Files
lang/js/transcribe.js

82 lines
3.6 KiB
JavaScript

// ---------- Groq API: транскрипция (прямой POST через ProxyAPI.ru) ----------
async function blobToWav(blob) {
const ab = await blob.arrayBuffer();
const ctx = new AudioContext({ sampleRate: 16000 });
const buf = await ctx.decodeAudioData(ab);
await ctx.close();
const mono = new Float32Array(buf.length);
for (let c = 0; c < buf.numberOfChannels; c++) {
const ch = buf.getChannelData(c);
for (let i = 0; i < buf.length; i++) mono[i] += ch[i];
}
if (buf.numberOfChannels > 1) for (let i = 0; i < mono.length; i++) mono[i] /= buf.numberOfChannels;
const wavBuf = new ArrayBuffer(44 + mono.length * 2);
const v = new DataView(wavBuf);
const wr = (o, s) => { for (let i = 0; i < s.length; i++) v.setUint8(o + i, s.charCodeAt(i)); };
wr(0, 'RIFF'); v.setUint32(4, 36 + mono.length * 2, true);
wr(8, 'WAVE'); wr(12, 'fmt ');
v.setUint32(16, 16, true); v.setUint16(20, 1, true); v.setUint16(22, 1, true);
v.setUint32(24, 16000, true); v.setUint32(28, 32000, true); v.setUint16(32, 2, true); v.setUint16(34, 16, true);
wr(36, 'data'); v.setUint32(40, mono.length * 2, true);
let off = 44;
for (let i = 0; i < mono.length; i++) {
const s = Math.max(-1, Math.min(1, mono[i]));
v.setInt16(off, s < 0 ? s * 0x8000 : s * 0x7FFF, true); off += 2;
}
return new Blob([wavBuf], { type: 'audio/wav' });
}
async function transcribe(blob) {
if (!GROQ_API_KEY) return { text: '', words: [], error: 'no_key' };
const tStart = performance.now();
try {
const wavBlob = await blobToWav(blob);
const fd = new FormData();
fd.append('file', wavBlob, 'audio.wav');
fd.append('model', 'whisper-1');
fd.append('language', 'it');
fd.append('response_format', 'verbose_json');
fd.append('timestamp_granularities[]', 'word');
const ctrl = new AbortController();
const timer = setTimeout(() => ctrl.abort(), 30000);
const r = await fetch('https://api.proxyapi.ru/openai/v1/audio/transcriptions', {
method: 'POST',
headers: { 'Authorization': `Bearer ${GROQ_API_KEY}` },
body: fd,
signal: ctrl.signal
});
clearTimeout(timer);
const raw = await r.text();
console.log('[TRANSCRIBE] ← ' + r.status + ' ' + ((performance.now()-tStart)/1000).toFixed(2) + 's raw=' + raw.slice(0,200));
let data;
try { data = JSON.parse(raw); } catch(pe) { return { text: '', words: [], error: 'parse:' + raw.slice(0,80) }; }
const words = (data.words || []).map(w => ({ word: w.word, start: w.start, end: w.end }));
console.log('[TRANSCRIBE] words:', words.length, words.map(w => w.start.toFixed(2)+'-'+w.end.toFixed(2)+' '+w.word).join(', '));
return { text: data.text || '', words, error: data.error?.message || data.error || null };
} catch(e) {
console.log('[TRANSCRIBE] ERR', e);
return { text: '', words: [], error: e.message };
}
}
async function translateToRussian(text) {
if (!GROQ_API_KEY) return;
try {
const res = await fetch('https://lang.kube5s.ru/openai/v1/chat/completions', {
method: 'POST',
headers: { 'Authorization': `Bearer ${GROQ_API_KEY}`, 'Content-Type': 'application/json' },
body: JSON.stringify({
model: 'gpt-4o',
messages: [{ role: 'user', content: 'Переведи на русский одним словом или фразой: ' + text }],
max_tokens: 50,
temperature: 0
})
});
const data = await res.json();
if (data.choices?.[0]?.message?.content) {
document.getElementById('translation').textContent = '🇷🇺 ' + data.choices[0].message.content;
}
} catch(e) { /* тихо */ }
}