ssml-builder-js 2.7.0 → 2.8.1

package/dist/index.mjs

@@ -3,12 +3,13 @@ import {
   buildPartialSsml,
   buildSsml,
   extractSsmlText,
+  isValidAzureAudioDuration,
   mapSsmlTextNodes,
   normalizeAzureLanguage,
   parseSsml,
   validateAzureSsml,
   validateSsml
-} from "./chunk-D6ITDU3A.mjs";
+} from "./chunk-VCDMKVVT.mjs";
 import {
   __privateAdd,
   __privateGet,
@@ -204,6 +205,7 @@ export {
   buildPartialSsml,
   buildSsml,
   extractSsmlText,
+  isValidAzureAudioDuration,
   mapSsmlTextNodes,
   normalizeAzureLanguage,
   parseSsml,

package/dist/index.mjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../packages/azure-tts-client/src/errors.ts","../packages/azure-tts-client/src/synthesis.ts","../packages/azure-tts-client/src/speechConfig.ts","../packages/azure-tts-client/src/outputFormats.ts","../packages/azure-tts-client/src/client.ts"],"sourcesContent":["export class AzureTtsError extends Error {\n  readonly status: number;\n  readonly statusText: string;\n  readonly responseBody: string;\n  readonly requestId: string | null;\n\n  constructor(status: number, statusText: string, responseBody: string, requestId: string | null) {\n    super(`Azure TTS request failed: ${status} ${statusText}`);\n    this.name = \"AzureTtsError\";\n    this.status = status;\n    this.statusText = statusText;\n    this.responseBody = responseBody;\n    this.requestId = requestId;\n  }\n}\n\nexport class AzureTtsSdkError extends AzureTtsError {\n  readonly errorDetails: string;\n\n  constructor(errorDetails: string) {\n    super(0, \"Speech SDK\", errorDetails, null);\n    this.name = \"AzureTtsSdkError\";\n    this.message = `Azure TTS synthesis failed: ${errorDetails}`;\n    this.errorDetails = errorDetails;\n  }\n}\n\nexport function createSpeechSdkError(error: unknown): AzureTtsSdkError {\n  const message = error instanceof Error ? error.message : String(error);\n  return new AzureTtsSdkError(message);\n}\n","import * as SpeechSDK from \"microsoft-cognitiveservices-speech-sdk\";\nimport { createSpeechSdkError } from \"./errors.ts\";\nimport { createSpeechConfig } from \"./speechConfig.ts\";\nimport type { TtsConfig } from \"./types.ts\";\n\nfunction closeSpeechResources(speechConfig: SpeechSDK.SpeechConfig, synthesizer: SpeechSDK.SpeechSynthesizer): void {\n  try {\n    synthesizer.close();\n  } catch {}\n\n  try {\n    speechConfig.close();\n  } catch {}\n}\n\nexport async function synthesizeSpeech(ssml: string, config: TtsConfig): Promise<ArrayBuffer> {\n  if (config.signal?.aborted) {\n    throw createSpeechSdkError(\"Speech synthesis was cancelled.\");\n  }\n\n  const speechConfig = createSpeechConfig(config);\n  const synthesizer = new SpeechSDK.SpeechSynthesizer(speechConfig, null);\n\n  return await new Promise<ArrayBuffer>((resolve, reject) => {\n    let resourcesClosed = false;\n    let settled = false;\n    let timeout: ReturnType<typeof setTimeout> | undefined;\n    let abortHandler: (() => void) | undefined;\n    const cleanup = () => {\n      if (timeout) clearTimeout(timeout);\n      if (abortHandler) config.signal?.removeEventListener(\"abort\", abortHandler);\n    };\n    const closeResources = () => {\n      if (resourcesClosed) return;\n      resourcesClosed = true;\n      closeSpeechResources(speechConfig, synthesizer);\n    };\n    const rejectWithError = (error: unknown) => {\n      if (settled) return;\n      settled = true;\n      cleanup();\n      closeResources();\n      reject(createSpeechSdkError(error));\n    };\n\n    const cb = (result: SpeechSDK.SpeechSynthesisResult) => {\n      if (settled) return;\n      const { reason, errorDetails } = result;\n      if (reason !== SpeechSDK.ResultReason.SynthesizingAudioCompleted) {\n        const err = errorDetails || `Speech synthesis failed with reason ${reason}.`;\n        rejectWithError(err);\n        return;\n      }\n      settled = true;\n      cleanup();\n      closeResources();\n      resolve(result.audioData);\n    };\n\n    try {\n      if (config.signal) {\n        abortHandler = () => rejectWithError(\"Speech synthesis was cancelled.\");\n        config.signal.addEventListener(\"abort\", abortHandler, { once: true });\n      }\n      if (config.timeoutMs !== undefined && config.timeoutMs > 0) {\n        timeout = setTimeout(\n          () => rejectWithError(`Speech synthesis timed out after ${config.timeoutMs} ms.