@mekuru/voisona 0.1.2 → 0.1.3

package/README.jp.md

@@ -104,7 +104,7 @@ import { Voisona, tanaka } from "@mekuru/voisona";
 - `len`: 無音を含む全体のフレーム数。既定: 音声の長さを切り上げた値 + `gap`。話速は変えない。
 - `id`・`at`: 生成する `<dur>` の識別名と開始時刻。[時間の属性](../../docs/reference/Syntax.jp.md#時間の属性)を参照。
 
-ルビ `｜表示《よみ》` は「よみ」を読み、タイムラインには「表示」を残します。半角 `|` と `漢字《かんじ》` も使用できます。`<br />` は空白になり、ほかの要素は入れられません。セリフの連続再生は `<seq>`、字幕との同時表示は `<stack>`、口パクは[立ち絵の `Talk`](../portrait/README.jp.md) を使います。
+ルビ `｜表示《よみ》` は「よみ」を読み、タイムラインには「表示」を残します。半角 `|` と `漢字《かんじ》` も使用できます。`<br />` は空白になり、ほかの要素は入れられません。セリフの連続再生は `<seq>`、字幕との同時表示は `<stack>`、口パクは[立ち絵の `Talk`](../narrator/README.jp.md) を使います。
 
 ### キャッシュとプレビュー
 
@@ -121,3 +121,5 @@ curl --user "$MEKURU_VOISONA_USER" http://localhost:32766/api/talk/v1/voices
 ```
 
 curl に API パスワードを入力します。HTTP 401 はメールアドレスと API パスワードを確認してください。接続できない場合は起動状態とポートを確認します。Windows のエンジンには [WSL の mirrored ネットワーク](https://learn.microsoft.com/en-us/windows/wsl/networking#mirrored-mode-networking)で `127.0.0.1` から接続できます。`localhost` で失敗する場合は `MEKURU_VOISONA_URL=http://127.0.0.1:32766` を指定します。
+
+独自のナレータでは `await Voisona.prepare({ ...声の設定, children })` で音声素材・表示文字・長さをまとめて取得できます。`id`・`at` は配置する部品に付けます。[共有する音声素材](../speech/README.jp.md#共有する音声素材)と[ナレータの組み立て](../narrator/README.jp.md)を参照してください。

package/README.md

@@ -104,7 +104,7 @@ Omitted numeric voice parameters use the API defaults. `/api/talk/v1/voices` lis
 - `len`: Total frames, including the gap. Default: rounded-up audio duration + `gap`. Does not change speaking speed.
 - `id`, `at`: Identifier and start timing for the generated `<dur>`; see [timing](../../docs/reference/Syntax.md#timing-attributes).
 
-Ruby `｜表示《よみ》` reads `よみ` and keeps `表示` in the timeline. ASCII `|` and `漢字《かんじ》` also work. `<br />` becomes a space; other nested elements are rejected. Use `<seq>` for successive lines and `<stack>` for speech with subtitles. For lip sync, wrap a line in a [portrait's `Talk`](../portrait/README.md).
+Ruby `｜表示《よみ》` reads `よみ` and keeps `表示` in the timeline. ASCII `|` and `漢字《かんじ》` also work. `<br />` becomes a space; other nested elements are rejected. Use `<seq>` for successive lines and `<stack>` for speech with subtitles. For lip sync, wrap a line in a [portrait's `Talk`](../narrator/README.md).
 
 ### Cache and preview
 
@@ -121,3 +121,5 @@ curl --user "$MEKURU_VOISONA_USER" http://localhost:32766/api/talk/v1/voices
 ```
 
 curl prompts for the API password. For HTTP 401, check the email and API password. For connection errors, check the engine and port. On Windows, use [WSL mirrored networking](https://learn.microsoft.com/en-us/windows/wsl/networking#mirrored-mode-networking) to reach the engine through `127.0.0.1`. Set `MEKURU_VOISONA_URL=http://127.0.0.1:32766` if `localhost` fails.
+
+For custom narrators, `await Voisona.prepare({ ...voiceSettings, children })` returns shared audio, display text, and duration. Put `id` and `at` on the components that place it. See [shared audio sources](../speech/README.md#shared-audio-sources) and [composing narrators](../narrator/README.md).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mekuru/voisona",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "The speech component <Voisona> of Mekuru Movie Maker: lines of speech read by VoiSona Talk, through its REST API",
   "type": "module",
   "exports": {
@@ -11,13 +11,14 @@
   ],
   "sideEffects": false,
   "peerDependencies": {
-    "@mekuru/core": "^0.1.2"
+    "@mekuru/core": "^0.1.3"
   },
   "devDependencies": {
-    "@mekuru/core": "0.1.2"
+    "@mekuru/core": "0.1.3"
   },
   "dependencies": {
-    "@mekuru/speech": "^0.1.2"
+    "@mekuru/speech": "^0.1.3",
+    "@mekuru/audio": "^0.1.3"
   },
   "engines": {
     "bun": ">=1.4"

