"""Dictation and read-aloud. Both directions go through the server rather than from the browser to the audio endpoint directly, for the same reason model requests do: the endpoint is often on a private address the browser cannot reach, and its API key must never leave this process. """ from __future__ import annotations import logging from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status from fastapi.responses import PlainTextResponse, Response, StreamingResponse from sqlalchemy.orm import Session as DBSession from lembas.api.deps import Db, RequiredUser, require_permission from lembas.db.models import Chat, Message, User from lembas.services import audio as audio_service from lembas.services import settings_store from lembas.services.llm.openai_client import LLMError from lembas.services.markdown import speakable_text log = logging.getLogger(__name__) router = APIRouter(prefix="/api/audio", tags=["audio"]) # A minute of speech is well under a megabyte in any browser codec; this is a # ceiling on nonsense, not a budget. Recorded audio is held in memory and never # written to disk: it is not an attachment, has no owner and nothing would ever # sweep it up. MAX_AUDIO_BYTES = 25 * 1024 * 1024 def _user_audio(user: User) -> dict: return dict((user.settings_json or {}).get("audio") or {}) def resolve_voice(config: dict, user: User) -> str: """The voice a given user should be read to in. Their own choice, then the instance default, then whatever the endpoint picks. Not validated against the discovered list: a voice can disappear when a server is reconfigured, and falling back beats failing. """ return (_user_audio(user).get("voice") or config.get("tts_voice") or "").strip() def resolve_speed(config: dict, user: User) -> float: """The playback speed for this user, in the range every endpoint accepts. Key presence decides which layer wins, not truthiness: chained `or` would make a stored speed of 0 fall through to the default instead of being clamped, which is a different answer for no stated reason. """ preferences = _user_audio(user) if "speed" in preferences: raw = preferences["speed"] elif "tts_speed" in config: raw = config["tts_speed"] else: return 1.0 try: chosen = float(raw) except (TypeError, ValueError): return 1.0 # Clamped rather than dropped, unlike the sampling parameters: a speed of 0 # is not a slower reading, it is silence. return min(max(chosen, 0.25), 4.0) @router.post( "/transcribe", dependencies=[Depends(require_permission("audio.transcribe"))] ) async def transcribe( db: Db, user: RequiredUser, file: UploadFile = File(...) ) -> Response: """Turn a recording into text for the composer. Returns plain text, not HTML: the caller assigns it to a textarea's value, where it is never parsed as markup. """ config = settings_store.audio(db) if not config.get("stt_enabled"): raise HTTPException( status.HTTP_404_NOT_FOUND, "Dictation is not enabled on this instance." ) data = await file.read(MAX_AUDIO_BYTES + 1) if len(data) > MAX_AUDIO_BYTES: raise HTTPException( status.HTTP_413_CONTENT_TOO_LARGE, "That recording is too long." ) if not data: raise HTTPException(status.HTTP_400_BAD_REQUEST, "The recording was empty.") language = (_user_audio(user).get("language") or config.get("stt_language") or "").strip() try: text = await audio_service.transcribe( audio_service.endpoint_for(config, "stt"), data=data, filename=file.filename or "speech.webm", content_type=file.content_type or "audio/webm", model=config.get("stt_model") or "whisper-1", language=language, ) except LLMError as exc: log.info("transcription failed: %s", exc.message) raise HTTPException(status.HTTP_502_BAD_GATEWAY, exc.message) from exc return PlainTextResponse(text) @router.get( "/speech/{chat_id}/{message_id}", dependencies=[Depends(require_permission("audio.listen"))], ) async def speech(db: Db, user: RequiredUser, chat_id: str, message_id: str) -> Response: """Read one message aloud.""" config = settings_store.audio(db) if not config.get("tts_enabled"): raise HTTPException( status.HTTP_404_NOT_FOUND, "Read-aloud is not enabled on this instance." ) message = _owned_message(db, chat_id, message_id, user) text = speakable_text(message.content) if not text: raise HTTPException(status.HTTP_404_NOT_FOUND, "There is nothing to read out.") try: media_type, stream = await audio_service.speak( audio_service.endpoint_for(config, "tts"), text, model=config.get("tts_model") or "tts-1", voice=resolve_voice(config, user), fmt=config.get("tts_format") or "mp3", speed=resolve_speed(config, user), ) except LLMError as exc: log.info("speech failed: %s", exc.message) raise HTTPException(status.HTTP_502_BAD_GATEWAY, exc.message) from exc return StreamingResponse( stream, media_type=media_type, # Not cached: the voice can change under the reader between plays, and # a message can be regenerated at the same URL. headers={"Cache-Control": "no-store", "X-Accel-Buffering": "no"}, ) async def available_voices(config: dict, *, refresh: bool = False) -> tuple[list[str], str]: """Discovered voices and, if discovery failed, why. Returns rather than raises: a settings page whose voice list could not be fetched should still render, with the reason next to an empty list. """ if not config.get("tts_enabled") or not (config.get("tts_base_url") or "").strip(): return [], "" try: return await audio_service.voices( audio_service.endpoint_for(config, "tts"), refresh=refresh ), "" except LLMError as exc: return [], exc.message def _owned_message(db: DBSession, chat_id: str, message_id: str, user: User) -> Message: """The message, if it belongs to a chat this user owns. 404 rather than 403 throughout, matching api/chats.py: whether a given id exists is not information these endpoints hand out. """ chat = db.get(Chat, chat_id) if chat is None or chat.user_id != user.id: raise HTTPException(status.HTTP_404_NOT_FOUND, "That chat no longer exists.") message = db.get(Message, message_id) if message is None or message.chat_id != chat.id: raise HTTPException(status.HTTP_404_NOT_FOUND, "That message no longer exists.") return message