speechmatics-batch 0.1.0__tar.gz

speechmatics_batch-0.1.0/PKG-INFO

@@ -0,0 +1,289 @@
+Metadata-Version: 2.4
+Name: speechmatics-batch
+Version: 0.1.0
+Summary: Speechmatics Batch API Client
+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,speech-to-text,batch,transcription,api
+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: aiohttp
+Requires-Dist: aiofiles
+Provides-Extra: dev
+Requires-Dist: black; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: types-aiofiles; 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"
+
+# Speechmatics Batch API Client
+
+Async Python client for Speechmatics Batch API.
+
+## Features
+
+- Async API client with comprehensive error handling
+- Type hints throughout for better IDE support
+- Environment variable support for credentials
+- Easy-to-use interface for submitting, monitoring, and retrieving transcription jobs
+- Full job configuration support with all Speechmatics features
+- Intelligent transcript formatting with speaker diarization
+- Support for multiple output formats (JSON, TXT, SRT)
+
+## Installation
+
+```bash
+pip install speechmatics-batch
+```
+
+## Usage
+
+### Quick Start
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient
+
+async def main():
+    # Create a client using environment variable SPEECHMATICS_API_KEY
+    async with AsyncClient() as client:
+        # Simple transcription
+        result = await client.transcribe("audio.wav")
+        print(result.transcript_text)
+
+asyncio.run(main())
+```
+
+### Basic Job Workflow
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, JobConfig, JobType, TranscriptionConfig
+
+async def main():
+    # Create client with explicit API key
+    async with AsyncClient(api_key="your-api-key") as client:
+
+        # Configure transcription
+        config = JobConfig(
+            type=JobType.TRANSCRIPTION,
+            transcription_config=TranscriptionConfig(
+                language="en",
+                enable_entities=True,
+                diarization="speaker"
+            )
+        )
+
+        # Submit job
+        job = await client.submit_job("audio.wav", config=config)
+        print(f"Job submitted: {job.id}")
+
+        # Wait for completion
+        result = await client.wait_for_completion(
+            job.id,
+            polling_interval=2.0,
+            timeout=300.0
+        )
+
+        # Access results
+        print(f"Transcript: {result.transcript_text}")
+        print(f"Confidence: {result.confidence}")
+
+asyncio.run(main())
+```
+
+### Advanced Configuration
+
+```python
+import asyncio
+from speechmatics.batch import (
+    AsyncClient,
+    JobConfig,
+    JobType,
+    OperatingPoint,
+    TranscriptionConfig,
+    TranslationConfig,
+    SummarizationConfig
+)
+
+async def main():
+    async with AsyncClient(api_key="your-api-key") as client:
+
+        # Advanced job configuration
+        config = JobConfig(
+            type=JobType.TRANSCRIPTION,
+            transcription_config=TranscriptionConfig(
+                language="en",
+                operating_point=OperatingPoint.ENHANCED,
+                enable_entities=True,
+                diarization="speaker",
+            ),
+            translation_config=TranslationConfig(target_languages=["es", "fr"]),
+            summarization_config=SummarizationConfig(
+                content_type="conversational", summary_length="brief"
+            ),
+        )
+
+        result = await client.transcribe("audio.wav", config=config)
+
+        # Access advanced features
+        if result.summary:
+            print(f"Summary: {result.summary}")
+        if result.translations:
+            print(f"Translations: {result.translations}")
+
+asyncio.run(main())
+```
+
+### Manual Job Management
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, JobStatus
+
+async def main():
+    async with AsyncClient() as client:
+
+        # Submit job
+        job = await client.submit_job("audio.wav")
+
+        # Check job status
+        job_details = await client.get_job_info(job.id)
+        print(f"Status: {job_details.status}")
+
+        # Wait for completion manually
+        while job_details.status == JobStatus.RUNNING:
+            await asyncio.sleep(5)
+            job_details = await client.get_job_info(job.id)
+
+        if job_details.status == JobStatus.DONE:
+            # Get transcript
+            transcript = await client.get_transcript(job.id)
+            print(transcript.transcript_text)
+        else:
+            print(f"Job failed with status: {job_details.status}")
+
+asyncio.run(main())
+```
+
+### Different Output Formats
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, FormatType
+
+async def main():
+    async with AsyncClient() as client:
+        job = await client.submit_job("audio.wav")
+
+        # Get JSON format (default)
+        json_result = await client.get_transcript(job.id, format_type=FormatType.JSON)
+        print(json_result.transcript_text)
+
+        # Get plain text
+        txt_result = await client.get_transcript(job.id, format_type=FormatType.TXT)
+        print(txt_result)
+
+        # Get SRT subtitles
+        srt_result = await client.get_transcript(job.id, format_type=FormatType.SRT)
+        print(srt_result)
+
+asyncio.run(main())
+```
+
+### Error Handling
+
+```python
+import asyncio
+from speechmatics.batch import (
+    AsyncClient,
+    BatchError,
+    AuthenticationError,
+    JobError,
+    TimeoutError
+)
+
+async def main():
+    try:
+        async with AsyncClient() as client:
+            result = await client.transcribe("audio.wav", timeout=120.0)
+            print(result.transcript_text)
+
+    except AuthenticationError:
+        print("Invalid API key")
+    except BatchError as e:
+        print(f"Job submission failed: {e}")
+    except JobError as e:
+        print(f"Job processing failed: {e}")
+    except TimeoutError as e:
+        print(f"Job timed out: {e}")
+    except FileNotFoundError:
+        print("Audio file not found")
+
+asyncio.run(main())
+```
+
+### Connection Configuration
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, ConnectionConfig
+
+async def main():
+    # Custom connection settings
+    config = ConnectionConfig(
+        url="https://asr.api.speechmatics.com/v2",
+        api_key="your-api-key",
+        connect_timeout=30.0,
+        operation_timeout=600.0
+    )
+
+    async with AsyncClient(conn_config=config) as client:
+        result = await client.transcribe("audio.wav")
+        print(result.transcript_text)
+
+asyncio.run(main())
+```
+
+## Logging
+
+The client supports logging with job id tracing for debugging. To increase logging verbosity, set `DEBUG` level in your example code:
+
+```python
+import logging
+import sys
+
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+```
+
+## Environment Variables
+
+The client supports the following environment variables:
+
+- `SPEECHMATICS_API_KEY`: Your Speechmatics API key
+- `SPEECHMATICS_BATCH_URL`: Custom API endpoint URL (optional)