package/src/client.ts

@@ -0,0 +1,180 @@
+import type { SpeechProps } from "@mekuru/speech";
+
+import { httpClient, limit, splitText } from "@mekuru/speech/engine";
+
+import { joinWavs } from "@mekuru/audio/wav";
+
+import type { VoisonaProps } from "./props.ts";
+type VoiceOptions = Omit<VoisonaProps, keyof SpeechProps | "url">;
+
+const DEFAULT_URL = "http://localhost:32766";
+const API = "/api/talk/v1";
+const TIMEOUT = 300_000;
+
+interface Voice {
+  voice_name: string;
+  voice_version: string;
+  languages: string[];
+  display_names?: { language: string; name: string }[];
+}
+
+interface VoiceDetail {
+  style_names?: string[];
+  default_style_weights?: number[];
+}
+
+interface Synthesis {
+  state: "queued" | "running" | "succeeded" | "failed";
+}
+
+const HELP =
+  "  - start VoiSona Talk (1.3.7 or later), sign in, and turn on 「REST APIを有効にする」 in the API tab of its preferences\n" +
+  "  - it listens on port 32766; if it is elsewhere (WSL2 without mirrored networking), set `url` on `<Voisona>`\n" +
+  "    or the MEKURU_VOISONA_URL environment variable";
+
+const CREDENTIALS =
+  "VoiSona Talk needs the email you sign in with and the API password (set in the API tab of its preferences):\n" +
+  "  set the MEKURU_VOISONA_USER and MEKURU_VOISONA_PASSWORD environment variables";
+
+const names = (v: Voice): string[] => [v.voice_name, ...(v.display_names ?? []).map((d) => d.name)];
+
+const newer = (a: string, b: string): number => {
+  const x = a.split(".").map(Number);
+  const y = b.split(".").map(Number);
+  for (let i = 0; i < Math.max(x.length, y.length); i++) {
+    const d = (y[i] ?? 0) - (x[i] ?? 0);
+    if (d) return d;
+  }
+  return 0;
+};
+
+class Server {
+  private readonly limited = limit(1);
+
+  private readonly raw: ReturnType<typeof httpClient>;
+
+  private voices?: Promise<Voice[]>;
+
+  private readonly details = new Map<string, Promise<VoiceDetail>>();
+
+  constructor(url: string) {
+    this.raw = httpClient(url, "VoiSona Talk", HELP);
+  }
+
+  private async call(path: string, init: RequestInit = {}): Promise<Response> {
+    const user = process.env.MEKURU_VOISONA_USER;
+    const password = process.env.MEKURU_VOISONA_PASSWORD;
+    if (!user || !password) throw new Error(CREDENTIALS);
+    const headers = new Headers(init.headers);
+    headers.set("Authorization", `Basic ${Buffer.from(`${user}:${password}`).toString("base64")}`);
+    try {
+      return await this.raw(API + path, { ...init, headers });
+    } catch (e) {
+      const message = e instanceof Error ? e.message : String(e);
+      throw /: HTTP 401\b/.test(message) ? new Error(`${message}\n${CREDENTIALS}`) : e;
+    }
+  }
+
+  private async voice(props: VoiceOptions): Promise<{ voice: Voice; language: string }> {
+    this.voices ??= this.call("/voices")
+      .then(async (res) => ((await res.json()) as { items: Voice[] }).items)
+      .catch((e: unknown) => {
+        this.voices = undefined;
+        throw e;
+      });
+    const all = await this.voices;
+    const found = all.filter((v) => names(v).includes(props.voice)).sort((a, b) => newer(a.voice_version, b.voice_version));
+    if (found.length === 0) {
+      const have = [...new Set(all.map((v) => `${v.voice_name} (${names(v).slice(1).join(", ")})`))];
+      throw new Error(`VoiSona Talk has no voice \`${props.voice}\` (it has ${have.join(", ") || "none"}; download voices in the app)`);
+    }
+    if (new Set(found.map((v) => v.voice_name)).size > 1) {
+      throw new Error(`VoiSona Talk has several voices named \`${props.voice}\`: write one of ${[...new Set(found.map((v) => v.voice_name))].join(", ")}`);
+    }
+    const voice = props.version === undefined ? found[0] : found.find((v) => v.voice_version === props.version);
