gortium/compose
1
1
Fork 0
Code Issues Pull Requests 18 Actions Packages Projects Releases Wiki Activity

fix: update TTS patch for latest hermes-agent tts_tool.py

Browse Source 
- Patch now matches the current tts_tool.py (newer version ships in
  nousresearch/hermes-agent:latest with different Edge fallback text)
- Adds dedicated elif provider == 'piper' block before else:
- Replaces else: fallback to use Piper instead of Edge
- Patches ALL copies (venv site-packages + /opt/hermes/tools/)
- Removes Edge TTS entirely as default/provider
This commit is contained in:
Thierry Pouplier
2026-05-09 19:03:10 +00:00
parent 3f80744ebd
commit 748b5037b9
1 changed files with 125 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

169
ai/patch_tts_tool.py
View File

@@ -1,38 +1,33 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
"""Patch Hermes TTS tool: remove Edge TTS, replace with Piper as default/fallback. """Patch Hermes TTS tool: add Piper TTS provider, remove Edge TTS as default.
Patches ALL copies of tts_tool.py found (venv site-packages + /opt/hermes/tools/).
Searches multiple paths for tts_tool.py so it works both at build time 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). (in the image venv) and at runtime (on the mounted data volume).
Idempotent: if already patched, does nothing.
""" """
import sys import sys
import os import os
# Search order: argument > site-packages > /opt/hermes/tools > /opt/hermes checkout # ---------------------------------------------------------------------------
SEARCH_PATHS = [] # Search for all copies of tts_tool.py
# ---------------------------------------------------------------------------
# Accept path as first argument CANDIDATE_PATHS = [
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/.venv/lib/python3.13/site-packages/tools/tts_tool.py",
"/opt/hermes/tools/tts_tool.py", "/opt/hermes/tools/tts_tool.py",
]) ]
tts_path = None found_paths = []
code = None
for p in SEARCH_PATHS: for p in CANDIDATE_PATHS:
if os.path.exists(p): if os.path.exists(p):
tts_path = p found_paths.append(p)
with open(tts_path) as f: print(f"Found tts_tool.py at: {p}")
code = f.read()
print(f"Found tts_tool.py at: {tts_path}")
break
if code is None: # Also try to find via Python import
# Try one more time: find it in the venv site-packages
import subprocess import subprocess
try: try:
result = subprocess.run( result = subprocess.run(
@@ -41,21 +36,21 @@ if code is None:
) )
if result.returncode == 0: if result.returncode == 0:
p = result.stdout.strip() p = result.stdout.strip()
if os.path.exists(p): if os.path.exists(p) and p not in found_paths:
tts_path = p found_paths.append(p)
with open(tts_path) as f: print(f"Found tts_tool.py via import at: {p}")
code = f.read()
print(f"Found tts_tool.py via import at: {tts_path}")
except Exception: except Exception:
pass pass
if code is None: if not found_paths:
print("WARNING: tts_tool.py not found. Patching deferred to runtime.") print("WARNING: tts_tool.py not found anywhere. Patching deferred to runtime.")
print(f"Searched: {SEARCH_PATHS}") print(f"Searched: {CANDIDATE_PATHS}")
sys.exit(0) sys.exit(0)
# Replace the Edge fallback with Piper fallback # ---------------------------------------------------------------------------
old_edge = ''' else: # Old else block: the Edge TTS default fallback to replace
# ---------------------------------------------------------------------------
old_else = ''' else:
# Default: Edge TTS (free), with NeuTTS as local fallback # Default: Edge TTS (free), with NeuTTS as local fallback
edge_available = True edge_available = True
try: try:
@@ -84,53 +79,103 @@ old_edge = ''' else:
"or set up NeuTTS for local synthesis." "or set up NeuTTS for local synthesis."
}, ensure_ascii=False)''' }, ensure_ascii=False)'''
new_piper = ''' else: # ---------------------------------------------------------------------------
# Default: Piper TTS (local, CPU, no cloud, no Microsoft) # New block: elif provider == "piper" + else: fallback with Piper only
piper_available = False # ---------------------------------------------------------------------------
try: new_block = ''' elif provider == "piper":
