129e4ea1fc
New router intelligence modules (26 files): alert_ingest/store, audit_store, architecture_pressure, backlog_generator/store, cost_analyzer, data_governance, dependency_scanner, drift_analyzer, incident_* (5 files), llm_enrichment, platform_priority_digest, provider_budget, release_check_runner, risk_* (6 files), signature_state_store, sofiia_auto_router, tool_governance New services: - sofiia-console: Dockerfile, adapters/, monitor/nodes/ops/voice modules, launchd, react static - memory-service: integration_endpoints, integrations, voice_endpoints, static UI - aurora-service: full app suite (analysis, job_store, orchestrator, reporting, schemas, subagents) - sofiia-supervisor: new supervisor service - aistalk-bridge-lite: Telegram bridge lite - calendar-service: CalDAV calendar service with reminders - mlx-stt-service / mlx-tts-service: Apple Silicon speech services - binance-bot-monitor: market monitor service - node-worker: STT/TTS memory providers New tools (9): agent_email, browser_tool, contract_tool, observability_tool, oncall_tool, pr_reviewer_tool, repo_tool, safe_code_executor, secure_vault New crews: agromatrix_crew (10 modules: depth_classifier, doc_facts, doc_focus, farm_state, light_reply, llm_factory, memory_manager, proactivity, reflection_engine, session_context, style_adapter, telemetry) Tests: 85+ test files for all new modules Made-with: Cursor
115 lines
4.0 KiB
Python
115 lines
4.0 KiB
Python
"""STT provider: delegates to existing Memory Service /voice/stt.
|
|
|
|
Memory Service accepts: multipart/form-data audio file upload.
|
|
Returns: {text, model, language}
|
|
|
|
Fabric contract output: {text, segments[], language, meta}
|
|
"""
|
|
import base64
|
|
import logging
|
|
import os
|
|
from typing import Any, Dict
|
|
|
|
import httpx
|
|
|
|
logger = logging.getLogger("provider.stt_memory_service")
|
|
|
|
MEMORY_SERVICE_URL = os.getenv("MEMORY_SERVICE_URL", "http://memory-service:8000")
|
|
MAX_AUDIO_BYTES = int(os.getenv("STT_MAX_AUDIO_BYTES", str(25 * 1024 * 1024)))
|
|
|
|
|
|
async def _resolve_audio_bytes(payload: Dict[str, Any]) -> tuple[bytes, str, str, str]:
|
|
"""Return (raw_bytes, filename, source, content_type) from audio_b64 or audio_url."""
|
|
audio_b64 = payload.get("audio_b64", "")
|
|
audio_url = payload.get("audio_url", "")
|
|
filename = payload.get("filename", "audio.wav")
|
|
|
|
if audio_b64:
|
|
raw = base64.b64decode(audio_b64)
|
|
if len(raw) > MAX_AUDIO_BYTES:
|
|
raise ValueError(f"Audio exceeds {MAX_AUDIO_BYTES} bytes")
|
|
return raw, filename, "b64", "audio/wav"
|
|
|
|
if audio_url:
|
|
if audio_url.startswith(("file://", "/")):
|
|
path = audio_url.replace("file://", "")
|
|
with open(path, "rb") as f:
|
|
raw = f.read()
|
|
if len(raw) > MAX_AUDIO_BYTES:
|
|
raise ValueError(f"Audio exceeds {MAX_AUDIO_BYTES} bytes")
|
|
ext = path.rsplit(".", 1)[-1] if "." in path else "wav"
|
|
return raw, f"audio.{ext}", "file", f"audio/{ext}"
|
|
|
|
# HTTP URL — check Content-Length header first if available
|
|
async with httpx.AsyncClient(timeout=30) as c:
|
|
try:
|
|
head_resp = await c.head(audio_url)
|
|
content_length = int(head_resp.headers.get("content-length", 0))
|
|
if content_length > MAX_AUDIO_BYTES:
|
|
raise ValueError(f"Audio URL Content-Length {content_length} exceeds {MAX_AUDIO_BYTES} bytes")
|
|
content_type = head_resp.headers.get("content-type", "audio/wav")
|
|
except httpx.HTTPError:
|
|
content_type = "audio/wav"
|
|
|
|
resp = await c.get(audio_url)
|
|
resp.raise_for_status()
|
|
raw = resp.content
|
|
content_type = resp.headers.get("content-type", content_type)
|
|
|
|
if len(raw) > MAX_AUDIO_BYTES:
|
|
raise ValueError(f"Audio exceeds {MAX_AUDIO_BYTES} bytes")
|
|
ext = content_type.split("/")[-1].split(";")[0] or "wav"
|
|
return raw, f"audio.{ext}", "url", content_type
|
|
|
|
raise ValueError("audio_b64 or audio_url is required")
|
|
|
|
|
|
async def transcribe(payload: Dict[str, Any]) -> Dict[str, Any]:
|
|
"""Fabric STT entry point — delegates to Memory Service.
|
|
|
|
Payload:
|
|
audio_url: str (http/file) — OR —
|
|
audio_b64: str (base64)
|
|
language: str (optional, e.g. "uk", "en")
|
|
filename: str (optional, helps whisper detect format)
|
|
|
|
Returns Fabric contract: {text, segments[], language, meta, provider, model}
|
|
"""
|
|
language = payload.get("language")
|
|
raw_bytes, filename, source, content_type = await _resolve_audio_bytes(payload)
|
|
|
|
params = {}
|
|
if language:
|
|
params["language"] = language
|
|
|
|
async with httpx.AsyncClient(timeout=90) as c:
|
|
resp = await c.post(
|
|
f"{MEMORY_SERVICE_URL}/voice/stt",
|
|
files={"audio": (filename, raw_bytes, "audio/wav")},
|
|
params=params,
|
|
)
|
|
resp.raise_for_status()
|
|
data = resp.json()
|
|
|
|
text = data.get("text", "")
|
|
model_used = data.get("model", "faster-whisper")
|
|
lang_detected = data.get("language", language or "")
|
|
|
|
return {
|
|
"text": text,
|
|
"segments": [],
|
|
"language": lang_detected,
|
|
"meta": {
|
|
"model": model_used,
|
|
"provider": "memory_service",
|
|
"engine": model_used,
|
|
"service_url": MEMORY_SERVICE_URL,
|
|
"source": source,
|
|
"bytes": len(raw_bytes),
|
|
"filename": filename,
|
|
"content_type": content_type,
|
|
},
|
|
"provider": "memory_service",
|
|
"model": model_used,
|
|
}
|