compose/ai/patch_tts_tool.py

#!/usr/bin/env python3
"""Patch Hermes TTS tool: remove Edge TTS, replace with Piper as default/fallback.

Searches multiple paths for tts_tool.py so it works both at build time
(in the image venv) and at runtime (on the mounted data volume).
"""
import sys
import os

# Search order: argument > site-packages > /opt/hermes/tools > /opt/hermes checkout
SEARCH_PATHS = []

# Accept path as first argument
if len(sys.argv) > 1:
    SEARCH_PATHS.append(sys.argv[1])

# Add known locations
SEARCH_PATHS.extend([
    "/opt/hermes/.venv/lib/python3.13/site-packages/tools/tts_tool.py",
    "/opt/hermes/tools/tts_tool.py",
])

tts_path = None
code = None

for p in SEARCH_PATHS:
    if os.path.exists(p):
        tts_path = p
        with open(tts_path) as f:
            code = f.read()
        print(f"Found tts_tool.py at: {tts_path}")
        break

if code is None:
    # Try one more time: find it in the venv site-packages
    import subprocess
    try:
        result = subprocess.run(
            [sys.executable, "-c", "import tools.tts_tool; print(tools.tts_tool.__file__)"],
            capture_output=True, text=True, timeout=5
        )
        if result.returncode == 0:
            p = result.stdout.strip()
            if os.path.exists(p):
                tts_path = p
                with open(tts_path) as f:
                    code = f.read()
                print(f"Found tts_tool.py via import at: {tts_path}")
    except Exception:
        pass

if code is None:
    print("WARNING: tts_tool.py not found. Patching deferred to runtime.")
    print(f"Searched: {SEARCH_PATHS}")
    sys.exit(0)

# Replace the Edge fallback with Piper fallback
old_edge = '''        else:
            # Default: Edge TTS (free), with NeuTTS as local fallback
            edge_available = True
            try:
                _import_edge_tts()
            except ImportError:
                edge_available = False

            if edge_available:
                logger.info("Generating speech with Edge TTS...")
                try:
                    import concurrent.futures
                    with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
                        pool.submit(
                            lambda: asyncio.run(_generate_edge_tts(text, file_str, tts_config))
                        ).result(timeout=60)
                except RuntimeError:
                    asyncio.run(_generate_edge_tts(text, file_str, tts_config))
            elif _check_neutts_available():
                logger.info("Edge TTS not available, falling back to NeuTTS (local)...")
                provider = "neutts"
                _generate_neutts(text, file_str, tts_config)
            else:
                return json.dumps({
                    "success": False,
                    "error": "No TTS provider available. Install edge-tts (pip install edge-tts) "
                             "or set up NeuTTS for local synthesis."
                }, ensure_ascii=False)'''

new_piper = '''        else:
            # Default: Piper TTS (local, CPU, no cloud, no Microsoft)
            piper_available = False
            try:
                piper_binary = "/opt/hermes/.venv/bin/piper"
                piper_config = tts_config.get("piper", {})
                voice = piper_config.get("voice", "en_US-lessac-medium")
                model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
                model_path = os.path.join(model_dir, f"{voice}.onnx")
                if os.path.exists(model_path):
                    piper_available = True
            except Exception:
                pass

            if piper_available:
                logger.info("Generating speech with Piper TTS (local, CPU)...")
                import subprocess
                piper_binary = "/opt/hermes/.venv/bin/piper"
                piper_config = tts_config.get("piper", {})
                voice = piper_config.get("voice", "en_US-lessac-medium")
                model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
                model_path = os.path.join(model_dir, f"{voice}.onnx")
                cmd = [piper_binary, "--model", model_path, "--output-raw"]
                proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
                raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
                if proc.returncode != 0:
                    raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
                ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
                subprocess.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
                logger.info("Piper TTS audio saved: %s", file_str)
            else:
                return json.dumps({
                    "success": False,
                    "error": "No TTS provider available. Install Piper TTS (pip install piper-tts) "
                             "and download a voice model."
                }, ensure_ascii=False)'''

if old_edge in code:
    code = code.replace(old_edge, new_piper)
    print("Edge fallback replaced with Piper")
elif 'Default: Piper TTS' in code:
    print("Piper fallback already present")
else:
    print("WARNING: Could not find Edge fallback in tts_tool.py")
    print("The tts_tool.py may be a version not matching this patch.")
    sys.exit(0)

with open(tts_path, 'w') as f:
    f.write(code)
print(f"tts_tool.py patched successfully at: {tts_path}")