Files
Triple-C/stt-container/server.py
Josh Knapp 532de77927
Some checks failed
Build App / compute-version (pull_request) Successful in 3s
Build App / build-macos (pull_request) Successful in 2m28s
Build STT Container / build-stt-container (pull_request) Successful in 3m18s
Build App / build-windows (pull_request) Successful in 4m40s
Build App / build-linux (pull_request) Failing after 1m46s
Build App / create-tag (pull_request) Has been skipped
Build App / sync-to-github (pull_request) Has been skipped
Add speech-to-text feature using Faster Whisper container
Adds a mic button to the terminal UI that captures speech, transcribes
it via a Faster Whisper sidecar container, and injects the text into
the terminal input. Includes settings panel for model selection
(tiny/small/medium), port config, and container lifecycle management.

- stt-container/: Dockerfile + FastAPI server for Whisper transcription
- Rust backend: STT container management, transcribe_audio IPC command
- Frontend: useSTT hook, SttButton, SttSettings, WAV encoder
- CI: Gitea Actions workflow for multi-arch STT image builds

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-12 20:02:39 -07:00

42 lines
1.1 KiB
Python

import os
import tempfile
from faster_whisper import WhisperModel
from fastapi import FastAPI, File, Form, UploadFile
from fastapi.responses import JSONResponse
app = FastAPI()
model: WhisperModel | None = None
@app.on_event("startup")
def load_model():
global model
model_size = os.environ.get("WHISPER_MODEL", "tiny")
model = WhisperModel(model_size, device="cpu", compute_type="int8")
@app.post("/transcribe")
async def transcribe(
file: UploadFile = File(...),
language: str = Form(None),
):
if model is None:
return JSONResponse(status_code=503, content={"error": "Model not loaded"})
with tempfile.NamedTemporaryFile(suffix=".wav", delete=True) as tmp:
tmp.write(await file.read())
tmp.flush()
kwargs = {}
if language:
kwargs["language"] = language
segments, info = model.transcribe(tmp.name, **kwargs)
text = " ".join(s.text for s in segments).strip()
return {"text": text, "language": info.language}
@app.get("/health")
def health():
return {"status": "ok"}