mirror of
https://github.com/hanzoai/frames.git
synced 2026-09-24 00:08:03 +00:00
zooqueen
ae80da5998
Voice is POST /v1/audio/speech and word timings come from POST /v1/audio/transcriptions over the rendered audio. Music, sound effects, images, and video generate through /v1/audio/music, /v1/audio/foley, /v1/images/generations, and /v1/videos/generations. The shared catalog is a listing under media/<type>/ in our own object store, browsed through /v1/s3 — an empty prefix reports itself as empty rather than reading as a bad query. One client (scripts/lib/api.mjs) holds every route and the one credential: a Hanzo IAM token in $HANZO_API_KEY, read from Hanzo KMS. No credential file, no per-repo .env, no per-provider CLI to install or keep current. $HANZO_BASE_URL points the same code at a local Hanzo Engine. Word timings are passed through, never interpolated: a caption cut on invented boundaries reads as correct and drifts against the voice. When the service returns text without them, the word array is empty and the caller is told. Deletes the provider cascade this replaces, its model ladders, and the account linking in telemetry — the install id stands alone.
79 lines
2.7 KiB
JavaScript
79 lines
2.7 KiB
JavaScript
#!/usr/bin/env node
|
|
|
|
import { existsSync, renameSync, writeFileSync } from "node:fs";
|
|
import { basename, extname, resolve } from "node:path";
|
|
import { parseArgs } from "node:util";
|
|
import { MODEL, transcript } from "./lib/api.mjs";
|
|
import { track } from "./lib/telemetry.mjs";
|
|
|
|
// Transcription: POST /v1/audio/transcriptions through api.hanzo.ai. Emits
|
|
// { text, words: [{ text, start, end }] } for transcript-cut, captions, and the
|
|
// audio engine — the one transcript shape the rest of media-use reads.
|
|
//
|
|
// `words` is empty when the service returns no per-word timings. That is
|
|
// reported, never interpolated: captions cut on invented boundaries look right
|
|
// and drift against the audio.
|
|
|
|
const { values: args } = parseArgs({
|
|
options: {
|
|
input: { type: "string", short: "i" },
|
|
out: { type: "string", short: "o" },
|
|
model: { type: "string", default: MODEL.words },
|
|
lang: { type: "string", default: "en" },
|
|
json: { type: "boolean", default: false },
|
|
help: { type: "boolean", short: "h", default: false },
|
|
},
|
|
strict: true,
|
|
});
|
|
|
|
if (args.help) {
|
|
console.log(`media-use transcribe: audio -> text + word timings
|
|
|
|
Usage:
|
|
node transcribe.mjs --input audio.wav [--out audio.transcribe.json] [--model ${MODEL.words}] [--lang en]
|
|
|
|
Runs against api.hanzo.ai/v1/audio/transcriptions. Needs $HANZO_API_KEY.`);
|
|
process.exit(0);
|
|
}
|
|
|
|
if (!args.input) {
|
|
console.error("error: --input is required");
|
|
process.exit(2);
|
|
}
|
|
const inputPath = resolve(args.input);
|
|
if (!existsSync(inputPath)) {
|
|
console.error(`error: input not found: ${inputPath}`);
|
|
process.exit(2);
|
|
}
|
|
const outPath = resolve(
|
|
args.out || `${inputPath.slice(0, -extname(inputPath).length)}.transcribe.json`,
|
|
);
|
|
|
|
// Write via a sibling temp + atomic rename so a SIGKILL mid-write can't leave a
|
|
// truncated transcript at outPath (downstream reads it as valid JSON).
|
|
function atomicWrite(target, data) {
|
|
const tmp = `${target}.tmp-${process.pid}`;
|
|
writeFileSync(tmp, data);
|
|
renameSync(tmp, target);
|
|
}
|
|
|
|
try {
|
|
const result = await transcript({ file: inputPath, lang: args.lang, model: args.model });
|
|
atomicWrite(outPath, JSON.stringify(result, null, 2));
|
|
if (args.json) {
|
|
console.log(JSON.stringify({ ok: true, out: outPath, words: result.words.length }));
|
|
} else {
|
|
console.log(
|
|
`transcribed ${basename(inputPath)} -> ${outPath} (${result.words.length} words, ${args.model})`,
|
|
);
|
|
if (!result.words.length) {
|
|
console.error("note: the service returned text without word timings");
|
|
}
|
|
}
|
|
await track("media_use_transcribe", { model: args.model, words: result.words.length });
|
|
} catch (err) {
|
|
if (args.json) console.log(JSON.stringify({ ok: false, error: err.message }));
|
|
else console.error(`error: transcription failed: ${err.message}`);
|
|
process.exit(1);
|
|
}
|