+        def handle_interim_segments(message):
+            segments: list[SpeakerSegment] = message["segments"]
+            for segment in segments:
+                print(f"Speaker {segment.speaker_id}: {segment.text}")
+
+        # Handle finalized transcription segments
+        @client.on(AgentServerMessageType.ADD_SEGMENTS)
+        def handle_final_segments(message):
+            segments: list[SpeakerSegment] = message["segments"]
+            for segment in segments:
+                print(f"Speaker {segment.speaker_id}: {segment.text}")
+
+        # Handle user started speaking event
+        @client.on(AgentServerMessageType.USER_SPEECH_STARTED)
+        def handle_speech_started(message):
+            print("User started speaking")
+
+        # Handle user stopped speaking event
+        @client.on(AgentServerMessageType.USER_SPEECH_ENDED)
+        def handle_speech_ended(message):
+            print("User stopped speaking")
+
+        # Connect and start processing audio
+        await client.connect()
+
+        while True:
+            frame = await mic.read(160)
+            await client.send_audio(frame)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Examples
+
+The `examples/` directory contains practical demonstrations of the Voice Agent SDK. See the README in the `examples/voice` directory for more information.
+
+## Documentation
+
+- **SDK Overview**: See [OVERVIEW.md](OVERVIEW.md) for comprehensive API documentation
+- **Speechmatics API**: https://docs.speechmatics.com
+
+## License
+
+[MIT](LICENSE)

speechmatics_voice-0.1.0/README.md

@@ -0,0 +1,105 @@
+# Voice Agent Python client for Speechmatics Real-Time API
+
+[![License](https://img.shields.io/badge/license-MIT-yellow.svg)](https://github.com/speechmatics/speechmatics-python-voice/blob/master/LICENSE)
+
+An SDK for working with the Speechmatics Real-Time API optimised for use in voice agents or transcription services.
+
+This uses the Python Real-Time API to process the transcription results from the STT engine and combine them into manageable segments of audio. Taking advantage of speaker diarization, the transcription is grouped into individual speakers, with advanced options to focus on and/or ignore specific speakers.
+
+See [OVERVIEW.md](OVERVIEW.md) for more information.
+
+## Installation
+
+```bash
+pip install speechmatics-voice
+```
+
+## Requirements
+
+You must have a valid Speechmatics API key to use this SDK. You can get one from the [Speechmatics Console](https://console.speechmatics.com).
+
+Store this as `SPEECHMATICS_API_KEY` environment variable in your `.env` file or use `export SPEECHMATICS_API_KEY="your_api_key_here"` in your terminal.
+
+## Quick Start
+
+Below is a basic example of how to use the SDK to transcribe audio from a microphone.
+
+```python
+import asyncio
+from speechmatics.rt import Microphone
+from speechmatics.voice import (
+    VoiceAgentClient,
+    VoiceAgentConfig,
+    EndOfUtteranceMode,
+    AgentServerMessageType,
+    SpeakerSegment,
+)
+
+async def main():
+    # Configure the voice agent
+    config = VoiceAgentConfig(
+        end_of_utterance_silence_trigger=0.5,
+        enable_diarization=True,
+        end_of_utterance_mode=EndOfUtteranceMode.ADAPTIVE,
+    )
+
+    # Initialize microphone
+    mic = Microphone(
+        sample_rate=16000,
+        chunk_size=160,
+    )
+
+    if not mic.start():
+        print("Microphone not available")
+        return
+
+    # Create client and register event handlers
+    async with VoiceAgentClient(config=config) as client:
+
+        # Handle interim transcription segments
+        @client.on(AgentServerMessageType.ADD_INTERIM_SEGMENTS)
+        def handle_interim_segments(message):
+            segments: list[SpeakerSegment] = message["segments"]
+            for segment in segments:
+                print(f"Speaker {segment.speaker_id}: {segment.text}")
+
+        # Handle finalized transcription segments
+        @client.on(AgentServerMessageType.ADD_SEGMENTS)
+        def handle_final_segments(message):
+            segments: list[SpeakerSegment] = message["segments"]
+            for segment in segments:
+                print(f"Speaker {segment.speaker_id}: {segment.text}")
+
+        # Handle user started speaking event
+        @client.on(AgentServerMessageType.USER_SPEECH_STARTED)
+        def handle_speech_started(message):
+            print("User started speaking")
+
+        # Handle user stopped speaking event
+        @client.on(AgentServerMessageType.USER_SPEECH_ENDED)
+        def handle_speech_ended(message):
+            print("User stopped speaking")
+
+        # Connect and start processing audio
+        await client.connect()
+
+        while True:
+            frame = await mic.read(160)
+            await client.send_audio(frame)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Examples
+
+The `examples/` directory contains practical demonstrations of the Voice Agent SDK. See the README in the `examples/voice` directory for more information.
+
+## Documentation
+
+- **SDK Overview**: See [OVERVIEW.md](OVERVIEW.md) for comprehensive API documentation
+- **Speechmatics API**: https://docs.speechmatics.com
+
+## License
+
+[MIT](LICENSE)

