username/derp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add always-on voice trigger mode with TTS echo

Browse Source 
When [voice] trigger is set in config, the bot continuously listens and
transcribes voice. Speech starting with the trigger word is stripped and
echoed back via TTS. Non-triggered speech is silently discarded unless
!listen is also active.
This commit is contained in:
user
2026-02-22 03:24:03 +01:00
parent 7b9359c152
commit e127f72660
2 changed files with 221 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
plugins/voice.py
View File

@@ -47,6 +47,7 @@ def _ps(bot):
cfg = getattr(bot, "config", {}).get("voice", {})
return bot._pstate.setdefault("voice", {
"listen": False,
"trigger": cfg.get("trigger", ""),
"buffers": {}, # {username: bytearray}
"last_ts": {}, # {username: float monotonic}
"flush_task": None,
@@ -83,7 +84,7 @@ def _pcm_to_wav(pcm: bytes) -> bytes:
def _on_voice(bot, user, sound_chunk):
"""Buffer incoming voice PCM per user. Runs on pymumble thread."""
ps = _ps(bot)
if not ps["listen"]:
if not ps["listen"] and not ps["trigger"]:
return
name = user["name"] if isinstance(user, dict) else None
if not name or name == bot.nick:
@@ -133,7 +134,7 @@ async def _flush_monitor(bot):
ps = _ps(bot)
loop = asyncio.get_running_loop()
try:
while ps["listen"]:
while ps["listen"] or ps["trigger"]:
await asyncio.sleep(_FLUSH_INTERVAL)
now = time.monotonic()
to_flush: list[tuple[str, bytes]] = []
@@ -158,8 +159,20 @@ async def _flush_monitor(bot):
continue
if not text or text.strip("., ") == "":
continue
log.info("voice: %s said: %s", name, text)
await bot.action("0", f"heard {name} say: {text}")
trigger = ps["trigger"]
if trigger and text.lower().startswith(trigger.lower()):
remainder = text[len(trigger):].strip()
if remainder:
log.info("voice: trigger from %s: %s", name, remainder)
bot._spawn(
_tts_play(bot, remainder), name="voice-tts",
)
continue
if ps["listen"]:
log.info("voice: %s said: %s", name, text)
await bot.action("0", f"heard {name} say: {text}")
except asyncio.CancelledError:
pass
except Exception:
@@ -256,7 +269,11 @@ async def cmd_listen(bot, message):
parts = message.text.split()
if len(parts) < 2:
state = "on" if ps["listen"] else "off"
await bot.reply(message, f"Listen: {state}")
trigger = ps["trigger"]
info = f"Listen: {state}"
if trigger:
info += f" | Trigger: {trigger}"
await bot.reply(message, info)
return
sub = parts[1].lower()
@@ -267,10 +284,11 @@ async def cmd_listen(bot, message):
await bot.reply(message, "Listening for voice")
elif sub == "off":
ps["listen"] = False
with ps["lock"]:
ps["buffers"].clear()
ps["last_ts"].clear()
_stop_flush_task(bot)
if not ps["trigger"]:
with ps["lock"]:
ps["buffers"].clear()
ps["last_ts"].clear()
_stop_flush_task(bot)
await bot.reply(message, "Stopped listening")
else:
await bot.reply(message, "Usage: !listen [on|off]")
@@ -300,10 +318,10 @@ async def cmd_say(bot, message):
async def on_connected(bot) -> None:
"""Re-register listener after reconnect if listen was on."""
"""Re-register listener after reconnect if listen or trigger is active."""
if not _is_mumble(bot):
return
ps = _ps(bot)
if ps["listen"]:
if ps["listen"] or ps["trigger"]:
_ensure_listener(bot)
_ensure_flush_task(bot)