Merge pull request #56 from speechmatics/fix/add-tts-workflow

Add TTS workflow

Author: lgavincrl

.github/workflows/release-tts.yml

@@ -0,0 +1,90 @@
+name: Release TTS SDK
+
+on:
+  push:
+    tags:
+      - "tts/v*"
+
+permissions:
+  contents: read
+  id-token: write
+
+jobs:
+  extract-version:
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.extract.outputs.version }}
+    steps:
+      - name: Extract version from tag
+        id: extract
+        run: |
+          # Extract version from tag (tts/v1.0.0 -> 1.0.0)
+          VERSION=${GITHUB_REF#refs/tags/tts/v}
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "Extracted version: $VERSION"
+
+  test-tts:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Test TTS SDK
+        run: |
+          make install-dev
+          make lint-tts
+          make test-tts
+
+  release-build:
+    runs-on: ubuntu-latest
+    needs: [extract-version, test-tts]
+    outputs:
+      version: ${{ needs.extract-version.outputs.version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Update package version in sdk/tts/speechmatics/tts/__init__.py
+        run: |
+          VERSION="${{ needs.extract-version.outputs.version }}"
+          sed -i "s/0\.0\.0/$VERSION/g" ./sdk/tts/speechmatics/tts/__init__.py
+          echo "Updated version to: $VERSION"
+          cat ./sdk/tts/speechmatics/tts/__init__.py | grep __version__
+
+      - name: Build TTS SDK
+        run: |
+          make install-dev
+          make build-tts
+
+      - name: Upload dist
+        uses: actions/upload-artifact@v4
+        with:
+          name: tts-release-dist
+          path: sdk/tts/dist/
+
+  pypi-publish:
+    runs-on: ubuntu-latest
+    needs: [release-build]
+    environment:
+      name: pypi-tts
+      url: https://pypi.org/project/speechmatics-tts/${{ needs.release-build.outputs.version }}
+
+    steps:
+      - name: Retrieve release dist
+        uses: actions/download-artifact@v4
+        with:
+          name: tts-release-dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: dist/
+          password: ${{ secrets.PYPI_ORG_TOKEN }}

sdk/tts/README.md

@@ -24,28 +24,19 @@ pip install speechmatics-tts
 ```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!",
+            text="Welcome to the future of voice AI!",
             voice=Voice.SARAH,
-            output_format=OutputFormat.RAW_PCM_16000
+            output_format=OutputFormat.WAV_16000
         ) as response:
             audio = b''.join([chunk async for chunk in response.content.iter_chunked(1024)])
-            await save_audio(audio, "output.wav")
+            with open("output.wav", "wb") as f:
+                f.write(audio)
 
 
 # Run the async main function

sdk/tts/speechmatics/tts/_helpers.py

@@ -1,5 +1,5 @@
 """
-Utility functions for the Speechmatics Batch SDK.
+Utility functions for the Speechmatics TTS SDK.
 """
 
 from __future__ import annotations
@@ -47,7 +47,7 @@ async def prepare_audio_file(
 
 def get_version() -> str:
     try:
-        return importlib.metadata.version("speechmatics-batch")
+        return importlib.metadata.version("speechmatics-tts")
     except importlib.metadata.PackageNotFoundError:
         try:
             from . import __version__