Added Push to talk example

OS/01/core/i_endpoint.py

@@ -67,6 +67,7 @@ async def a(ws: WebSocket):
                 elif 'bytes' in message:
                     # If it's not a control message, it's part of the audio file
                     audio_file.extend(message['bytes'])
+                    
     except Exception as e:
         print(f"WebSocket connection closed with exception: {e}")
     finally:

OS/01/core/stt/__init__.py

@@ -6,7 +6,7 @@ import ffmpeg
 import subprocess
 
 def convert_mime_type_to_format(mime_type: str) -> str:
-    if mime_type == "audio/x-wav":
+    if mime_type == "audio/x-wav" or mime_type == "audio/wav":
         return "wav"
     if mime_type == "audio/webm":
         return "webm"
@@ -33,7 +33,7 @@ def export_audio_to_wav_ffmpeg(audio: bytearray, mime_type: str) -> str:
         yield output_path
     finally:
         os.remove(input_path)
-        #os.remove(output_path)
+        os.remove(output_path)
 
 def run_command(command):
     result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)

examples/push-to-record/.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

examples/push-to-record/README.md

@@ -0,0 +1,9 @@
+
+# Setup
+
+On Mac install portaudio `brew install portaudio`
+
+1. Run `pip install -r requirements.txt`
+2. Start the core/i_endpoint.py service
+3. Run `python main.py`
+4. Press spacebar down to talk and release to get the transcription back

examples/push-to-record/main.py

@@ -0,0 +1,129 @@
+import os
+import pyaudio
+import threading
+import asyncio
+import websockets
+import json
+from pynput import keyboard
+import wave
+import tempfile
+from datetime import datetime
+
+# Configuration
+chunk = 1024  # Record in chunks of 1024 samples
+sample_format = pyaudio.paInt16  # 16 bits per sample
+channels = 1  # Stereo
+fs = 48000 # Sample rate
+
+p = pyaudio.PyAudio()  # Create an interface to PortAudio
+frames = []  # Initialize array to store frames
+recording = False  # Flag to control recording state
+
+ws_chunk_size = 4096 # Websocket stream chunk size
+
+async def start_recording():
+    global recording
+
+    if recording:
+        return  # Avoid multiple starts
+    recording = True
+    frames.clear()  # Clear existing frames
+
+    stream = p.open(format=sample_format,
+                    channels=channels,
+                    rate=fs,
+                    frames_per_buffer=chunk,
+                    input=True)
+
+    print("Recording started...")
+    async with websockets.connect("ws://localhost:8000/a") as websocket:
+        # Send the start command with mime type
+        await websocket.send(json.dumps({"action": "command", "state": "start", "mimeType": "audio/wav"}))
+        while recording:
+            data = stream.read(chunk)
+            frames.append(data)
+
+        stream.stop_stream()
+        stream.close()
+
+        try:
+            file_path = save_recording(frames)
+            with open(file_path, 'rb') as audio_file:
+                byte_chunk = audio_file.read(ws_chunk_size)
+                while byte_chunk:
+                    await websocket.send(byte_chunk)
+                    byte_chunk = audio_file.read(ws_chunk_size)
+        finally:
+            os.remove(file_path)
+
+        # Send the end command
+        await websocket.send(json.dumps({"action": "command", "state": "end"}))
+
+        # Receive a json message and then close the connection
+        message = await websocket.recv()
+        print("Received message:", json.loads(message))
+
+
+    print("Recording stopped.")
+
+def save_recording(frames) -> str:
+    # Save the recorded data as a WAV file
+    temp_dir = tempfile.gettempdir()
+
+    # Create a temporary file with the appropriate extension
+    output_path = os.path.join(temp_dir, f"input_{datetime.now().strftime('%Y%m%d%H%M%S%f')}.wav")
+    with wave.open(output_path, 'wb') as wf:
+        wf.setnchannels(channels)
+        wf.setsampwidth(p.get_sample_size(sample_format))
+        wf.setframerate(fs)
+        wf.writeframes(b''.join(frames))
+
+    return output_path
+
+def start_recording_sync():
+    # Create a new event loop for the thread
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    # Run the asyncio event loop
+    loop.run_until_complete(start_recording())
+    loop.close()
+
+
+def stop_recording():
+    global recording
+    recording = False
+    print("Stopped recording")
+
+def toggle_recording(e):
+    global recording
+    if recording:
+        stop_recording()
+    else:
+        # Start recording in a new thread to avoid blocking
+        print("Starting recording")
+        threading.Thread(target=start_recording_sync).start()
+
+is_space_pressed = False  # Flag to track the state of the spacebar
+
+def on_press(key):
+    global is_space_pressed
+    if key == keyboard.Key.space and not is_space_pressed:
+        is_space_pressed = True
+        toggle_recording(key)
+
+def on_release(key):
+    global is_space_pressed
+    if key == keyboard.Key.space and is_space_pressed:
+        is_space_pressed = False
+        stop_recording()
+    if key == keyboard.Key.esc:
+        # Stop listener
+        return False
+
+# Collect events until released
+with keyboard.Listener(on_press=on_press, on_release=on_release) as listener:
+    with tempfile.TemporaryDirectory():
+        print("Press the spacebar to start/stop recording. Press ESC to exit.")
+        listener.join()
+
+p.terminate()

examples/push-to-record/requirements.txt

@@ -0,0 +1,4 @@
+pynput @ git+https://github.com/moses-palmer/pynput.git@12acf84dc0f721d91a957da65311497acb664933
+pyaudio
+websockets==12.0
+asyncio==3.4.3