From 263e9aa20915c826f0a807a367c5eb41ddbae1c7 Mon Sep 17 00:00:00 2001
From: ov <ov@h5>
Date: Thu, 26 Jun 2025 15:17:11 +0000
Subject: [PATCH] init

---
 .gitignore       |  4 +++
 readme.txt       | 15 ++++++++
 requirements.txt |  7 ++++
 stt_piper.py     | 90 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 116 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 readme.txt
 create mode 100644 requirements.txt
 create mode 100644 stt_piper.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..64b05be
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+data
+model
+piper
+
diff --git a/readme.txt b/readme.txt
new file mode 100644
index 0000000..35b90ca
--- /dev/null
+++ b/readme.txt
@@ -0,0 +1,15 @@
+uv venv .venv
+source .venv/bin/activate.fish
+uv pip install flask
+uv pip freeze > requirements.txt
+
+get piper binary https://github.com/rhasspy/piper
+tar -xvf piper_linux_aarch64.tar.gz
+
+wget https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/amy/medium/en_US-amy-medium.onnx
+https://huggingface.co/rhasspy/piper-voices/tree/v1.0.0/en/en_US/amy/medium
+
+echo 'Welcome to the world of speech synthesis!' | \
+  ./piper/piper --model en_US-lessac-medium.onnx --output_file welcome.wav
+
+or run any script
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..f4b2284
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+blinker==1.9.0
+click==8.2.1
+flask==3.1.1
+itsdangerous==2.2.0
+jinja2==3.1.6
+markupsafe==3.0.2
+werkzeug==3.1.3
diff --git a/stt_piper.py b/stt_piper.py
new file mode 100644
index 0000000..d443d9b
--- /dev/null
+++ b/stt_piper.py
@@ -0,0 +1,90 @@
+from flask import Flask, request, Response
+import subprocess
+import os
+import time
+import random
+from datetime import datetime
+
+app = Flask(__name__)
+
+# Ensure storage directories exist
+os.makedirs('texts', exist_ok=True)
+os.makedirs('audio', exist_ok=True)
+
+def generate_filename():
+    """Generate timestamp + random number filename"""
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    random_num = random.randint(1000, 9999)
+    return f"{timestamp}_{random_num}"
+
+@app.route('/tts', methods=['POST'])
+def tts():
+    # Validate input
+    if not request.is_json:
+        return {"error": "Request must be JSON"}, 400
+
+    text = request.json.get('text', '').strip()
+    if not text:
+        return {"error": "No text provided"}, 400
+    if len(text) > 1000:
+        return {"error": "Text too long (max 1000 characters)"}, 400
+
+    # Generate unique filename
+    base_filename = generate_filename()
+    text_filename = f"data/texts/{base_filename}.txt"
+    wav_filename = f"data/audio/{base_filename}.wav"
+
+    try:
+        # Save the input text
+        with open(text_filename, 'w') as f:
+            f.write(text)
+
+        # Generate WAV audio with Piper - directly to file first
+        piper_cmd = [
+            'echo', f'"{text}"', '|',
+            './piper/piper',
+            '--model', './model/en_US-amy-medium.onnx',
+            '--output_file', wav_filename
+        ]
+
+        # Run the command
+        process = subprocess.run(
+            ' '.join(piper_cmd),
+            shell=True,
+            check=True,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE
+        )
+
+        # Verify the output file was created
+        if not os.path.exists(wav_filename):
+            raise Exception("Piper failed to create audio file")
+
+        # Get file size for logging
+        file_size = os.path.getsize(wav_filename)
+
+        # Read the generated audio
+        with open(wav_filename, 'rb') as f:
+            audio_data = f.read()
+
+        # Log the successful generation
+        print(f"Generated TTS: {len(text)} chars -> {file_size} bytes audio")
+
+        # Return WAV audio directly
+        return Response(
+            audio_data,
+            mimetype='audio/wav',
+            headers={'Content-Disposition': f'attachment; filename={base_filename}.wav'}
+        )
+
+    except subprocess.CalledProcessError as e:
+        error_msg = f"Piper TTS failed: {e.stderr.decode().strip()}"
+        print(error_msg)
+        return {"error": "TTS generation failed", "details": error_msg}, 500
+    except Exception as e:
+        error_msg = f"Unexpected error: {str(e)}"
+        print(error_msg)
+        return {"error": "TTS processing failed", "details": error_msg}, 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=4005, debug=True)