`),\n          config.timeoutMs,\n        );\n      }\n      synthesizer.speakSsmlAsync(ssml, cb, rejectWithError);\n    } catch (error) {\n      rejectWithError(error);\n    }\n  });\n}\n","import { SpeechConfig } from \"microsoft-cognitiveservices-speech-sdk\";\nimport { DEFAULT_OUTPUT_FORMAT, resolveOutputFormat } from \"./outputFormats.ts\";\nimport type { TtsConfig } from \"./types.ts\";\n\nexport function resolveEndpoint(config: TtsConfig): string {\n  const endpoint = config.endpoint?.trim() || \"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1\";\n  return endpoint.replace(/\\{region\\}/g, encodeURIComponent(config.region));\n}\n\nexport function createSpeechConfig(config: TtsConfig): SpeechConfig {\n  const { outputFormat = DEFAULT_OUTPUT_FORMAT, subscriptionKey } = config;\n\n  const endpoint = new URL(resolveEndpoint(config));\n  const speechConfig = SpeechConfig.fromEndpoint(endpoint, subscriptionKey);\n  speechConfig.speechSynthesisOutputFormat = resolveOutputFormat(outputFormat);\n  return speechConfig;\n}\n","import * as SpeechSDK from \"microsoft-cognitiveservices-speech-sdk\";\n\nexport const DEFAULT_OUTPUT_FORMAT = \"audio-16khz-128kbitrate-mono-mp3\";\n\nconst OUTPUT_FORMATS: Record<string, SpeechSDK.SpeechSynthesisOutputFormat> = {\n  \"raw-8khz-8bit-mono-mulaw\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz8BitMonoMULaw,\n  \"riff-16khz-16kbps-mono-siren\": SpeechSDK.SpeechSynthesisOutputFormat.Riff16Khz16KbpsMonoSiren,\n  \"audio-16khz-16kbps-mono-siren\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz16KbpsMonoSiren,\n  \"audio-16khz-32kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3,\n  \"audio-16khz-128kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz128KBitRateMonoMp3,\n  \"audio-16khz-64kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz64KBitRateMonoMp3,\n  \"audio-24khz-48kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz48KBitRateMonoMp3,\n  \"audio-24khz-96kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz96KBitRateMonoMp3,\n  \"audio-24khz-160kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3,\n  \"raw-16khz-16bit-mono-truesilk\": SpeechSDK.SpeechSynthesisOutputFormat.Raw16Khz16BitMonoTrueSilk,\n  \"riff-16khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff16Khz16BitMonoPcm,\n  \"riff-8khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz16BitMonoPcm,\n  \"riff-24khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff24Khz16BitMonoPcm,\n  \"riff-8khz-8bit-mono-mulaw\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz8BitMonoMULaw,\n  \"raw-16khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw16Khz16BitMonoPcm,\n  \"raw-24khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw24Khz16BitMonoPcm,\n  \"raw-8khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz16BitMonoPcm,\n  \"ogg-16khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg16Khz16BitMonoOpus,\n  \"ogg-24khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg24Khz16BitMonoOpus,\n  \"raw-48khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw48Khz16BitMonoPcm,\n  \"riff-48khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff48Khz16BitMonoPcm,\n  \"audio-48khz-96kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio48Khz96KBitRateMonoMp3,\n  \"audio-48khz-192kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio48Khz192KBitRateMonoMp3,\n  \"ogg-48khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg48Khz16BitMonoOpus,\n  \"webm-16khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm16Khz16BitMonoOpus,\n  \"webm-24khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm24Khz16BitMonoOpus,\n  \"webm-24khz-16bit-24kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm24Khz16Bit24KbpsMonoOpus,\n  \"raw-24khz-16bit-mono-truesilk\": SpeechSDK.SpeechSynthesisOutputFormat.Raw24Khz16BitMonoTrueSilk,\n  \"raw-8khz-8bit-mono-alaw\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz8BitMonoALaw,\n  \"riff-8khz-8bit-mono-alaw\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz8BitMonoALaw,\n  \"audio-16khz-16bit-32kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz16Bit32KbpsMonoOpus,\n  \"audio-24khz-16bit-48kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz16Bit48KbpsMonoOpus,\n  \"audio-24khz-16bit-24kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz16Bit24KbpsMonoOpus,\n  \"raw-22050hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw22050Hz16BitMonoPcm,\n  \"riff-22050hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff22050Hz16BitMonoPcm,\n  \"raw-44100hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw44100Hz16BitMonoPcm,\n  \"riff-44100hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff44100Hz16BitMonoPcm,\n  \"amr-wb-16000hz\": SpeechSDK.SpeechSynthesisOutputFormat.AmrWb16000Hz,\n  \"g722-16khz-64kbps\": SpeechSDK.SpeechSynthesisOutputFormat.G72216Khz64Kbps,\n};\n\nexport function resolveOutputFormat(outputFormat: string): SpeechSDK.SpeechSynthesisOutputFormat {\n  const resolvedFormat = OUTPUT_FORMATS[outputFormat];\n  if (resolvedFormat === undefined) {\n    throw new Error(`Unsupported Azure Speech output format: ${outputFormat}`);\n  }\n\n  return resolvedFormat;\n}\n","import { synthesizeSpeech } from \"./synthesis.ts\";\nimport type { AzureTtsClientOptions } from \"./types.ts\";\n\nconst ENDPOINT_TEMPLATE = \"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1\";\n\nexport class AzureTtsClient {\n  readonly #options: AzureTtsClientOptions;\n\n  constructor(options: AzureTtsClientOptions) {\n    this.