+    if (!voice) throw new Error(`VoiSona Talk has no version ${props.version} of \`${props.voice}\` (it has ${found.map((v) => v.voice_version).join(", ")})`);
+    const language = props.language ?? voice.languages[0];
+    if (!voice.languages.includes(language)) {
+      throw new Error(`the VoiSona Talk voice \`${props.voice}\` does not speak ${language} (it speaks ${voice.languages.join(", ")})`);
+    }
+    return { voice, language };
+  }
+
+  private async styleWeights(voice: Voice, style: Readonly<Record<string, number>>): Promise<number[]> {
+    const key = `${voice.voice_name}/${voice.voice_version}`;
+    let detail = this.details.get(key);
+    if (!detail) {
+      detail = this.call(`/voices/${encodeURIComponent(voice.voice_name)}/${encodeURIComponent(voice.voice_version)}`).then(
+        async (res) => (await res.json()) as VoiceDetail,
+      );
+      detail.catch(() => this.details.delete(key));
+      this.details.set(key, detail);
+    }
+    const { style_names: styles = [], default_style_weights: defaults = [] } = await detail;
+    const weights = styles.map((_, i) => defaults[i] ?? 0);
+    for (const [name, weight] of Object.entries(style)) {
+      const i = styles.indexOf(name);
+      if (i < 0) throw new Error(`the VoiSona Talk voice \`${voice.voice_name}\` has no style \`${name}\` (it has ${styles.join(", ") || "none"})`);
+      weights[i] = weight;
+    }
+    return weights;
+  }
+
+  private async speak(body: object, text: string): Promise<Buffer> {
+    const res = await this.call("/speech-syntheses", {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ ...body, text }),
+    });
+    const { uuid } = (await res.json()) as { uuid: string };
+    try {
+      const until = Date.now() + TIMEOUT;
+      for (;;) {
+        const { state } = (await (await this.call(`/speech-syntheses/${uuid}`)).json()) as Synthesis;
+        if (state === "succeeded") break;
+        if (state === "failed") throw new Error(`VoiSona Talk could not read: ${text.slice(0, 40)}`);
+        if (Date.now() > until) throw new Error(`VoiSona Talk did not finish in ${TIMEOUT / 1000}s: ${text.slice(0, 40)}`);
+        await Bun.sleep(100);
+      }
+      return Buffer.from(await (await this.call(`/speech-syntheses/${uuid}/wav`)).arrayBuffer());
+    } finally {
+      await this.call(`/speech-syntheses/${uuid}`, { method: "DELETE" }).catch(() => {});
+    }
+  }
+
+  private async write(props: VoiceOptions, text: string, out: string): Promise<void> {
+    const { voice, language } = await this.voice(props);
+    const global: Record<string, number | number[]> = {};
+    for (const key of ["speed", "pitch", "volume", "alp", "huskiness", "intonation"] as const) {
+      const value = props[key];
+      if (value !== undefined) global[key] = value;
+    }
+    if (props.style) global.style_weights = await this.styleWeights(voice, props.style);
+    const body = {
+      language,
+      voice_name: voice.voice_name,
+      voice_version: voice.voice_version,
+      global_parameters: global,
+      destination: "memory",
+      force_enqueue: true,
+    };
+    const wavs: Buffer[] = [];
+    for (const part of splitText(text, props["max-chars"] ?? 500)) wavs.push(await this.speak(body, part));
+    await Bun.write(out, wavs.length === 1 ? wavs[0] : joinWavs(wavs));
+  }
+
+  synthesize(props: VoiceOptions, text: string, out: string): Promise<void> {
+    return this.limited(() => this.write(props, text, out));
+  }
+}
+
+const servers = new Map<string, Server>();
+
+export const server = (url: string | undefined): Server => {
+  const at = (url ?? process.env.MEKURU_VOISONA_URL ?? DEFAULT_URL).replace(/\/+$/, "");
+  const found = servers.get(at);
+  if (found) return found;
+  const created = new Server(at);
+  servers.set(at, created);
+  return created;
+};

