Spaces:
Running on Zero
Running on Zero
File size: 1,651 Bytes
4cd8837 4aaae80 4cd8837 4aaae80 4cd8837 4aaae80 4cd8837 3f78ea8 4cd8837 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | """STT and TTS backend protocol and result types."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Protocol, runtime_checkable
# ── STT ───────────────────────────────────────────────────────────────────────
@dataclass(frozen=True)
class SttSegment:
start_seconds: float
end_seconds: float
text: str
language: str | None = None
confidence: float | None = None
@dataclass(frozen=True)
class SttResult:
segments: list[SttSegment]
full_text: str
detected_language: str
backend: str
ms: int
@runtime_checkable
class SttBackend(Protocol):
name: str
async def transcribe(
self,
audio_bytes: bytes,
language: str | None = None,
translate_to_en: bool = False,
) -> SttResult: ...
def health(self) -> dict: ...
# ── TTS ───────────────────────────────────────────────────────────────────────
@dataclass(frozen=True)
class TtsResult:
audio_bytes: bytes
audio_format: str
duration_seconds: float
backend: str
ms: int
@runtime_checkable
class TtsBackend(Protocol):
name: str
async def synthesize(
self,
text: str,
voice: str | None = None,
language: str = "de",
audio_format: str = "ogg_vorbis",
) -> TtsResult: ...
def health(self) -> dict: ...
|