#options = options;\n  }\n\n  async synthesize(ssml: string): Promise<ArrayBuffer> {\n    const { region, subscriptionKey, outputFormat, signal, timeoutMs } = this.#options;\n    const endpoint = this.#options.endpoint?.trim() || ENDPOINT_TEMPLATE.replace(\"{region}\", region);\n    this.#options.logger?.debug?.(\"Using Azure TTS endpoint:\", endpoint);\n\n    const config = { endpoint, region, subscriptionKey, outputFormat, signal, timeoutMs };\n    return synthesizeSpeech(ssml, config);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;AAAO,IAAM,gBAAN,cAA4B,MAAM;AAAA,EAMvC,YAAY,QAAgB,YAAoB,cAAsB,WAA0B;AAC9F,UAAM,6BAA6B,MAAM,IAAI,UAAU,EAAE;AACzD,SAAK,OAAO;AACZ,SAAK,SAAS;AACd,SAAK,aAAa;AAClB,SAAK,eAAe;AACpB,SAAK,YAAY;AAAA,EACnB;AACF;AAEO,IAAM,mBAAN,cAA+B,cAAc;AAAA,EAGlD,YAAY,cAAsB;AAChC,UAAM,GAAG,cAAc,cAAc,IAAI;AACzC,SAAK,OAAO;AACZ,SAAK,UAAU,+BAA+B,YAAY;AAC1D,SAAK,eAAe;AAAA,EACtB;AACF;AAEO,SAAS,qBAAqB,OAAkC;AACrE,QAAM,UAAU,iBAAiB,QAAQ,MAAM,UAAU,OAAO,KAAK;AACrE,SAAO,IAAI,iBAAiB,OAAO;AACrC;;;AC9BA,YAAYA,gBAAe;;;ACA3B,SAAS,oBAAoB;;;ACA7B,YAAY,eAAe;AAEpB,IAAM,wBAAwB;AAErC,IAAM,iBAAwE;AAAA,EAC5E,4BAAsC,sCAA4B;AAAA,EAClE,gCAA0C,sCAA4B;AAAA,EACtE,iCAA2C,sCAA4B;AAAA,EACvE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,mCAA6C,sCAA4B;AAAA,EACzE,mCAA6C,sCAA4B;AAAA,EACzE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,iCAA2C,sCAA4B;AAAA,EACvE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,6BAAuC,sCAA4B;AAAA,EACnE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,4BAAsC,sCAA4B;AAAA,EAClE,2BAAqC,sCAA4B;AAAA,EACjE,6BAAuC,sCAA4B;AAAA,EACnE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,6BAAuC,sCAA4B;AAAA,EACnE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,6BAAuC,sCAA4B;AAAA,EACnE,8BAAwC,sCAA4B;AAAA,EACpE,8BAAwC,sCAA4B;AAAA,EACpE,qCAA+C,sCAA4B;AAAA,EAC3E,iCAA2C,sCAA4B;AAAA,EACvE,2BAAqC,sCAA4B;AAAA,EACjE,4BAAsC,sCAA4B;AAAA,EAClE,sCAAgD,sCAA4B;AAAA,EAC5E,sCAAgD,sCAA4B;AAAA,EAC5E,sCAAgD,sCAA4B;AAAA,EAC5E,8BAAwC,sCAA4B;AAAA,EACpE,+BAAyC,sCAA4B;AAAA,EACrE,8BAAwC,sCAA4B;AAAA,EACpE,+BAAyC,sCAA4B;AAAA,EACrE,kBAA4B,sCAA4B;AAAA,EACxD,qBAA+B,sCAA4B;AAC7D;AAEO,SAAS,oBAAoB,cAA6D;AAC/F,QAAM,iBAAiB,eAAe,YAAY;AAClD,MAAI,mBAAmB,QAAW;AAChC,UAAM,IAAI,MAAM,2CAA2C,YAAY,EAAE;AAAA,EAC3E;AAEA,SAAO;AACT;;;ADjDO,SAAS,gBAAgB,QAA2B;AACzD,QAAM,WAAW,OAAO,UAAU,KAAK,KAAK;AAC5C,SAAO,SAAS,QAAQ,eAAe,mBAAmB,OAAO,MAAM,CAAC;AAC1E;AAEO,SAAS,mBAAmB,QAAiC;AAClE,QAAM,EAAE,eAAe,uBAAuB,gBAAgB,IAAI;AAElE,QAAM,WAAW,IAAI,IAAI,gBAAgB,MAAM,CAAC;AAChD,QAAM,eAAe,aAAa,aAAa,UAAU,eAAe;AACxE,eAAa,8BAA8B,oBAAoB,YAAY;AAC3E,SAAO;AACT;;;ADXA,SAAS,qBAAqB,cAAsC,aAAgD;AAClH,MAAI;AACF,gBAAY,MAAM;AAAA,EACpB,QAAQ;AAAA,EAAC;AAET,MAAI;AACF,iBAAa,MAAM;AAAA,EACrB,QAAQ;AAAA,EAAC;AACX;AAEA,eAAsB,iBAAiB,MAAc,QAAyC;AAC5F,MAAI,OAAO,QAAQ,SAAS;AAC1B,UAAM,qBAAqB,iCAAiC;AAAA,EAC9D;AAEA,QAAM,eAAe,mBAAmB,MAAM;AAC9C,QAAM,cAAc,IAAc,6BAAkB,cAAc,IAAI;AAEtE,SAAO,MAAM,IAAI,QAAqB,CAAC,SAAS,WAAW;AACzD,QAAI,kBAAkB;AACtB,QAAI,UAAU;AACd,QAAI;AACJ,QAAI;AACJ,UAAM,UAAU,MAAM;AACpB,UAAI,QAAS,cAAa,OAAO;AACjC,UAAI,aAAc,QAAO,QAAQ,oBAAoB,SAAS,YAAY;AAAA,IAC5E;AACA,UAAM,iBAAiB,MAAM;AAC3B,UAAI,gBAAiB;AACrB,wBAAkB;AAClB,2BAAqB,cAAc,WAAW;AAAA,IAChD;AACA,UAAM,kBAAkB,CAAC,UAAmB;AAC1C,UAAI,QAAS;AACb,gBAAU;AACV,cAAQ;AACR,qBAAe;AACf,aAAO,qBAAqB,KAAK,CAAC;AAAA,IACpC;AAEA,UAAM,KAAK,CAAC,WAA4C;AACtD,UAAI,QAAS;AACb,YAAM,EAAE,QAAQ,aAAa,IAAI;AACjC,UAAI,WAAqB,wBAAa,4BAA4B;AAChE,cAAM,MAAM,gBAAgB,uCAAuC,MAAM;AACzE,wBAAgB,GAAG;AACnB;AAAA,MACF;AACA,gBAAU;AACV,cAAQ;AACR,qBAAe;AACf,cAAQ,OAAO,SAAS;AAAA,IAC1B;AAEA,QAAI;AACF,UAAI,OAAO,QAAQ;AACjB,uBAAe,MAAM,gBAAgB,iCAAiC;AACtE,eAAO,OAAO,iBAAiB,SAAS,cAAc,EAAE,MAAM,KAAK,CAAC;AAAA,MACtE;AACA,UAAI,OAAO,cAAc,UAAa,OAAO,YAAY,GAAG;AAC1D,kBAAU;AAAA,UACR,MAAM,gBAAgB,oCAAoC,OAAO,SAAS,MAAM;AAAA,UAChF,OAAO;AAAA,QACT;AAAA,MACF;AACA,kBAAY,eAAe,MAAM,IAAI,eAAe;AAAA,IACtD,SAAS,OAAO;AACd,sBAAgB,KAAK;AAAA,IACvB;AAAA,EACF,CAAC;AACH;;;AGxEA,IAAM,oBAAoB;AAH1B;AAKO,IAAM,iBAAN,MAAqB;AAAA,EAG1B,YAAY,SAAgC;AAF5C,uBAAS;AAGP,uBAAK,UAAW;AAAA,EAClB;AAAA,EAEA,MAAM,WAAW,MAAoC;AACnD,UAAM,EAAE,QAAQ,iBAAiB,cAAc,QAAQ,UAAU,IAAI,mBAAK;AAC1E,UAAM,WAAW,mBAAK,UAAS,UAAU,KAAK,KAAK,kBAAkB,QAAQ,YAAY,MAAM;AAC/F,uBAAK,UAAS,QAAQ,QAAQ,6BAA6B,QAAQ;AAEnE,UAAM,SAAS,EAAE,UAAU,QAAQ,iBAAiB,cAAc,QAAQ,UAAU;AACpF,WAAO,iBAAiB,MAAM,MAAM;AAAA,EACtC;AACF;AAdW;","names":["SpeechSDK"]}
