6a62a43d61
Generation Page (complete rebuild): - Full production-parity exam generation wizard with 4 IELTS modules - Reading: AI passage gen, 5 exercise types (MCQ, Fill, Write, T/F, Match) - Listening: 4 section types, AI context gen, TTS audio gen (ElevenLabs) - Writing: Task 1/2, AI instruction gen, word limits, marks - Speaking: 3 parts, AI script gen, avatar video gen (7 avatars) - Per-module config: timer, CEFR difficulty, access, approval, rubrics - Exam submission workflow (draft/published) Exam Structures: - New encoach.exam.structure model + CRUD controller - ExamStructuresPage wired to real API AI Module (encoach_ai): - OpenAI service, ElevenLabs TTS, AWS Polly, ELAI avatars - AI settings model with Odoo config parameters - 7 generation endpoints (passage, exercises, instructions, scripts, context) Vector Module (encoach_vector): - pgvector integration for RAG-based content search - Embedding service with sentence-transformers Exam Session Fixes: - Fixed ExamSession.tsx field mapping (question_type→type, exam_title→title) - Fixed submit payload to include attempt_id and answers - Fixed normalizeType to handle null/undefined Tested: 12/12 API tests passed, browser-verified with real OpenAI calls Made-with: Cursor
103 lines
3.4 KiB
Python
103 lines
3.4 KiB
Python
"""AWS Polly text-to-speech service."""
|
|
|
|
import logging
|
|
import time
|
|
|
|
_logger = logging.getLogger(__name__)
|
|
|
|
try:
|
|
import boto3 as _boto3
|
|
except ImportError:
|
|
_boto3 = None
|
|
|
|
VOICE_MAP = {
|
|
"en-GB": {"female": "Amy", "male": "Brian"},
|
|
"en-US": {"female": "Joanna", "male": "Matthew"},
|
|
"en-AU": {"female": "Nicole", "male": "Russell"},
|
|
"en-IN": {"female": "Aditi", "male": "Aditi"},
|
|
}
|
|
|
|
|
|
class PollyService:
|
|
"""AWS Polly TTS for generating listening exam audio."""
|
|
|
|
def __init__(self, env):
|
|
self.env = env
|
|
self._get_param = env["ir.config_parameter"].sudo().get_param
|
|
self._client = None
|
|
|
|
def _get_client(self):
|
|
if self._client:
|
|
return self._client
|
|
if not _boto3:
|
|
raise RuntimeError("boto3 not installed — run: pip install boto3")
|
|
access_key = self._get_param("encoach_ai.aws_access_key", "")
|
|
secret_key = self._get_param("encoach_ai.aws_secret_key", "")
|
|
region = self._get_param("encoach_ai.aws_region", "eu-west-1")
|
|
if not access_key or not secret_key:
|
|
import os
|
|
access_key = access_key or os.environ.get("AWS_ACCESS_KEY_ID", "")
|
|
secret_key = secret_key or os.environ.get("AWS_SECRET_ACCESS_KEY", "")
|
|
if not access_key:
|
|
raise RuntimeError("AWS credentials not configured — set in AI Settings")
|
|
self._client = _boto3.client(
|
|
"polly",
|
|
aws_access_key_id=access_key,
|
|
aws_secret_access_key=secret_key,
|
|
region_name=region,
|
|
)
|
|
return self._client
|
|
|
|
def _log(self, action, latency, status="success", error=None):
|
|
try:
|
|
self.env["encoach.ai.log"].sudo().create({
|
|
"service": "polly",
|
|
"action": action,
|
|
"latency_ms": latency,
|
|
"status": status,
|
|
"error_message": error,
|
|
})
|
|
except Exception:
|
|
pass
|
|
|
|
def synthesize(self, text, *, voice=None, language="en-GB", gender="female",
|
|
engine="neural", output_format="mp3"):
|
|
"""Convert text to speech audio bytes.
|
|
|
|
Returns:
|
|
dict with 'audio' (bytes), 'content_type', 'voice', 'characters'
|
|
"""
|
|
client = self._get_client()
|
|
if not voice:
|
|
voice = VOICE_MAP.get(language, VOICE_MAP["en-GB"]).get(gender, "Amy")
|
|
t0 = time.time()
|
|
try:
|
|
resp = client.synthesize_speech(
|
|
Text=text,
|
|
OutputFormat=output_format,
|
|
VoiceId=voice,
|
|
Engine=engine,
|
|
LanguageCode=language,
|
|
)
|
|
audio = resp["AudioStream"].read()
|
|
latency = int((time.time() - t0) * 1000)
|
|
self._log("synthesize", latency)
|
|
return {
|
|
"audio": audio,
|
|
"content_type": resp["ContentType"],
|
|
"voice": voice,
|
|
"characters": len(text),
|
|
}
|
|
except Exception as exc:
|
|
self._log("synthesize", int((time.time() - t0) * 1000), "error", str(exc))
|
|
raise
|
|
|
|
def list_voices(self, language="en-GB"):
|
|
"""List available voices for a language."""
|
|
client = self._get_client()
|
|
resp = client.describe_voices(LanguageCode=language)
|
|
return [
|
|
{"id": v["Id"], "name": v["Name"], "gender": v["Gender"], "engine": v.get("SupportedEngines", [])}
|
|
for v in resp.get("Voices", [])
|
|
]
|