0b1f1d4480
Big push driven by user feedback ("делай имбу") and web research on what
voice assistants need to be the ideal:
TTS backend abstraction (P0.1)
- new module crates/jarvis-core/src/tts/{mod,sapi,piper,silero}.rs
- TtsBackend trait with SapiBackend (current PowerShell), PiperBackend
(rhasspy/piper, neural quality), SileroBackend (python subprocess)
- JARVIS_TTS env var picks (sapi|piper|silero). Auto-detect Piper if
binary + voice present in tools/piper/. Falls back to SAPI on missing.
- SpeakOpts {lang, detached, raw} replaces ad-hoc args. text_utils
sanitiser applied unless raw=true.
- llm_fallback + lua/api/tts both routed through tts::backend().
- tools/piper/install.ps1 downloads piper.exe + ru_RU-irina-medium.onnx
from rhasspy releases + huggingface. Smoke-test included.
- tools/silero/silero_tts.py helper (PyTorch); rust spawns it as subprocess.
IMBA-1 Agentic LLM router
- crates/jarvis-app/src/llm_router.rs
- When fuzzy/intent matcher fails, LLM picks the closest command from the
full registry. Returns JSON {command_id, confidence, reason}.
- Threshold-gated re-dispatch via substitute phrase. JARVIS_LLM_ROUTER=1
enables; JARVIS_LLM_ROUTER_THRESHOLD overrides 0.55 default.
- Inserted in app.rs::execute_command between "no match" and existing
llm_fallback chat fallback.
IMBA-2 Long-term memory
- crates/jarvis-core/src/long_term_memory.rs — JSON store at
APP_CONFIG_DIR/long_term_memory.json. Atomic write-through.
- remember/recall/search/forget/all/build_context API.
- Lua bindings: jarvis.memory.* (5 functions).
- llm_fallback auto-injects relevant facts (substring search of prompt)
into system message before LLM call.
- Pack resources/commands/memory_pack/ with 4 commands: remember, recall,
forget, list.
IMBA-3 Profile switching (work/game/sleep/driving/default)
- crates/jarvis-core/src/profiles.rs — JSON profiles at APP_CONFIG_DIR/profiles/
Auto-seeds 5 defaults on first run with personality + allow/deny lists +
greetings + emoji icons.
- active_profile.txt persists choice across restart.
- Lua bindings: jarvis.profile.{active,set,list,allows,active_name}.
- llm_fallback prepends profile personality to system prompt.
- Pack resources/commands/profile_switch/ with 6 voice triggers.
IMBA-4 Multimodal screenshot + vision LLM
- crates/jarvis-core/src/lua/api/vision.rs — gated on HTTP sandbox.
- jarvis.vision.screenshot() captures via PowerShell System.Drawing.
- jarvis.vision.describe(prompt?) sends base64 PNG to Groq vision model
(default llama-3.2-11b-vision-preview, override via GROQ_VISION_MODEL).
- Pack resources/commands/vision/ with 2 commands: describe + read_error.
P0.2 Continuous conversation grace window
- config::CONVERSATION_GRACE_MS = 30_000.
- app.rs: after command result, if grace_ms > 0 keep listening WITHOUT
re-wake for the grace duration. Existing CMS_WAIT_DELAY back-dated so
the existing timeout fires at start + grace_ms.
Tests: 24/24 jarvis-core unit tests pass (including 5 text_utils).
Build: cargo build --release -p jarvis-app and -p jarvis-gui both succeed
on Windows MSVC (VS 2026 Enterprise vcvars64).
Notes for setup:
- Piper voice install: pwsh tools/piper/install.ps1 (downloads ~90 MB).
- GROQ_TOKEN needed for IMBA-1 (router) and IMBA-4 (vision).
- All features are opt-in via env vars or auto-detect; existing SAPI +
fuzzy match path remains the default.
85 lines
2.2 KiB
Python
85 lines
2.2 KiB
Python
"""Silero TTS helper for J.A.R.V.I.S.
|
|
|
|
Reads text from stdin, synthesises with snakers4/silero-models, writes the result
|
|
to a temp wav, and prints the path on stdout. The Rust side then plays + deletes it.
|
|
|
|
Install:
|
|
pip install torch soundfile numpy
|
|
|
|
Usage (called by jarvis-core/src/tts/silero.rs):
|
|
echo "привет" | python silero_tts.py --voice xenia
|
|
|
|
Voices for ru_v3:
|
|
xenia (female, default), baya (female), aidar (male), eugene (male), kseniya (female).
|
|
"""
|
|
|
|
import argparse
|
|
import os
|
|
import sys
|
|
import tempfile
|
|
|
|
try:
|
|
import torch # type: ignore
|
|
except ImportError:
|
|
print("silero_tts: torch not installed. Run `pip install torch`.", file=sys.stderr)
|
|
sys.exit(2)
|
|
|
|
import warnings
|
|
|
|
warnings.filterwarnings("ignore")
|
|
|
|
_MODEL = None
|
|
|
|
|
|
def load_model(device: str = "cpu"):
|
|
global _MODEL
|
|
if _MODEL is None:
|
|
torch.set_num_threads(4)
|
|
_MODEL, _ = torch.hub.load(
|
|
repo_or_dir="snakers4/silero-models",
|
|
model="silero_tts",
|
|
language="ru",
|
|
speaker="v3_1_ru",
|
|
trust_repo=True,
|
|
)
|
|
_MODEL.to(torch.device(device))
|
|
return _MODEL
|
|
|
|
|
|
def synth(text: str, voice: str, sample_rate: int = 48000) -> str:
|
|
"""Synth text → return path to temp wav."""
|
|
model = load_model()
|
|
audio = model.apply_tts(text=text, speaker=voice, sample_rate=sample_rate)
|
|
|
|
import numpy as np
|
|
import soundfile as sf # type: ignore
|
|
|
|
fd, path = tempfile.mkstemp(prefix="jarvis-silero-", suffix=".wav")
|
|
os.close(fd)
|
|
sf.write(path, audio.numpy().astype(np.float32), sample_rate)
|
|
return path
|
|
|
|
|
|
def main() -> int:
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--voice", default="xenia", help="speaker name (xenia, baya, aidar, eugene, kseniya)")
|
|
ap.add_argument("--sample-rate", type=int, default=48000)
|
|
args = ap.parse_args()
|
|
|
|
text = sys.stdin.read().strip()
|
|
if not text:
|
|
print("silero_tts: empty input", file=sys.stderr)
|
|
return 1
|
|
|
|
try:
|
|
path = synth(text, args.voice, args.sample_rate)
|
|
except Exception as exc:
|
|
print(f"silero_tts: synth failed: {exc}", file=sys.stderr)
|
|
return 3
|
|
|
|
print(path)
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|