+{"version":3,"sources":["../packages/azure-tts-client/src/errors.ts","../packages/azure-tts-client/src/synthesis.ts","../packages/azure-tts-client/src/speechConfig.ts","../packages/azure-tts-client/src/outputFormats.ts","../packages/azure-tts-client/src/client.ts"],"sourcesContent":["export class AzureTtsError extends Error {\n  readonly status: number;\n  readonly statusText: string;\n  readonly responseBody: string;\n  readonly requestId: string | null;\n\n  constructor(status: number, statusText: string, responseBody: string, requestId: string | null) {\n    super(`Azure TTS request failed: ${status} ${statusText}`);\n    this.name = \"AzureTtsError\";\n    this.status = status;\n    this.statusText = statusText;\n    this.responseBody = responseBody;\n    this.requestId = requestId;\n  }\n}\n\nexport class AzureTtsSdkError extends AzureTtsError {\n  readonly errorDetails: string;\n\n  constructor(errorDetails: string) {\n    super(0, \"Speech SDK\", errorDetails, null);\n    this.name = \"AzureTtsSdkError\";\n    this.message = `Azure TTS synthesis failed: ${errorDetails}`;\n    this.errorDetails = errorDetails;\n  }\n}\n\nexport function createSpeechSdkError(error: unknown): AzureTtsSdkError {\n  const message = error instanceof Error ? error.message : String(error);\n  return new AzureTtsSdkError(message);\n}\n","import * as SpeechSDK from \"microsoft-cognitiveservices-speech-sdk\";\nimport { createSpeechSdkError } from \"./errors.ts\";\nimport { createSpeechConfig } from \"./speechConfig.ts\";\nimport type { TtsConfig } from \"./types.ts\";\n\nfunction closeSpeechResources(speechConfig: SpeechSDK.SpeechConfig, synthesizer: SpeechSDK.SpeechSynthesizer): void {\n  try {\n    synthesizer.close();\n  } catch {}\n\n  try {\n    speechConfig.close();\n  } catch {}\n}\n\nexport async function synthesizeSpeech(ssml: string, config: TtsConfig): Promise<ArrayBuffer> {\n  if (config.signal?.aborted) {\n    throw createSpeechSdkError(\"Speech synthesis was cancelled.\");\n  }\n\n  const speechConfig = createSpeechConfig(config);\n  const synthesizer = new SpeechSDK.SpeechSynthesizer(speechConfig, null);\n\n  return await new Promise<ArrayBuffer>((resolve, reject) => {\n    let resourcesClosed = false;\n    let settled = false;\n    let timeout: ReturnType<typeof setTimeout> | undefined;\n    let abortHandler: (() => void) | undefined;\n    const cleanup = () => {\n      if (timeout) clearTimeout(timeout);\n      if (abortHandler) config.signal?.removeEventListener(\"abort\", abortHandler);\n    };\n    const closeResources = () => {\n      if (resourcesClosed) return;\n      resourcesClosed = true;\n      closeSpeechResources(speechConfig, synthesizer);\n    };\n    const rejectWithError = (error: unknown) => {\n      if (settled) return;\n      settled = true;\n      cleanup();\n      closeResources();\n      reject(createSpeechSdkError(error));\n    };\n\n    const cb = (result: SpeechSDK.SpeechSynthesisResult) => {\n      if (settled) return;\n      const { reason, errorDetails } = result;\n      if (reason !== SpeechSDK.ResultReason.SynthesizingAudioCompleted) {\n        const err = errorDetails || `Speech synthesis failed with reason ${reason}.`;\n        rejectWithError(err);\n        return;\n      }\n      settled = true;\n      cleanup();\n      closeResources();\n      resolve(result.audioData);\n    };\n\n    try {\n      if (config.signal) {\n        abortHandler = () => rejectWithError(\"Speech synthesis was cancelled.\");\n        config.signal.addEventListener(\"abort\", abortHandler, { once: true });\n      }\n      if (config.timeoutMs !== undefined && config.timeoutMs > 0) {\n        timeout = setTimeout(\n          () => rejectWithError(`Speech synthesis timed out after ${config.timeoutMs} ms.