package/src/index.tsx

@@ -1,197 +1,12 @@
-import type { JSX } from "@mekuru/core";
-import { httpClient, limit, splitText } from "@mekuru/speech/engine";
-import { joinWavs, line, voiceOf, type SpeechProps } from "@mekuru/speech";
-
-const DEFAULT_URL = "http://localhost:32766";
-const API = "/api/talk/v1";
-const TIMEOUT = 300_000;
-
-export interface VoisonaProps extends SpeechProps {
-  voice: string;
-  version?: string;
-  language?: string;
-  speed?: number;
-  pitch?: number;
-  volume?: number;
-  alp?: number;
-  huskiness?: number;
-  intonation?: number;
-  style?: Readonly<Record<string, number>>;
-  "max-chars"?: number;
-  url?: string;
-}
-
-interface Voice {
-  voice_name: string;
-  voice_version: string;
-  languages: string[];
-  display_names?: { language: string; name: string }[];
-}
-
-interface VoiceDetail {
-  style_names?: string[];
-  default_style_weights?: number[];
-}
-
-interface Synthesis {
-  state: "queued" | "running" | "succeeded" | "failed";
-}
-
-const HELP =
-  "  - start VoiSona Talk (1.3.7 or later), sign in, and turn on 「REST APIを有効にする」 in the API tab of its preferences\n" +
-  "  - it listens on port 32766; if it is elsewhere (WSL2 without mirrored networking), set `url` on `<Voisona>`\n" +
-  "    or the MEKURU_VOISONA_URL environment variable";
-
-const CREDENTIALS =
-  "VoiSona Talk needs the email you sign in with and the API password (set in the API tab of its preferences):\n" +
-  "  set the MEKURU_VOISONA_USER and MEKURU_VOISONA_PASSWORD environment variables";
-
-const names = (v: Voice): string[] => [v.voice_name, ...(v.display_names ?? []).map((d) => d.name)];
-
-const newer = (a: string, b: string): number => {
-  const x = a.split(".").map(Number);
-  const y = b.split(".").map(Number);
-  for (let i = 0; i < Math.max(x.length, y.length); i++) {
-    const d = (y[i] ?? 0) - (x[i] ?? 0);
-    if (d) return d;
-  }
-  return 0;
-};
-
-class Server {
-  private readonly limited = limit(1);
-
-  private readonly raw: ReturnType<typeof httpClient>;
-
-  private voices?: Promise<Voice[]>;
-
-  private readonly details = new Map<string, Promise<VoiceDetail>>();
-
-  constructor(url: string) {
-    this.raw = httpClient(url, "VoiSona Talk", HELP);
-  }
-
-  private async call(path: string, init: RequestInit = {}): Promise<Response> {
-    const user = process.env.MEKURU_VOISONA_USER;
-    const password = process.env.MEKURU_VOISONA_PASSWORD;
-    if (!user || !password) throw new Error(CREDENTIALS);
-    const headers = new Headers(init.headers);
-    headers.set("Authorization", `Basic ${Buffer.from(`${user}:${password}`).toString("base64")}`);
-    try {
-      return await this.raw(API + path, { ...init, headers });
-    } catch (e) {
-      const message = e instanceof Error ? e.message : String(e);
-      throw /: HTTP 401\b/.test(message) ? new Error(`${message}\n${CREDENTIALS}`) : e;
-    }
-  }
-
-  private async voice(props: VoisonaProps): Promise<{ voice: Voice; language: string }> {
-    this.voices ??= this.call("/voices")
-      .then(async (res) => ((await res.json()) as { items: Voice[] }).items)
-      .catch((e: unknown) => {
-        this.voices = undefined;
-        throw e;
-      });
-    const all = await this.voices;
-    const found = all.filter((v) => names(v).includes(props.voice)).sort((a, b) => newer(a.voice_version, b.voice_version));
-    if (found.length === 0) {
-      const have = [...new Set(all.map((v) => `${v.voice_name} (${names(v).slice(1).join(", ")})`))];
-      throw new Error(`VoiSona Talk has no voice \`${props.voice}\` (it has ${have.join(", ") || "none"}; download voices in the app)`);
-    }
-    if (new Set(found.map((v) => v.voice_name)).size > 1) {
-      throw new Error(`VoiSona Talk has several voices named \`${props.voice}\`: write one of ${[...new Set(found.map((v) => v.voice_name))].join(", ")}`);
-    }
-    const voice = props.version === undefined ? found[0] : found.find((v) => v.voice_version === props.version);
-    if (!voice) throw new Error(`VoiSona Talk has no version ${props.version} of \`${props.voice}\` (it has ${found.map((v) => v.voice_version).join(", ")})`);
-    const language = props.language ?? voice.languages[0];
-    if (!voice.languages.includes(language)) {
-      throw new Error(`the VoiSona Talk voice \`${props.voice}\` does not speak ${language} (it speaks ${voice.languages.join(", ")})`);
-    }
-    return { voice, language };
-  }
-
-  private async styleWeights(voice: Voice, style: Readonly<Record<string, number>>): Promise<number[]> {