speechmatics_voice-0.1.0/pyproject.toml

@@ -0,0 +1,67 @@
+[build-system]
+requires = ["setuptools>=61.0.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "speechmatics-voice"
+dynamic = ["version"]
+description = "Speechmatics Voice Agent Python client for Real-Time API"
+readme = "README.md"
+authors = [{ name = "Speechmatics", email = "support@speechmatics.com" }]
+license = "MIT"
+requires-python = ">=3.9"
+dependencies = ["websockets>=10.0"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Operating System :: OS Independent",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+keywords = [
+    "speechmatics",
+    "conversational-ai",
+    "voice",
+    "agents",
+    "websocket",
+    "real-time",
+    "pipecat",
+    "livekit"
+]
+
+[project.optional-dependencies]
+dev = [
+    "black",
+    "ruff",
+    "mypy",
+    "pre-commit",
+    "pytest",
+    "pytest-asyncio",
+    "pytest-cov",
+    "pytest-mock",
+    "build",
+]
+
+[project.urls]
+homepage = "https://github.com/speechmatics/speechmatics-python-sdk"
+documentation = "https://docs.speechmatics.com/"
+repository = "https://github.com/speechmatics/speechmatics-python-sdk"
+issues = "https://github.com/speechmatics/speechmatics-python-sdk/issues"
+
+[tool.setuptools.dynamic]
+version = { attr = "speechmatics.voice.__version__" }
+
+[tool.setuptools.package-data]
+"speechmatics.voice" = ["py.typed"]
+
+[tool.setuptools.packages.find]
+where = ["."]
+
+[[tool.mypy.overrides]]
+module = ["speechmatics.rt.*"]
+ignore_missing_imports = true

speechmatics_voice-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

speechmatics_voice-0.1.0/speechmatics/__init__.py

@@ -0,0 +1 @@
+__path__ = __import__("pkgutil").extend_path(__path__, __name__)

speechmatics_voice-0.1.0/speechmatics/voice/__init__.py

@@ -0,0 +1,59 @@
+#
+# Copyright (c) 2025, Speechmatics / Cantab Research Ltd
+#
+
+
+"""Voice Agents SDK.
+
+A comprehensive set of utility classes tailored for Voice Agents and
+using the Speechmatics Python Real-Time SDK, including the processing of
+partial and final transcription from the STT engine into accumulated
+transcriptions with flags to indicate changes between messages, etc.
+"""
+
+__version__ = "0.1.0"
+
+from speechmatics.rt import AudioEncoding
+from speechmatics.rt import AudioFormat
+from speechmatics.rt import OperatingPoint
+
+from ._client import VoiceAgentClient
+from ._models import AdditionalVocabEntry
+from ._models import AgentClientMessageType
+from ._models import AgentServerMessageType
+from ._models import AnnotationFlags
+from ._models import AnnotationResult
+from ._models import DiarizationFocusMode
+from ._models import DiarizationKnownSpeaker
+from ._models import DiarizationSpeakerConfig
+from ._models import EndOfUtteranceMode
+from ._models import SpeakerSegment
+from ._models import SpeakerVADStatus
+from ._models import SpeechFragment
+from ._models import VoiceAgentConfig
+
+__all__ = [
+    # SDK
+    "__version__",
+    # Conversation config
+    "VoiceAgentConfig",
+    "EndOfUtteranceMode",
+    "DiarizationSpeakerConfig",
+    "DiarizationFocusMode",
+    "AdditionalVocabEntry",
+    "DiarizationKnownSpeaker",
+    "AudioEncoding",
+    "AudioFormat",
+    "OperatingPoint",
+    # Transcription models
+    "AnnotationFlags",
+    "AnnotationResult",
+    "SpeakerSegment",
+    "SpeechFragment",
+    # Events
+    "SpeakerVADStatus",
+    # Client
+    "VoiceAgentClient",
+    "AgentClientMessageType",
+    "AgentServerMessageType",
+]