`),\n          config.timeoutMs,\n        );\n      }\n      synthesizer.speakSsmlAsync(ssml, cb, rejectWithError);\n    } catch (error) {\n      rejectWithError(error);\n    }\n  });\n}\n","import { SpeechConfig } from \"microsoft-cognitiveservices-speech-sdk\";\nimport { DEFAULT_OUTPUT_FORMAT, resolveOutputFormat } from \"./outputFormats.ts\";\nimport type { TtsConfig } from \"./types.ts\";\n\nexport function resolveEndpoint(config: TtsConfig): string {\n  const endpoint = config.endpoint?.trim() || \"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1\";\n  return endpoint.replace(/\\{region\\}/g, encodeURIComponent(config.region));\n}\n\nexport function createSpeechConfig(config: TtsConfig): SpeechConfig {\n  const { outputFormat = DEFAULT_OUTPUT_FORMAT, subscriptionKey } = config;\n\n  const endpoint = new URL(resolveEndpoint(config));\n  const speechConfig = SpeechConfig.fromEndpoint(endpoint, subscriptionKey);\n  speechConfig.speechSynthesisOutputFormat = resolveOutputFormat(outputFormat);\n  return speechConfig;\n}\n","import * as SpeechSDK from \"microsoft-cognitiveservices-speech-sdk\";\n\nexport const DEFAULT_OUTPUT_FORMAT = \"audio-16khz-128kbitrate-mono-mp3\";\n\nconst OUTPUT_FORMATS: Record<string, SpeechSDK.SpeechSynthesisOutputFormat> = {\n  \"raw-8khz-8bit-mono-mulaw\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz8BitMonoMULaw,\n  \"riff-16khz-16kbps-mono-siren\": SpeechSDK.SpeechSynthesisOutputFormat.Riff16Khz16KbpsMonoSiren,\n  \"audio-16khz-16kbps-mono-siren\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz16KbpsMonoSiren,\n  \"audio-16khz-32kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz32KBitRateMonoMp3,\n  \"audio-16khz-128kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz128KBitRateMonoMp3,\n  \"audio-16khz-64kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz64KBitRateMonoMp3,\n  \"audio-24khz-48kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz48KBitRateMonoMp3,\n  \"audio-24khz-96kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz96KBitRateMonoMp3,\n  \"audio-24khz-160kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz160KBitRateMonoMp3,\n  \"raw-16khz-16bit-mono-truesilk\": SpeechSDK.SpeechSynthesisOutputFormat.Raw16Khz16BitMonoTrueSilk,\n  \"riff-16khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff16Khz16BitMonoPcm,\n  \"riff-8khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz16BitMonoPcm,\n  \"riff-24khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff24Khz16BitMonoPcm,\n  \"riff-8khz-8bit-mono-mulaw\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz8BitMonoMULaw,\n  \"raw-16khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw16Khz16BitMonoPcm,\n  \"raw-24khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw24Khz16BitMonoPcm,\n  \"raw-8khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz16BitMonoPcm,\n  \"ogg-16khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg16Khz16BitMonoOpus,\n  \"ogg-24khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg24Khz16BitMonoOpus,\n  \"raw-48khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw48Khz16BitMonoPcm,\n  \"riff-48khz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff48Khz16BitMonoPcm,\n  \"audio-48khz-96kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio48Khz96KBitRateMonoMp3,\n  \"audio-48khz-192kbitrate-mono-mp3\": SpeechSDK.SpeechSynthesisOutputFormat.Audio48Khz192KBitRateMonoMp3,\n  \"ogg-48khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Ogg48Khz16BitMonoOpus,\n  \"webm-16khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm16Khz16BitMonoOpus,\n  \"webm-24khz-16bit-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm24Khz16BitMonoOpus,\n  \"webm-24khz-16bit-24kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Webm24Khz16Bit24KbpsMonoOpus,\n  \"raw-24khz-16bit-mono-truesilk\": SpeechSDK.SpeechSynthesisOutputFormat.Raw24Khz16BitMonoTrueSilk,\n  \"raw-8khz-8bit-mono-alaw\": SpeechSDK.SpeechSynthesisOutputFormat.Raw8Khz8BitMonoALaw,\n  \"riff-8khz-8bit-mono-alaw\": SpeechSDK.SpeechSynthesisOutputFormat.Riff8Khz8BitMonoALaw,\n  \"audio-16khz-16bit-32kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio16Khz16Bit32KbpsMonoOpus,\n  \"audio-24khz-16bit-48kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz16Bit48KbpsMonoOpus,\n  \"audio-24khz-16bit-24kbps-mono-opus\": SpeechSDK.SpeechSynthesisOutputFormat.Audio24Khz16Bit24KbpsMonoOpus,\n  \"raw-22050hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw22050Hz16BitMonoPcm,\n  \"riff-22050hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff22050Hz16BitMonoPcm,\n  \"raw-44100hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Raw44100Hz16BitMonoPcm,\n  \"riff-44100hz-16bit-mono-pcm\": SpeechSDK.SpeechSynthesisOutputFormat.Riff44100Hz16BitMonoPcm,\n  \"amr-wb-16000hz\": SpeechSDK.SpeechSynthesisOutputFormat.AmrWb16000Hz,\n  \"g722-16khz-64kbps\": SpeechSDK.SpeechSynthesisOutputFormat.G72216Khz64Kbps,\n};\n\nexport function resolveOutputFormat(outputFormat: string): SpeechSDK.SpeechSynthesisOutputFormat {\n  const resolvedFormat = OUTPUT_FORMATS[outputFormat];\n  if (resolvedFormat === undefined) {\n    throw new Error(`Unsupported Azure Speech output format: ${outputFormat}`);\n  }\n\n  return resolvedFormat;\n}\n","import { synthesizeSpeech } from \"./synthesis.ts\";\nimport type { AzureTtsClientOptions } from \"./types.ts\";\n\nconst ENDPOINT_TEMPLATE = \"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1\";\n\nexport class AzureTtsClient {\n  readonly #options: AzureTtsClientOptions;\n\n  constructor(options: AzureTtsClientOptions) {\n    this.