mirror of
https://github.com/heygen-com/hyperframes.git
synced 2026-09-07 10:06:21 +00:00
James Russo
4a55bc8673
* feat(cli): add --lang and auto-infer phonemizer locale from voice prefix `hyperframes tts` was calling Kokoro's `model.create(text, voice=, speed=)` with no language argument, so Kokoro's default phonemizer (en-us) was applied regardless of the voice selected. Picking `ef_dora` or `jf_alpha` and feeding it Spanish or Japanese text produced English-phonemized output. Closes #349. - `manager.ts`: add `SUPPORTED_LANGS`, `inferLangFromVoiceId`, and `isSupportedLang`. Attach a `defaultLang` field to every bundled voice and expand the bundled list with `ef_dora`, `ff_siwis`, `jf_alpha`, `zf_xiaobei` so `--list` surfaces multilingual options. - `synthesize.ts`: accept optional `lang: SupportedLang` in `SynthesizeOptions`, forward it to the Python worker as `argv[7]`. The worker introspects `Kokoro.create`'s signature and only passes `lang=` when the installed kokoro-onnx version supports it. Returned metadata now includes `lang` and `langApplied` so callers can detect silent no-ops. Bump the cached script filename to `synth-v2.py` so existing installs pick up the new script automatically. - `commands/tts.ts`: add `--lang, -l` with validation against `SUPPORTED_LANGS`. Resolution order is explicit `--lang` > inferred from voice prefix > `en-us`. When explicit lang disagrees with the voice-implied lang (legitimate for stylized accents), emit a dim-level hint; suppress under `--json`. When kokoro-onnx silently ignores the kwarg, log that too. Update `--list` with a new "Lang code" column and add multilingual examples. - Tests: new `manager.test.ts` covering every supported prefix, the unknown-prefix fallback, case-insensitivity, `isSupportedLang` validation, and a regression guard that every bundled voice has a valid `defaultLang` matching its ID. - Docs: `docs/packages/cli.mdx` and `skills/hyperframes/references/tts.md` updated with the flag, examples, the espeak-ng dependency note for non-English phonemization, and the voice-prefix → lang table. Backward compatibility: - English voices (a*/b* prefixes) continue to phonemize as en-us / en-gb — no change. - Non-English voices now phonemize correctly by default (bug fix, not a regression). - Older kokoro-onnx versions that don't know the `lang` kwarg keep working via signature introspection; the CLI logs a dim note if `--lang` was requested but ignored. Verification: - `bun --cwd packages/cli test` — 128 tests pass (incl. 17 new). - `bunx oxlint` and `bunx oxfmt --check` clean on changed files. - `bun run build` succeeds. - `npx tsx packages/cli/src/cli.ts tts --help` / `--list` render cleanly; invalid `--lang` produces a clean error with the valid-codes list. * refactor(cli): simplify tts --lang implementation Post-review cleanup on #351. Net -21 lines. - Drop `defaultLang` field + `makeVoice()` helper from VoiceInfo — compute via `inferLangFromVoiceId(v.id)` at read time in listVoices. The only reader was the --list table; caching the derived value on every voice added a self-consistency invariant we had to test. - Drop redundant `lang` field from SynthesizeResult — caller already knows the requested lang since it passed it in; only `langApplied` carries information the caller can't derive. - Use `errorBox` for --lang validation to match the house style in render.ts (other validation errors already use errorBox). - Reuse existing `langList` module constant in the validation error instead of re-joining SUPPORTED_LANGS. - Inline `DEFAULT_LANG` — used once in inferLangFromVoiceId. - Trim WHAT-restating comments and the duplicate prefix-enumeration JSDoc on inferLangFromVoiceId (VOICE_PREFIX_LANG already carries per-row comments). - Clean up orphaned `synth*.py` files in ~/.cache/hyperframes/tts when writing the current versioned script, so repeated upgrades don't leak files. - Drop the `EN-US` case-sensitive-rejection test assertion — the CLI lowercases input before validation, so accepting mixed case is a feature, not a bug. Tests: 16/16 in `manager.test.ts`, 127/127 full CLI suite pass. Lint + format + typecheck clean.
62 lines
1.8 KiB
TypeScript
62 lines
1.8 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import {
|
|
BUNDLED_VOICES,
|
|
SUPPORTED_LANGS,
|
|
inferLangFromVoiceId,
|
|
isSupportedLang,
|
|
} from "./manager.js";
|
|
|
|
describe("inferLangFromVoiceId", () => {
|
|
it.each([
|
|
["af_heart", "en-us"],
|
|
["am_adam", "en-us"],
|
|
["bf_emma", "en-gb"],
|
|
["bm_george", "en-gb"],
|
|
["ef_dora", "es"],
|
|
["ff_siwis", "fr-fr"],
|
|
["hf_alpha", "hi"],
|
|
["if_sara", "it"],
|
|
["jf_alpha", "ja"],
|
|
["pf_dora", "pt-br"],
|
|
["zf_xiaobei", "zh"],
|
|
])("maps voice %s to lang %s", (voiceId, expected) => {
|
|
expect(inferLangFromVoiceId(voiceId)).toBe(expected);
|
|
});
|
|
|
|
it("falls back to en-us for unknown prefixes", () => {
|
|
expect(inferLangFromVoiceId("xf_test")).toBe("en-us");
|
|
expect(inferLangFromVoiceId("")).toBe("en-us");
|
|
});
|
|
|
|
it("is case-insensitive on the prefix letter", () => {
|
|
expect(inferLangFromVoiceId("EF_dora")).toBe("es");
|
|
expect(inferLangFromVoiceId("ZF_xiaobei")).toBe("zh");
|
|
});
|
|
});
|
|
|
|
describe("isSupportedLang", () => {
|
|
it("accepts every value in SUPPORTED_LANGS", () => {
|
|
for (const lang of SUPPORTED_LANGS) {
|
|
expect(isSupportedLang(lang)).toBe(true);
|
|
}
|
|
});
|
|
|
|
it("rejects invalid or misspelled lang codes", () => {
|
|
expect(isSupportedLang("english")).toBe(false);
|
|
expect(isSupportedLang("de")).toBe(false);
|
|
expect(isSupportedLang("")).toBe(false);
|
|
});
|
|
});
|
|
|
|
describe("BUNDLED_VOICES", () => {
|
|
// --lang is user-facing, so the voice list must give users a working
|
|
// example in at least the most common non-English locales.
|
|
it("exposes at least one voice per non-English language", () => {
|
|
const langs = new Set(BUNDLED_VOICES.map((v) => inferLangFromVoiceId(v.id)));
|
|
expect(langs.has("es")).toBe(true);
|
|
expect(langs.has("fr-fr")).toBe(true);
|
|
expect(langs.has("ja")).toBe(true);
|
|
expect(langs.has("zh")).toBe(true);
|
|
});
|
|
});
|