# Piper TTS (local, CPU, no cloud, no Microsoft)
piper_binary = "/opt/hermes/.venv/bin/piper" piper_binary = "/opt/hermes/.venv/bin/piper"
piper_config = tts_config.get("piper", {}) piper_config = tts_config.get("piper", {})
voice = piper_config.get("voice", "en_US-lessac-medium") voice = piper_config.get("voice", "en_US-lessac-medium")
model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices") model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
model_path = os.path.join(model_dir, f"{voice}.onnx") model_path = os.path.join(model_dir, f"{voice}.onnx")
if os.path.exists(model_path): if not os.path.exists(model_path):
piper_available = True return json.dumps({
except Exception: "success": False,
pass "error": "Piper TTS voice model not found. "
"Install Piper TTS and download a voice model."
if piper_available: }, ensure_ascii=False)
logger.info("Generating speech with Piper TTS (local, CPU)...") logger.info("Generating speech with Piper TTS (local, CPU)...")
import subprocess import subprocess as _sp
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"] cmd = [piper_binary, "--model", model_path, "--output-raw"]
proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) try:
proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.PIPE)
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60) raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
if proc.returncode != 0: if proc.returncode != 0:
raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}") raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str] 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) _sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
logger.info("Piper TTS audio saved: %s", file_str) except Exception as e:
return json.dumps({
"success": False,
"error": f"Piper TTS failed: {e}"
}, ensure_ascii=False)
else:
# Default: Piper TTS (local, CPU, no cloud, no Microsoft)
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) and os.path.exists(piper_binary):
logger.info("Generating speech with Piper TTS (local, CPU)...")
import subprocess as _sp
cmd = [piper_binary, "--model", model_path, "--output-raw"]
try:
proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.PIPE)
raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
if proc.returncode != 0:
raise RuntimeError(stderr.decode()[:200])
ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
_sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
except Exception:
pass
else: else:
return json.dumps({ return json.dumps({
"success": False, "success": False,
"error": "No TTS provider available. Install Piper TTS (pip install piper-tts) " "error": "Piper TTS not available. Install piper-tts and download a voice model."
"and download a voice model."
}, ensure_ascii=False)''' }, ensure_ascii=False)'''
if old_edge in code: # ---------------------------------------------------------------------------
code = code.replace(old_edge, new_piper) # Apply the patch to all copies found
print("Edge fallback replaced with Piper") # ---------------------------------------------------------------------------
elif 'Default: Piper TTS' in code: patched_any = False
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)
for tts_path in found_paths:
with open(tts_path) as f:
code = f.read()
if 'provider == "piper"' in code:
print(f"ALREADY PATCHED: {tts_path}")
continue
if old_else in code:
code = code.replace(old_else, new_block, 1)
with open(tts_path, 'w') as f: with open(tts_path, 'w') as f:
f.write(code) f.write(code)
print(f"tts_tool.py patched successfully at: {tts_path}") print(f"PATCHED: {tts_path}")
patched_any = True
else:
print(f"SKIP {tts_path}: Edge fallback pattern not found")
import re
for m in re.finditer(r' else:\n # Default:', code):
start = max(0, m.start() - 100)
end = min(len(code), m.end() + 300)
print(f" Found 'else:/# Default:' at position {m.start()}:")
print(f" {code[start:end]}")
print(" ---")
# Don't exit with error — if one copy isn't patchable, try the others
if not patched_any:
all_patched = all(
'provider == "piper"' in open(p).read()
for p in found_paths
)
if all_patched:
print("All copies already patched.")
sys.exit(0)
print("WARNING: Could not patch any copy of tts_tool.py")
sys.exit(1)
print("tts_tool.py patched successfully across all copies.")