#options = options;\n  }\n\n  async synthesize(ssml: string): Promise<ArrayBuffer> {\n    const { region, subscriptionKey, outputFormat, signal, timeoutMs } = this.#options;\n    const endpoint = this.#options.endpoint?.trim() || ENDPOINT_TEMPLATE.replace(\"{region}\", region);\n    this.#options.logger?.debug?.(\"Using Azure TTS endpoint:\", endpoint);\n\n    const config = { endpoint, region, subscriptionKey, outputFormat, signal, timeoutMs };\n    return synthesizeSpeech(ssml, config);\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;AAAO,IAAM,gBAAN,cAA4B,MAAM;AAAA,EAMvC,YAAY,QAAgB,YAAoB,cAAsB,WAA0B;AAC9F,UAAM,6BAA6B,MAAM,IAAI,UAAU,EAAE;AACzD,SAAK,OAAO;AACZ,SAAK,SAAS;AACd,SAAK,aAAa;AAClB,SAAK,eAAe;AACpB,SAAK,YAAY;AAAA,EACnB;AACF;AAEO,IAAM,mBAAN,cAA+B,cAAc;AAAA,EAGlD,YAAY,cAAsB;AAChC,UAAM,GAAG,cAAc,cAAc,IAAI;AACzC,SAAK,OAAO;AACZ,SAAK,UAAU,+BAA+B,YAAY;AAC1D,SAAK,eAAe;AAAA,EACtB;AACF;AAEO,SAAS,qBAAqB,OAAkC;AACrE,QAAM,UAAU,iBAAiB,QAAQ,MAAM,UAAU,OAAO,KAAK;AACrE,SAAO,IAAI,iBAAiB,OAAO;AACrC;;;AC9BA,YAAYA,gBAAe;;;ACA3B,SAAS,oBAAoB;;;ACA7B,YAAY,eAAe;AAEpB,IAAM,wBAAwB;AAErC,IAAM,iBAAwE;AAAA,EAC5E,4BAAsC,sCAA4B;AAAA,EAClE,gCAA0C,sCAA4B;AAAA,EACtE,iCAA2C,sCAA4B;AAAA,EACvE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,mCAA6C,sCAA4B;AAAA,EACzE,mCAA6C,sCAA4B;AAAA,EACzE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,iCAA2C,sCAA4B;AAAA,EACvE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,6BAAuC,sCAA4B;AAAA,EACnE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,4BAAsC,sCAA4B;AAAA,EAClE,2BAAqC,sCAA4B;AAAA,EACjE,6BAAuC,sCAA4B;AAAA,EACnE,6BAAuC,sCAA4B;AAAA,EACnE,4BAAsC,sCAA4B;AAAA,EAClE,6BAAuC,sCAA4B;AAAA,EACnE,mCAA6C,sCAA4B;AAAA,EACzE,oCAA8C,sCAA4B;AAAA,EAC1E,6BAAuC,sCAA4B;AAAA,EACnE,8BAAwC,sCAA4B;AAAA,EACpE,8BAAwC,sCAA4B;AAAA,EACpE,qCAA+C,sCAA4B;AAAA,EAC3E,iCAA2C,sCAA4B;AAAA,EACvE,2BAAqC,sCAA4B;AAAA,EACjE,4BAAsC,sCAA4B;AAAA,EAClE,sCAAgD,sCAA4B;AAAA,EAC5E,sCAAgD,sCAA4B;AAAA,EAC5E,sCAAgD,sCAA4B;AAAA,EAC5E,8BAAwC,sCAA4B;AAAA,EACpE,+BAAyC,sCAA4B;AAAA,EACrE,8BAAwC,sCAA4B;AAAA,EACpE,+BAAyC,sCAA4B;AAAA,EACrE,kBAA4B,sCAA4B;AAAA,EACxD,qBAA+B,sCAA4B;AAC7D;AAEO,SAAS,oBAAoB,cAA6D;AAC/F,QAAM,iBAAiB,eAAe,YAAY;AAClD,MAAI,mBAAmB,QAAW;AAChC,UAAM,IAAI,MAAM,2CAA2C,YAAY,EAAE;AAAA,EAC3E;AAEA,SAAO;AACT;;;ADjDO,SAAS,gBAAgB,QAA2B;AACzD,QAAM,WAAW,OAAO,UAAU,KAAK,KAAK;AAC5C,SAAO,SAAS,QAAQ,eAAe,mBAAmB,OAAO,MAAM,CAAC;AAC1E;AAEO,SAAS,mBAAmB,QAAiC;AAClE,QAAM,EAAE,eAAe,uBAAuB,gBAAgB,IAAI;AAElE,QAAM,WAAW,IAAI,IAAI,gBAAgB,MAAM,CAAC;AAChD,QAAM,eAAe,aAAa,aAAa,UAAU,eAAe;AACxE,eAAa,8BAA8B,oBAAoB,YAAY;AAC3E,SAAO;AACT;;;ADXA,SAAS,qBAAqB,cAAsC,aAAgD;AAClH,MAAI;AACF,gBAAY,MAAM;AAAA,EACpB,QAAQ;AAAA,EAAC;AAET,MAAI;AACF,iBAAa,MAAM;AAAA,EACrB,QAAQ;AAAA,EAAC;AACX;AAEA,eAAsB,iBAAiB,MAAc,QAAyC;AAC5F,MAAI,OAAO,QAAQ,SAAS;AAC1B,UAAM,qBAAqB,iCAAiC;AAAA,EAC9D;AAEA,QAAM,eAAe,mBAAmB,MAAM;AAC9C,QAAM,cAAc,IAAc,6BAAkB,cAAc,IAAI;AAEtE,SAAO,MAAM,IAAI,QAAqB,CAAC,SAAS,WAAW;AACzD,QAAI,kBAAkB;AACtB,QAAI,UAAU;AACd,QAAI;AACJ,QAAI;AACJ,UAAM,UAAU,MAAM;AACpB,UAAI,QAAS,cAAa,OAAO;AACjC,UAAI,aAAc,QAAO,QAAQ,oBAAoB,SAAS,YAAY;AAAA,IAC5E;AACA,UAAM,iBAAiB,MAAM;AAC3B,UAAI,gBAAiB;AACrB,wBAAkB;AAClB,2BAAqB,cAAc,WAAW;AAAA,IAChD;AACA,UAAM,kBAAkB,CAAC,UAAmB;AAC1C,UAAI,QAAS;AACb,gBAAU;AACV,cAAQ;AACR,qBAAe;AACf,aAAO,qBAAqB,KAAK,CAAC;AAAA,IACpC;AAEA,UAAM,KAAK,CAAC,WAA4C;AACtD,UAAI,QAAS;AACb,YAAM,EAAE,QAAQ,aAAa,IAAI;AACjC,UAAI,WAAqB,wBAAa,4BAA4B;AAChE,cAAM,MAAM,gBAAgB,uCAAuC,MAAM;AACzE,wBAAgB,GAAG;AACnB;AAAA,MACF;AACA,gBAAU;AACV,cAAQ;AACR,qBAAe;AACf,cAAQ,OAAO,SAAS;AAAA,IAC1B;AAEA,QAAI;AACF,UAAI,OAAO,QAAQ;AACjB,uBAAe,MAAM,gBAAgB,iCAAiC;AACtE,eAAO,OAAO,iBAAiB,SAAS,cAAc,EAAE,MAAM,KAAK,CAAC;AAAA,MACtE;AACA,UAAI,OAAO,cAAc,UAAa,OAAO,YAAY,GAAG;AAC1D,kBAAU;AAAA,UACR,MAAM,gBAAgB,oCAAoC,OAAO,SAAS,MAAM;AAAA,UAChF,OAAO;AAAA,QACT;AAAA,MACF;AACA,kBAAY,eAAe,MAAM,IAAI,eAAe;AAAA,IACtD,SAAS,OAAO;AACd,sBAAgB,KAAK;AAAA,IACvB;AAAA,EACF,CAAC;AACH;;;AGxEA,IAAM,oBAAoB;AAH1B;AAKO,IAAM,iBAAN,MAAqB;AAAA,EAG1B,YAAY,SAAgC;AAF5C,uBAAS;AAGP,uBAAK,UAAW;AAAA,EAClB;AAAA,EAEA,MAAM,WAAW,MAAoC;AACnD,UAAM,EAAE,QAAQ,iBAAiB,cAAc,QAAQ,UAAU,IAAI,mBAAK;AAC1E,UAAM,WAAW,mBAAK,UAAS,UAAU,KAAK,KAAK,kBAAkB,QAAQ,YAAY,MAAM;AAC/F,uBAAK,UAAS,QAAQ,QAAQ,6BAA6B,QAAQ;AAEnE,UAAM,SAAS,EAAE,UAAU,QAAQ,iBAAiB,cAAc,QAAQ,UAAU;AACpF,WAAO,iBAAiB,MAAM,MAAM;AAAA,EACtC;AACF;AAdW;","names":["SpeechSDK"]}