speechmatics_batch-0.1.0/README.md

@@ -0,0 +1,252 @@
+# Speechmatics Batch API Client
+
+Async Python client for Speechmatics Batch API.
+
+## Features
+
+- Async API client with comprehensive error handling
+- Type hints throughout for better IDE support
+- Environment variable support for credentials
+- Easy-to-use interface for submitting, monitoring, and retrieving transcription jobs
+- Full job configuration support with all Speechmatics features
+- Intelligent transcript formatting with speaker diarization
+- Support for multiple output formats (JSON, TXT, SRT)
+
+## Installation
+
+```bash
+pip install speechmatics-batch
+```
+
+## Usage
+
+### Quick Start
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient
+
+async def main():
+    # Create a client using environment variable SPEECHMATICS_API_KEY
+    async with AsyncClient() as client:
+        # Simple transcription
+        result = await client.transcribe("audio.wav")
+        print(result.transcript_text)
+
+asyncio.run(main())
+```
+
+### Basic Job Workflow
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, JobConfig, JobType, TranscriptionConfig
+
+async def main():
+    # Create client with explicit API key
+    async with AsyncClient(api_key="your-api-key") as client:
+
+        # Configure transcription
+        config = JobConfig(
+            type=JobType.TRANSCRIPTION,
+            transcription_config=TranscriptionConfig(
+                language="en",
+                enable_entities=True,
+                diarization="speaker"
+            )
+        )
+
+        # Submit job
+        job = await client.submit_job("audio.wav", config=config)
+        print(f"Job submitted: {job.id}")
+
+        # Wait for completion
+        result = await client.wait_for_completion(
+            job.id,
+            polling_interval=2.0,
+            timeout=300.0
+        )
+
+        # Access results
+        print(f"Transcript: {result.transcript_text}")
+        print(f"Confidence: {result.confidence}")
+
+asyncio.run(main())
+```
+
+### Advanced Configuration
+
+```python
+import asyncio
+from speechmatics.batch import (
+    AsyncClient,
+    JobConfig,
+    JobType,
+    OperatingPoint,
+    TranscriptionConfig,
+    TranslationConfig,
+    SummarizationConfig
+)
+
+async def main():
+    async with AsyncClient(api_key="your-api-key") as client:
+
+        # Advanced job configuration
+        config = JobConfig(
+            type=JobType.TRANSCRIPTION,
+            transcription_config=TranscriptionConfig(
+                language="en",
+                operating_point=OperatingPoint.ENHANCED,
+                enable_entities=True,
+                diarization="speaker",
+            ),
+            translation_config=TranslationConfig(target_languages=["es", "fr"]),
+            summarization_config=SummarizationConfig(
+                content_type="conversational", summary_length="brief"
+            ),
+        )
+
+        result = await client.transcribe("audio.wav", config=config)
+
+        # Access advanced features
+        if result.summary:
+            print(f"Summary: {result.summary}")
+        if result.translations:
+            print(f"Translations: {result.translations}")
+
+asyncio.run(main())
+```
+
+### Manual Job Management
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, JobStatus
+
+async def main():
+    async with AsyncClient() as client:
+
+        # Submit job
+        job = await client.submit_job("audio.wav")
+
+        # Check job status
+        job_details = await client.get_job_info(job.id)
+        print(f"Status: {job_details.status}")
+
+        # Wait for completion manually
+        while job_details.status == JobStatus.RUNNING:
+            await asyncio.sleep(5)
+            job_details = await client.get_job_info(job.id)
+
+        if job_details.status == JobStatus.DONE:
+            # Get transcript
+            transcript = await client.get_transcript(job.id)
+            print(transcript.transcript_text)
+        else:
+            print(f"Job failed with status: {job_details.status}")
+
+asyncio.run(main())
+```
+
+### Different Output Formats
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, FormatType
+
+async def main():
+    async with AsyncClient() as client:
+        job = await client.submit_job("audio.wav")
+
+        # Get JSON format (default)
+        json_result = await client.get_transcript(job.id, format_type=FormatType.JSON)
+        print(json_result.transcript_text)
+
+        # Get plain text
+        txt_result = await client.get_transcript(job.id, format_type=FormatType.TXT)
+        print(txt_result)
+
+        # Get SRT subtitles
+        srt_result = await client.get_transcript(job.id, format_type=FormatType.SRT)
+        print(srt_result)
+
+asyncio.run(main())
+```
+
+### Error Handling
+
+```python
+import asyncio
+from speechmatics.batch import (
+    AsyncClient,
+    BatchError,
+    AuthenticationError,
+    JobError,
+    TimeoutError
+)
+
+async def main():
+    try:
+        async with AsyncClient() as client:
+            result = await client.transcribe("audio.wav", timeout=120.0)
+            print(result.transcript_text)
+
+    except AuthenticationError:
+        print("Invalid API key")
+    except BatchError as e:
+        print(f"Job submission failed: {e}")
+    except JobError as e:
+        print(f"Job processing failed: {e}")
+    except TimeoutError as e:
+        print(f"Job timed out: {e}")
+    except FileNotFoundError:
+        print("Audio file not found")
+
+asyncio.run(main())
+```
+
+### Connection Configuration
+
+```python
+import asyncio
+from speechmatics.batch import AsyncClient, ConnectionConfig
+
+async def main():
+    # Custom connection settings
+    config = ConnectionConfig(
+        url="https://asr.api.speechmatics.com/v2",
+        api_key="your-api-key",
+        connect_timeout=30.0,
+        operation_timeout=600.0
+    )
+
+    async with AsyncClient(conn_config=config) as client:
+        result = await client.transcribe("audio.wav")
+        print(result.transcript_text)
+
+asyncio.run(main())
+```
+
+## Logging
+
+The client supports logging with job id tracing for debugging. To increase logging verbosity, set `DEBUG` level in your example code:
+
+```python
+import logging
+import sys
+
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.StreamHandler(sys.stdout)
+    ]
+)
+```
+
+## Environment Variables
+
+The client supports the following environment variables:
+
+- `SPEECHMATICS_API_KEY`: Your Speechmatics API key
+- `SPEECHMATICS_BATCH_URL`: Custom API endpoint URL (optional)

