tts changes

.gitignore

@@ -171,3 +171,6 @@ cython_debug/
 
 # PyPI configuration file
 .pypirc
+
+# Examples
+**/output.wav

Makefile

@@ -1,12 +1,12 @@
 # Makefile for Speechmatics Python SDKs
 
 .PHONY: help
-.PHONY: test-all test-rt test-batch test-flow
-.PHONY: format-all format-rt format-batch format-flow
-.PHONY: lint-all lint-rt lint-batch lint-flow
-.PHONY: type-check-all type-check-rt type-check-batch type-check-flow
-.PHONY: build-all build-rt build-batch build-flow
-.PHONY: clean-all clean-rt clean-batch clean-flow clean-flow
+.PHONY: test-all test-rt test-batch test-flow test-tts
+.PHONY: format-all format-rt format-batch format-flow format-tts
+.PHONY: lint-all lint-rt lint-batch lint-flow lint-tts
+.PHONY: type-check-all type-check-rt type-check-batch type-check-flow type-check-tts
+.PHONY: build-all build-rt build-batch build-flow build-tts
+.PHONY: clean-all clean-rt clean-batch clean-flow clean-tts
 
 help:
 	@echo "Available commands:"
@@ -40,16 +40,18 @@ help:
 	@echo "  build-rt          Build RT SDK"
 	@echo "  build-batch       Build Batch SDK"
 	@echo "  build-flow        Build Flow SDK"
+	@echo "  build-tts         Build TTS SDK"
 	@echo ""
 	@echo "Cleaning:"
 	@echo "  clean-all         Clean all SDKs"
 	@echo "  clean-rt          Clean RT SDK build artifacts"
 	@echo "  clean-batch       Clean Batch SDK build artifacts"
 	@echo "  clean-flow        Clean Flow SDK build artifacts"
+	@echo "  clean-tts         Clean TTS SDK build artifacts"
 	@echo ""
 
 # Testing targets
-test-all: test-rt test-batch test-flow
+test-all: test-rt test-batch test-flow test-tts
 
 test-rt:
 	pytest tests/rt/ -v
@@ -61,7 +63,7 @@ test-flow:
 	pytest tests/flow/ -v
 
 # Formatting targets
-format-all: format-rt format-batch format-flow
+format-all: format-rt format-batch format-flow format-tts
 
 format-rt:
 	cd sdk/rt/speechmatics && black .
@@ -75,8 +77,12 @@ format-flow:
 	cd sdk/flow/speechmatics && black .
 	cd sdk/flow/speechmatics && ruff check --fix .
 
+format-tts:
+	cd sdk/tts/speechmatics && black .
+	cd sdk/tts/speechmatics && ruff check --fix .
+
 # Linting targets
-lint-all: lint-rt lint-batch lint-flow
+lint-all: lint-rt lint-batch lint-flow lint-tts
 
 lint-rt:
 	cd sdk/rt/speechmatics && ruff check .
@@ -87,8 +93,11 @@ lint-batch:
 lint-flow:
 	cd sdk/flow/speechmatics && ruff check .
 
+lint-tts:
+	cd sdk/tts/speechmatics && ruff check .
+
 # Type checking targets
-type-check-all: type-check-rt type-check-batch type-check-flow
+type-check-all: type-check-rt type-check-batch type-check-flow type-check-tts
 
 type-check-rt:
 	cd sdk/rt/speechmatics && mypy .
@@ -99,18 +108,22 @@ type-check-batch:
 type-check-flow:
 	cd sdk/flow/speechmatics && mypy .
 
+type-check-tts:
+	cd sdk/tts/speechmatics && mypy .
+
 # Installation targets
 install-dev:
 	python -m pip install --upgrade pip
 	python -m pip install -e sdk/rt[dev]
 	python -m pip install -e sdk/batch[dev]
 	python -m pip install -e sdk/flow[dev]
+	python -m pip install -e sdk/tts[dev]
 
 install-build:
 	python -m pip install --upgrade build
 
 # Building targets
-build-all: build-rt build-batch build-flow
+build-all: build-rt build-batch build-flow build-tts
 
 build-rt: install-build
 	cd sdk/rt && python -m build
@@ -121,8 +134,11 @@ build-batch: install-build
 build-flow: install-build
 	cd sdk/flow && python -m build
 
+build-tts: install-build
+	cd sdk/tts && python -m build
+
 # Cleaning targets
-clean-all: clean-rt clean-batch clean-flow
+clean-all: clean-rt clean-batch clean-flow clean-tts
 
 clean-rt:
 	rm -rf sdk/rt/dist sdk/rt/build sdk/rt/*.egg-info
@@ -135,3 +151,7 @@ clean-batch:
 clean-flow:
 	rm -rf sdk/flow/dist sdk/flow/build sdk/flow/*.egg-info
 	find sdk/flow -name __pycache__ -exec rm -rf {} + 2>/dev/null || true
+
+clean-tts:
+	rm -rf sdk/tts/dist sdk/tts/build sdk/tts/*.egg-info
+	find sdk/tts -name __pycache__ -exec rm -rf {} + 2>/dev/null || true