package/dist/react.d.mts

@@ -103,11 +103,15 @@ interface MsttsVisemeElement extends SsmlElementBase {
     typeValue?: string;
     visemeType?: string;
 }
+interface MsttsAudioDurationElement extends SsmlElementBase {
+    type: "mstts:audioduration";
+    value?: SsmlAttributeValue;
+}
 interface CustomElement extends SsmlElementBase {
     type: "custom" | "element";
     name: string;
 }
-type SsmlElement = VoiceElement | ProsodyElement | BreakElement | ExpressAsElement | SayAsElement | PhonemeElement | EmphasisElement | AudioElement | SubElement | LangElement | MarkElement | BookmarkElement | LexiconElement | ParagraphElement | SentenceElement | WordElement | MsttsSilenceElement | MsttsVisemeElement | CustomElement;
+type SsmlElement = VoiceElement | ProsodyElement | BreakElement | ExpressAsElement | SayAsElement | PhonemeElement | EmphasisElement | AudioElement | SubElement | LangElement | MarkElement | BookmarkElement | LexiconElement | ParagraphElement | SentenceElement | WordElement | MsttsSilenceElement | MsttsVisemeElement | MsttsAudioDurationElement | CustomElement;
 interface SsmlDocument {
     type?: "speak";
     version: string;
@@ -118,7 +122,7 @@ interface SsmlDocument {
     attributes?: SsmlAttributes;
 }
 
-type SsmlEditorInsertionButton = "break" | "emphasis" | "rate" | "pitch" | "volume" | "emotion" | "say-as" | "phoneme" | "audio" | "sub" | "lang" | "mark" | "bookmark" | "mstts:silence" | "mstts:viseme" | (string & {});
+type SsmlEditorInsertionButton = "break" | "emphasis" | "rate" | "pitch" | "volume" | "emotion" | "say-as" | "phoneme" | "audio" | "sub" | "lang" | "mark" | "bookmark" | "mstts:silence" | "mstts:audioduration" | "mstts:viseme" | (string & {});
 type SsmlEditorButton = "help" | SsmlEditorInsertionButton | "undo" | "redo" | "clearAll" | "format" | "decorations" | (string & {});
 type SsmlEditorButtonVisibility = Readonly<Partial<Record<string, boolean>>>;
 
@@ -389,8 +393,8 @@ declare function updateTagAttribute(text: string, tagRange: SsmlTagRange, attrib
 
 type SsmlCodeLensAction = {
     type: "attribute";
-    insertionId: "rate" | "pitch" | "break";
-    attributeName: "rate" | "pitch" | "time";
+    insertionId: "rate" | "pitch" | "break" | "mstts:audioduration";
+    attributeName: "rate" | "pitch" | "time" | "value";
     tagRange: SsmlTagRange;
 } | {
     type: "unwrap" | "delete";

package/dist/react.d.ts

@@ -103,11 +103,15 @@ interface MsttsVisemeElement extends SsmlElementBase {
     typeValue?: string;
     visemeType?: string;
 }
+interface MsttsAudioDurationElement extends SsmlElementBase {
+    type: "mstts:audioduration";
+    value?: SsmlAttributeValue;
+}
 interface CustomElement extends SsmlElementBase {
     type: "custom" | "element";
     name: string;
 }
-type SsmlElement = VoiceElement | ProsodyElement | BreakElement | ExpressAsElement | SayAsElement | PhonemeElement | EmphasisElement | AudioElement | SubElement | LangElement | MarkElement | BookmarkElement | LexiconElement | ParagraphElement | SentenceElement | WordElement | MsttsSilenceElement | MsttsVisemeElement | CustomElement;
+type SsmlElement = VoiceElement | ProsodyElement | BreakElement | ExpressAsElement | SayAsElement | PhonemeElement | EmphasisElement | AudioElement | SubElement | LangElement | MarkElement | BookmarkElement | LexiconElement | ParagraphElement | SentenceElement | WordElement | MsttsSilenceElement | MsttsVisemeElement | MsttsAudioDurationElement | CustomElement;
 interface SsmlDocument {
     type?: "speak";
     version: string;
@@ -118,7 +122,7 @@ interface SsmlDocument {
     attributes?: SsmlAttributes;
 }
 
-type SsmlEditorInsertionButton = "break" | "emphasis" | "rate" | "pitch" | "volume" | "emotion" | "say-as" | "phoneme" | "audio" | "sub" | "lang" | "mark" | "bookmark" | "mstts:silence" | "mstts:viseme" | (string & {});
+type SsmlEditorInsertionButton = "break" | "emphasis" | "rate" | "pitch" | "volume" | "emotion" | "say-as" | "phoneme" | "audio" | "sub" | "lang" | "mark" | "bookmark" | "mstts:silence" | "mstts:audioduration" | "mstts:viseme" | (string & {});
 type SsmlEditorButton = "help" | SsmlEditorInsertionButton | "undo" | "redo" | "clearAll" | "format" | "decorations" | (string & {});
 type SsmlEditorButtonVisibility = Readonly<Partial<Record<string, boolean>>>;
 
