diff --git a/packages/cli/src/commands/media-use/generate.ts b/packages/cli/src/commands/media-use/generate.ts index 4182e698d0..1bb19cfc50 100644 --- a/packages/cli/src/commands/media-use/generate.ts +++ b/packages/cli/src/commands/media-use/generate.ts @@ -116,7 +116,8 @@ export default defineCommand({ script: { type: "string", description: "avatar, voice: the words spoken" }, voice: { type: "string", - description: "avatar, voice: a HeyGen voice id, or a language for its first voice in it", + description: + "avatar, voice: a HeyGen voice id, or a language (English, Chinese, en, zh-CN) for its first voice in it", }, seconds: { type: "string", diff --git a/packages/cli/src/commands/media-use/voices.test.ts b/packages/cli/src/commands/media-use/voices.test.ts new file mode 100644 index 0000000000..de3d9ed1b5 --- /dev/null +++ b/packages/cli/src/commands/media-use/voices.test.ts @@ -0,0 +1,51 @@ +import { mkdtempSync } from "node:fs"; +import { tmpdir } from "node:os"; +import { join } from "node:path"; +import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"; + +vi.mock("../../cloud/auth.js", () => ({ + resolveCloudAuthHeaders: async () => ({ "x-api-key": "k" }), + refreshIfNeeded: async (credential: T) => credential, + resolveCloudBaseUrl: () => "https://api.test", +})); + +const { default: voices } = await import("./voices.js"); + +beforeEach(() => { + vi.stubEnv("HYPERFRAMES_CONFIG_DIR", mkdtempSync(join(tmpdir(), "hf-voices-test-"))); +}); +afterEach(() => { + vi.unstubAllGlobals(); + vi.unstubAllEnvs(); + vi.restoreAllMocks(); +}); + +describe("media-use voices", () => { + it("says the list is the workspace's, not the person's, so a teammate's clone is never taken as theirs", async () => { + vi.stubGlobal( + "fetch", + async () => + new Response( + JSON.stringify({ + data: [{ voice_id: "v1", name: "Teammate clone", language: "English" }], + }), + { status: 200, headers: { "content-type": "application/json" } }, + ), + ); + const out: string[] = []; + vi.spyOn(console, "log").mockImplementation((line: string) => void out.push(line)); + await voices.run!({ args: { json: true } } as never); + const printed = JSON.parse(out.join("\n")); + expect(printed.voices).toEqual([ + { voice_id: "v1", name: "Teammate clone", language: "English", gender: undefined }, + ]); + expect(printed.whose).toMatch(/a teammate's included/); + expect(printed.whose).toMatch(/never pick one by count, language or name/); + expect(printed.whose).toMatch( + /says it is theirs or that its owner agreed, whether they name it or give its id/, + ); + expect(printed.whose).toMatch( + /an id missing here may still be a teammate's clone, never proof of a stock voice/, + ); + }); +}); diff --git a/packages/cli/src/commands/media-use/voices.ts b/packages/cli/src/commands/media-use/voices.ts index a443b75f63..36c5ca1ba8 100644 --- a/packages/cli/src/commands/media-use/voices.ts +++ b/packages/cli/src/commands/media-use/voices.ts @@ -4,14 +4,17 @@ import { jsonArg, num, runMeasure } from "../../measure/command.js"; import { ownVoices } from "../../heygen/v3.js"; export const examples: Example[] = [ - ["The voice clones the film's own account can speak with", "hyperframes media-use voices"], + ["The voice clones the film's workspace can speak with", "hyperframes media-use voices"], ]; +const WHOSE = + "Every clone this workspace can use, a teammate's included: HeyGen does not say who made one. Use a clone only when the person says it is theirs or that its owner agreed, whether they name it or give its id; never pick one by count, language or name. This is one page of at most --limit, so an id missing here may still be a teammate's clone, never proof of a stock voice."; + export default defineCommand({ meta: { name: "voices", description: - "List the voice clones on the HyperFrames account that makes the film. Never use `heygen voice list` for this: that is a separate sign-in and can be another account", + "List the voice clones the HyperFrames account's workspace can use, a teammate's included. Use one only when the person names it as their own. Never use `heygen voice list` for this: that is a separate sign-in and can be another account", }, args: { limit: { type: "string", description: "How many to list (default 20)" }, @@ -20,6 +23,7 @@ export default defineCommand({ async run({ args }) { await runMeasure(async () => ({ voices: await ownVoices(num(args.limit, "--limit", 20)), + whose: WHOSE, })); }, }); diff --git a/packages/cli/src/heygen/generate.test.ts b/packages/cli/src/heygen/generate.test.ts index 7d83df19b1..57fe4a573c 100644 --- a/packages/cli/src/heygen/generate.test.ts +++ b/packages/cli/src/heygen/generate.test.ts @@ -1021,7 +1021,12 @@ describe("foldShort", () => { }); describe("pickVoice", () => { - const voice = (id: string, name: string) => ({ voice_id: id.repeat(32), name, gender: "female" }); + const voice = (id: string, name: string, language?: string) => ({ + voice_id: id.repeat(32), + name, + gender: "female", + language, + }); let catalog = [voice("a", "Lin"), voice("b", "Wei")]; const asked: string[] = []; const posts: { key: string | null; body: Record }[] = []; @@ -1061,6 +1066,46 @@ describe("pickVoice", () => { expect(asked[0]).toBe("https://api.test/v3/voices?type=public&language=Chinese&limit=1"); }); + for (const [spelled, language] of [ + ["en", "English"], + ["en-US", "English"], + ["zh-CN", "Chinese"], + ["cmn", "Chinese"], + ] as const) { + it(`asks for ${language} voices when --voice is the language code ${spelled}, not for multilingual ones`, async () => { + heygen(); + catalog = [voice("a", "Lin", language)]; + const r = { + type: "voice" as const, + out: join(project, `assets/${spelled}.mp3`), + voice: spelled, + }; + expect((await pickVoice(r)).name).toBe("Lin"); + expect(new URL(asked[0]!).searchParams.get("language")).toBe(language); + }); + } + + it("refuses the multilingual voice HeyGen offers for a language it does not list, instead of using it", async () => { + heygen(); + catalog = [voice("g", "Gail in car", "Multilingual")]; + const r = { type: "voice" as const, out: join(project, "assets/m.mp3"), voice: "Mandarin" }; + await expect(pickVoice(r)).rejects.toMatchObject({ + message: "HeyGen has no public voice for Mandarin (it offered a Multilingual one)", + fix: expect.stringContaining("English or Chinese"), + }); + }); + + it("takes a multilingual voice when the request names Multilingual", async () => { + heygen(); + catalog = [voice("g", "Gail in car", "Multilingual")]; + const r = { + type: "voice" as const, + out: join(project, "assets/ml.mp3"), + voice: "Multilingual", + }; + expect((await pickVoice(r)).name).toBe("Gail in car"); + }); + it("says what to do when HeyGen will not list its voices", async () => { vi.stubGlobal( "fetch", diff --git a/packages/cli/src/heygen/generate.ts b/packages/cli/src/heygen/generate.ts index e9f1ef791a..6f908146bb 100644 --- a/packages/cli/src/heygen/generate.ts +++ b/packages/cli/src/heygen/generate.ts @@ -616,12 +616,27 @@ export async function pickVoice(r: GenerateRequest): Promise { ]); const kept = keptVoice(project, request); if (kept) return kept; - const [voice] = await publicVoices(r.voice, 1); - if (!voice) throw new Fix(`HeyGen has no public voice for ${r.voice}`, "--voice "); + const language = languageName(r.voice); + const [voice] = await publicVoices(language, 1); + const named = voice?.language?.toLowerCase() === language.toLowerCase(); + if (!voice || (!named && voice.language?.toLowerCase() === "multilingual")) + throw new Fix( + `HeyGen has no public voice for ${r.voice}${voice ? ` (it offered a ${voice.language} one)` : ""}`, + "--voice , or --voice ", + ); keepVoice(project, request, voice); return voice; } +const LANGUAGE_TAG = /^([a-z]{2,3})(?:[-_][a-z0-9]{2,8})*$/i; +const LANGUAGE_NAMES = new Intl.DisplayNames(["en"], { type: "language", fallback: "none" }); + +function languageName(spelled: string): string { + const tag = LANGUAGE_TAG.exec(spelled.trim()); + if (!tag) return spelled; + return LANGUAGE_NAMES.of(tag[1]!.toLowerCase()) ?? spelled; +} + export function checkRequest(r: GenerateRequest): void { const route = ROUTES[r.type]; if (!route.ext.includes(extname(r.out).toLowerCase())) diff --git a/skills-manifest.json b/skills-manifest.json index 10be9ab490..90499b61c5 100644 --- a/skills-manifest.json +++ b/skills-manifest.json @@ -34,7 +34,7 @@ "files": 2 }, "style-sampling": { - "hash": "e54aca29ef95de2e", + "hash": "5d26c6211fdfc062", "files": 2 } } diff --git a/skills/style-sampling/references/remix.md b/skills/style-sampling/references/remix.md index c4891aad5b..1acb62fc34 100644 --- a/skills/style-sampling/references/remix.md +++ b/skills/style-sampling/references/remix.md @@ -23,7 +23,7 @@ The person's message carries what it carries. Ask once, together, only what is s - **Never the creator's face, voice, footage, wordmark or show name.