examples/tts/tts_async_example.py

@@ -0,0 +1,55 @@
+import os
+import asyncio
+
+import wave 
+from pathlib import Path
+
+from speechmatics.tts import AsyncClient, Voice, OutputFormat
+
+
+# Set configuration 
+TEXT = "Welcome to the future of audio generation from text!"
+VOICE = Voice.SARAH
+OUTPUT_FORMAT = OutputFormat.RAW_PCM_16000
+OUTPUT_FILE = "output.wav"
+
+# Set Format Parameters for WAV output file
+SAMPLE_RATE = 16000 #Hz
+SAMPLE_WIDTH = 2 # 16-bit audio
+CHANNELS = 1 # Mono audio
+
+# Save audio to WAV file
+async def save_audio_to_wav(audio_data: bytes,
+                            output_file_name: str) -> None:
+    with wave.open(output_file_name, "wb") as wav_file:
+        wav_file.setnchannels(CHANNELS)
+        wav_file.setsampwidth(SAMPLE_WIDTH)
+        wav_file.setframerate(SAMPLE_RATE)
+        wav_file.writeframes(audio_data)
+
+# Generate speech from text and save to WAV file
+async def main():
+    print(f"Generating speech from text: {TEXT}")
+
+    try:
+        async with AsyncClient() as client:
+            async with await client.generate(
+                text=TEXT,
+                voice=VOICE,
+                output_format=OUTPUT_FORMAT
+            ) as response:           
+                # Process the response in chunks and save to WAV
+                audio_chunks = []
+                async for chunk in response.content.iter_chunked(1024):
+                    audio_chunks.append(chunk)
+
+                # Combine chunks and save to WAV
+                audio_data = b''.join(audio_chunks)
+                await save_audio_to_wav(audio_data, OUTPUT_FILE)
+                print(f"Speech saved to {Path(OUTPUT_FILE).resolve()}")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+# Run the async main function
+if __name__ == "__main__":
+    asyncio.run(main())

sdk/tts/README.md

@@ -0,0 +1,128 @@
+# Speechmatics TTS API Client
+
+[![PyPI](https://img.shields.io/pypi/v/speechmatics-tts)](https://pypi.org/project/speechmatics-tts/)
+![PythonSupport](https://img.shields.io/badge/Python-3.9%2B-green)
+
+Async Python client for Speechmatics TTS API.
+
+## Features
+
+- Async API client with comprehensive error handling
+- Type hints throughout for better IDE support
+- Environment variable support for credentials
+
+## Installation
+
+```bash
+pip install speechmatics-tts
+```
+
+## Usage
+
+### Quick Start
+
+```python
+import asyncio
+
+import wave 
+from pathlib import Path
+
+from speechmatics.tts import AsyncClient, Voice, OutputFormat
+
+async def save_audio(audio_data: bytes, filename: str) -> None:
+    with wave.open(filename, "wb") as wav:
+        wav.setnchannels(1)           # Mono
+        wav.setsampwidth(2)           # 16-bit
+        wav.setframerate(16000)       # 16kHz
+        wav.writeframes(audio_data)
+
+# Generate speech data from text and save to WAV file
+async def main():
+    async with AsyncClient() as client:
+        async with await client.generate(
+            text="Welcome to the future of audio generation from text!",
+            voice=Voice.SARAH,
+            output_format=OutputFormat.RAW_PCM_16000
+        ) as response:
+            audio = b''.join([chunk async for chunk in response.content.iter_chunked(1024)])
+            await save_audio(audio, "output.wav")
+
+
+# Run the async main function
+if __name__ == "__main__":
+    asyncio.run(main())
+
+```
+
+### Error Handling
+
+```python
+import asyncio
+from speechmatics.tts import (
+    AsyncClient,
+    AuthenticationError,
+    TimeoutError
+)
+
+async def main():
+    try:
+        async with AsyncClient() as client:
+            response = await client.generate(text="Hello, this is the Speechmatics TTS API. We are excited to have you here!")
+
+    except AuthenticationError:
+        print("Invalid API key")
+    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.tts import AsyncClient, ConnectionConfig
+
+async def main():
+    # Custom connection settings
+    config = ConnectionConfig(
+        url="https://preview.tts.speechmatics.com",
+        api_key="your-api-key",
+        connect_timeout=30.0,
+        operation_timeout=600.0
+    )
+
+    async with AsyncClient(conn_config=config) as client:
+        response = await client.generate(text="Hello World")
+
+
+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_TTS_URL`: Custom API endpoint URL (optional)

sdk/tts/pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=61.0.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "speechmatics-tts"
+dynamic = ["version"]
+description = "Speechmatics TTS API Client"
+readme = "README.md"
+authors = [{ name = "Speechmatics", email = "[email protected]" }]
+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", "tts", "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.tts.__version__" }
+
+[tool.setuptools.packages.find]
+where = ["."]

sdk/tts/speechmatics/tts/__init__.py

@@ -0,0 +1,29 @@
+__version__ = "0.0.0"
+
+from ._async_client import AsyncClient
+from ._auth import AuthBase
+from ._auth import JWTAuth
+from ._auth import StaticKeyAuth
+from ._exceptions import AuthenticationError
+from ._exceptions import ConfigurationError
+from ._exceptions import ConnectionError
+from ._exceptions import TimeoutError
+from ._exceptions import TransportError
+from ._models import ConnectionConfig
+from ._models import OutputFormat
+from ._models import Voice
+
+__all__ = [
+    "AsyncClient",
+    "AuthBase",
+    "JWTAuth",
+    "StaticKeyAuth",
+    "ConfigurationError",
+    "AuthenticationError",
+    "ConnectionError",
+    "TransportError",
+    "TimeoutError",
+    "ConnectionConfig",
+    "Voice",
+    "OutputFormat",
+]