Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: Use /synthesize-direct for correct language selection

Browse Source 
/synthesize always used the German model. /synthesize-direct uses
Edge TTS (with language-aware voice selection) and falls back to
Piper with the correct model (Thorsten DE / Lessac EN).

Also cleared audio cache to purge wrongly-generated files.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-04-26 23:46:40 +02:00
parent 6b3bff48f0
commit 198a0b2a0d
1 changed files with 2 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
backend-lehrer/services/audio.py
View File

@@ -56,56 +56,14 @@ async def synthesize_word(
if os.path.exists(cached): if os.path.exists(cached):
return cached return cached
# Call Piper TTS service # Call Piper TTS service via /synthesize-direct (returns MP3, selects language correctly)
try: try:
async with httpx.AsyncClient(timeout=30.0) as client: async with httpx.AsyncClient(timeout=30.0) as client:
resp = await client.post( resp = await client.post(
f"{TTS_SERVICE_URL}/synthesize", f"{TTS_SERVICE_URL}/synthesize-direct",
json={ json={
"text": text, "text": text,
"language": language, "language": language,
"voice": "thorsten-high" if language == "de" else "lessac-high",
"module_id": "vocabulary",
"content_id": word_id or _cache_key(text, language),
},
)
if resp.status_code != 200:
logger.warning(f"TTS service returned {resp.status_code} for '{text}'")
return None
data = resp.json()
bucket = data.get("bucket")
object_key = data.get("object_key")
if bucket and object_key:
# Get presigned URL to download the audio
url_resp = await client.post(
f"{TTS_SERVICE_URL}/presigned-url",
json={"bucket": bucket, "object_key": object_key, "expires": 300},
)
if url_resp.status_code == 200:
audio_url = url_resp.json().get("url")
if audio_url:
audio_resp = await client.get(audio_url)
if audio_resp.status_code == 200:
with open(cached, "wb") as f:
f.write(audio_resp.content)
logger.info(f"TTS cached: '{text}' ({language}) → {cached}")
return cached
except Exception as e:
logger.warning(f"TTS service unavailable: {e}")
# Fallback: try direct MP3 endpoint
try:
async with httpx.AsyncClient(timeout=30.0) as client:
resp = await client.post(
f"{TTS_SERVICE_URL}/synthesize/mp3",
json={
"text": text,
"language": language,
"voice": "thorsten-high" if language == "de" else "lessac-high",
"module_id": "vocabulary",
}, },
) )
if resp.status_code == 200 and resp.headers.get("content-type", "").startswith("audio"): if resp.status_code == 200 and resp.headers.get("content-type", "").startswith("audio"):