** That rule is about the creator: the person's own clone, their own recording or a credited stock voice are all fine. - **A presenter runs on the plan.** Their own HeyGen avatar if they have one (`npx hyperframes media-use avatars` lists the looks on the HyperFrames account making the film; never `heygen avatar list`, a separate sign-in that can be another account), otherwise Avatar IV from their photo, both through `npx hyperframes media-use generate --type avatar` with the finished voice, so the lips land on it. HeyGen Video 1 is the fallback when neither works. -- **Settle the voice before any research.** A HeyGen voice id the person gave is the voice: use it and ask nothing. Only part of one (an 8-character prefix): find the full id in `npx hyperframes media-use voices` and ask only when no clone or several match. Anything else: run `npx hyperframes media-use voices`, which lists the clones on the HyperFrames account making the film; never `heygen voice list`, a separate sign-in that can be another account. One clone: use it. Several: ask which. None, or not signed in: ask once for their voice id, a clone they make in HeyGen from 30 s to 3 min of their own reading, or their own recorded narration; with none of these, say in one line that you'll use a HeyGen stock voice, name it in the credits as AI-generated, and go on. Nothing is voiced for it before stop 1: at the voice step, `npx hyperframes media-use generate --type voice --voice --script "" --out .media/pick.mp3 --plan` names HeyGen's first public voice in that language without making anything; set the kit's voice id to its `voice_id` and credit that voice by name. Nothing else starts until this is settled. +- **Settle the voice before any research.** A HeyGen voice id the person gave, or an 8-character prefix of one, is used only when they say it is theirs, that its owner agreed to this film, or that it is a HeyGen stock voice. Having the id is not that, and an id missing from `npx hyperframes media-use voices` proves nothing (it lists one page), so when they have not said, ask it in the one round of questions. A prefix: find the full id in `npx hyperframes media-use voices --limit 100`, and ask when it matches none or several. A clone they name as theirs, or say its owner agreed to: find it there and use it. That list is every clone the HyperFrames account's workspace can use, a teammate's included, and does not say who made one, so never pick from it by count, language or name; never `heygen voice list`, a separate sign-in that can be another account. Nothing named, or not signed in: ask once for their voice id, a clone they make in HeyGen from 30 s to 3 min of their own reading, or their own recorded narration; with none of these, say in one line that you'll use a HeyGen stock voice, name it in the credits as AI-generated, and go on. Nothing is voiced for it before stop 1: at the voice step, `npx hyperframes media-use generate --type voice --voice --script "" --out .media/pick.mp3 --plan` names HeyGen's first public voice in that language without making anything; set the kit's voice id to its `voice_id` and credit that voice by name. Nothing else starts until this is settled. - **Then say what's coming** in one short message that is not a question, and go on without waiting: the working title and hook, the length, and roughly how long it takes. No prices. - **The length is the person's, and it beats the template's runtime.** Offer about 1 minute first: the cold open, the title beat and one chapter, the end card short. 2 to 4 minutes: REMIX.md's short cut. A full episode: the series' own runtime. Their own words ("90 seconds", "5 min"): that length. No length answered and none in the topic: about 1 minute, and offer the longer cut in the reply. Scale everything to it: script words (the template's script stats at that runtime), facts, sections, music cues, review rounds (one for a minute, two for a full episode); never pad or trim to reach the series' runtime instead. - **Credits name only who the person names.** Roles and names come from the person, never from a voice list, an account or a placeholder; a role nobody named is left out.