speechmatics_batch-0.1.0/pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=61.0.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "speechmatics-batch"
+dynamic = ["version"]
+description = "Speechmatics Batch API Client"
+readme = "README.md"
+authors = [{ name = "Speechmatics", email = "support@speechmatics.com" }]
+license = "MIT"
+requires-python = ">=3.9"
+dependencies = ["aiohttp", "aiofiles"]
+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", "speech-to-text", "batch", "transcription", "api"]
+
+[project.optional-dependencies]
+dev = [
+    "black",
+    "ruff",
+    "mypy",
+    "types-aiofiles",
+    "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.batch.__version__" }
+
+[tool.setuptools.packages.find]
+where = ["."]

speechmatics_batch-0.1.0/setup.cfg

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

speechmatics_batch-0.1.0/speechmatics/batch/__init__.py

@@ -0,0 +1,47 @@
+__version__ = "0.1.0"
+
+from ._async_client import AsyncClient
+from ._exceptions import AuthenticationError
+from ._exceptions import BatchError
+from ._exceptions import ConfigurationError
+from ._exceptions import ConnectionError
+from ._exceptions import JobError
+from ._exceptions import TimeoutError
+from ._exceptions import TransportError
+from ._models import ConnectionConfig
+from ._models import FormatType
+from ._models import JobConfig
+from ._models import JobDetails
+from ._models import JobInfo
+from ._models import JobStatus
+from ._models import JobType
+from ._models import NotificationConfig
+from ._models import OperatingPoint
+from ._models import SummarizationConfig
+from ._models import Transcript
+from ._models import TranscriptionConfig
+from ._models import TranslationConfig
+
+__all__ = [
+    "AsyncClient",
+    "ConfigurationError",
+    "AuthenticationError",
+    "ConnectionError",
+    "TransportError",
+    "BatchError",
+    "JobError",
+    "TimeoutError",
+    "JobConfig",
+    "JobDetails",
+    "JobInfo",
+    "NotificationConfig",
+    "OperatingPoint",
+    "SummarizationConfig",
+    "Transcript",
+    "TranscriptionConfig",
+    "TranslationConfig",
+    "ConnectionConfig",
+    "JobStatus",
+    "JobType",
+    "FormatType",
+]