-    const key = `${voice.voice_name}/${voice.voice_version}`;
-    let detail = this.details.get(key);
-    if (!detail) {
-      detail = this.call(`/voices/${encodeURIComponent(voice.voice_name)}/${encodeURIComponent(voice.voice_version)}`).then(
-        async (res) => (await res.json()) as VoiceDetail,
-      );
-      detail.catch(() => this.details.delete(key));
-      this.details.set(key, detail);
-    }
-    const { style_names: styles = [], default_style_weights: defaults = [] } = await detail;
-    const weights = styles.map((_, i) => defaults[i] ?? 0);
-    for (const [name, weight] of Object.entries(style)) {
-      const i = styles.indexOf(name);
-      if (i < 0) throw new Error(`the VoiSona Talk voice \`${voice.voice_name}\` has no style \`${name}\` (it has ${styles.join(", ") || "none"})`);
-      weights[i] = weight;
-    }
-    return weights;
-  }
-
-  private async speak(body: object, text: string): Promise<Buffer> {
-    const res = await this.call("/speech-syntheses", {
-      method: "POST",
-      headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({ ...body, text }),
-    });
-    const { uuid } = (await res.json()) as { uuid: string };
-    try {
-      const until = Date.now() + TIMEOUT;
-      for (;;) {
-        const { state } = (await (await this.call(`/speech-syntheses/${uuid}`)).json()) as Synthesis;
-        if (state === "succeeded") break;
-        if (state === "failed") throw new Error(`VoiSona Talk could not read: ${text.slice(0, 40)}`);
-        if (Date.now() > until) throw new Error(`VoiSona Talk did not finish in ${TIMEOUT / 1000}s: ${text.slice(0, 40)}`);
-        await Bun.sleep(100);
-      }
-      return Buffer.from(await (await this.call(`/speech-syntheses/${uuid}/wav`)).arrayBuffer());
-    } finally {
-      await this.call(`/speech-syntheses/${uuid}`, { method: "DELETE" }).catch(() => {});
-    }
-  }
-
-  private async write(props: VoisonaProps, text: string, out: string): Promise<void> {
-    const { voice, language } = await this.voice(props);
-    const global: Record<string, number | number[]> = {};
-    for (const key of ["speed", "pitch", "volume", "alp", "huskiness", "intonation"] as const) {
-      const value = props[key];
-      if (value !== undefined) global[key] = value;
-    }
-    if (props.style) global.style_weights = await this.styleWeights(voice, props.style);
-    const body = {
-      language,
-      voice_name: voice.voice_name,
-      voice_version: voice.voice_version,
-      global_parameters: global,
-      destination: "memory",
-      force_enqueue: true,
-    };
-    const wavs: Buffer[] = [];
-    for (const part of splitText(text, props["max-chars"] ?? 500)) wavs.push(await this.speak(body, part));
-    await Bun.write(out, wavs.length === 1 ? wavs[0] : joinWavs(wavs));
-  }
-
-  synthesize(props: VoisonaProps, text: string, out: string): Promise<void> {
-    return this.limited(() => this.write(props, text, out));
-  }
-}
-
-const servers = new Map<string, Server>();
-
-const server = (url: string | undefined): Server => {
-  const at = (url ?? process.env.MEKURU_VOISONA_URL ?? DEFAULT_URL).replace(/\/+$/, "");
-  const found = servers.get(at);
-  if (found) return found;
-  const created = new Server(at);
-  servers.set(at, created);
-  return created;
-};
-
-export const Voisona = async (props: VoisonaProps): Promise<Awaited<JSX.Element>> => {
+import { defineSpeech, prepare, voiceOf } from "@mekuru/speech";
+import { server } from "./client.ts";
+import type { VoisonaProps } from "./props.ts";
+export type { VoisonaProps } from "./props.ts";
+const prepareLine = async (props: Omit<VoisonaProps, "id" | "at">) => {
   const { url, ...voice } = voiceOf(props);
-  return line("voisona", props, props.voice, voice, (say, out) => server(url).synthesize(props, say, out));
+  return prepare("voisona", props, props.voice, voice, (say, out) => server(url).synthesize(voice, say, out));
 };
 
+export const Voisona = defineSpeech<VoisonaProps>(prepareLine);
+
 export * from "./characters.ts";

package/src/props.ts

@@ -0,0 +1,15 @@
+import type { SpeechProps } from "@mekuru/speech";
+export interface VoisonaProps extends SpeechProps {
+  voice: string;
+  version?: string;
+  language?: string;
+  speed?: number;
+  pitch?: number;
+  volume?: number;
+  alp?: number;
+  huskiness?: number;
+  intonation?: number;
+  style?: Readonly<Record<string, number>>;
+  "max-chars"?: number;
+  url?: string;
+}