@@ -389,8 +393,8 @@ declare function updateTagAttribute(text: string, tagRange: SsmlTagRange, attrib
 
 type SsmlCodeLensAction = {
     type: "attribute";
-    insertionId: "rate" | "pitch" | "break";
-    attributeName: "rate" | "pitch" | "time";
+    insertionId: "rate" | "pitch" | "break" | "mstts:audioduration";
+    attributeName: "rate" | "pitch" | "time" | "value";
     tagRange: SsmlTagRange;
 } | {
     type: "unwrap" | "delete";

package/dist/react.js

@@ -54,6 +54,8 @@ function isSsmlEditorButtonVisible(buttonVisibility, button) {
 // packages/ssml-editor-react/src/constants/ssmlPresets.ts
 var ssmlPresets_exports = {};
 __export(ssmlPresets_exports, {
+  AUDIO_DURATION_DESCRIPTIONS: () => AUDIO_DURATION_DESCRIPTIONS,
+  AUDIO_DURATION_PRESETS: () => AUDIO_DURATION_PRESETS,
   BREAK_STRENGTH_PRESETS: () => BREAK_STRENGTH_PRESETS,
   BREAK_TIME_DESCRIPTIONS: () => BREAK_TIME_DESCRIPTIONS,
   BREAK_TIME_PRESETS: () => BREAK_TIME_PRESETS,
@@ -86,6 +88,103 @@ __export(ssmlPresets_exports, {
   getExpressAsStyleCategory: () => getExpressAsStyleCategory,
   resolveExpressAsStyles: () => resolveExpressAsStyles
 });
+
+// packages/ssml-editor-react/src/constants/azureVoiceStyleMap.generated.ts
+var AZURE_VOICE_STYLE_MAP = {
+  "de-DE-ConradNeural": ["cheerful", "sad"],
+  "de-DE-KatjaNeural": ["cheerful", "sad"],
+  "en-US-AndrewNeural": ["empathetic", "relieved"],
+  "en-US-GuyNeural": [
+    "angry",
+    "cheerful",
+    "excited",
+    "friendly",
+    "hopeful",
+    "newscast",
+    "sad",
+    "shouting",
+    "terrified",
+    "unfriendly",
+    "whispering"
+  ],
+  "en-US-JennyMultilingualNeural": [
+    "cheerful",
+    "empathetic",
+    "excited",
+    "friendly",
+    "hopeful",
+    "sad",
+    "shouting",
+    "terrified",
+    "unfriendly",
+    "whispering"
+  ],
+  "en-US-JennyNeural": [
+    "assistant",
+    "chat",
+    "customerservice",
+    "newscast",
+    "cheerful",
+    "empathetic",
+    "excited",
+    "friendly",
+    "hopeful",
+    "sad",
+    "shouting",
+    "terrified",
+    "unfriendly",
+    "whispering"
+  ],
+  "es-ES-ElviraNeural": [],
+  "fil-PH-AngeloNeural": [],
+  "fr-FR-DeniseNeural": ["cheerful", "sad"],
+  "fr-FR-HenriNeural": ["cheerful", "sad"],
+  "id-ID-GadisNeural": [],
+  "it-IT-ElsaNeural": ["cheerful", "sad"],
+  "ja-JP-KeitaNeural": ["chat"],
+  "ja-JP-MayuNeural": ["calm", "cheerful", "sad"],
+  "ja-JP-NanamiNeural": ["chat", "customerservice", "cheerful", "whispering", "sad"],
+  "ko-KR-SunHiNeural": ["cheerful", "sad"],
+  "ms-MY-YasminNeural": [],
+  "pt-BR-FranciscaNeural": ["calm"],
+  "ru-RU-SvetlanaNeural": ["cheerful", "sad", "angry", "disgruntled", "embarrassed", "fearful"],
+  "th-TH-PremwadeeNeural": [],
+  "vi-VN-HoaiMyNeural": [],
+  "zh-CN-XiaoxiaoNeural": [
+    "assistant",
+    "chat",
+    "customerservice",
+    "newscast",
+    "cheerful",
+    "empathetic",
+    "excited",
+    "friendly",
+    "hopeful",
+    "sad",
+    "terrified",
+    "whispering",
+    "poetry-reading",
+    "sports_commentary",
+    "sports_commentary_excited",
+    "story"
+  ],
+  "zh-CN-YunxiNeural": [
+    "narration-relaxed",
+    "embarrassed",
+    "fearful",
+    "sad",
+    "disgruntled",
+    "serious",
+    "angry",
+    "depressed",
+    "chat",
+    "cheerful",
+    "assistant"
+  ],
+  "zh-TW-HsiaoChenNeural": []
+};
+
+// packages/ssml-editor-react/src/constants/ssmlPresets.ts
 var SSML_PRESETS = [
   {
     id: "basic",
@@ -185,7 +284,7 @@ function getExpressAsStyleCategory(style) {
   }
   return "other";
 }
-var VOICE_STYLE_MAP = {
+var LEGACY_VOICE_STYLE_MAP = {
   "ja-JP-MayuNeural": ["calm", "cheerful", "sad"],
   "ja-JP-KeitaNeural": ["chat"],
   "ja-JP-NanamiNeural": ["chat", "customerservice", "cheerful", "whispering", "sad"],
@@ -271,6 +370,7 @@ var VOICE_STYLE_MAP = {
   "de-DE-ConradNeural": ["cheerful", "sad"],
   "ru-RU-SvetlanaNeural": ["cheerful", "sad", "angry", "disgruntled", "embarrassed", "fearful"]
 };
+var VOICE_STYLE_MAP = Object.keys(AZURE_VOICE_STYLE_MAP).length > 0 ? AZURE_VOICE_STYLE_MAP : LEGACY_VOICE_STYLE_MAP;
 var VOICE_STYLE_MAP_BY_NORMALIZED_NAME = new Map(
   Object.entries(VOICE_STYLE_MAP).map(([voiceName, styles]) => [voiceName.toLowerCase(), styles])
 );
@@ -313,6 +413,7 @@ var SAY_AS_PRESETS = [
 ];
 var LANGUAGE_PRESETS = ["ja-JP", "en-US", "de-DE", "fr-FR"];
 var SILENCE_VALUE_PRESETS = ["300ms", "500ms", "1s"];
+var AUDIO_DURATION_PRESETS = ["5s", "10s", "30s"];
 var SILENCE_TYPE_PRESETS = [
   "Leading",
   "Tailing",
@@ -321,6 +422,11 @@ var SILENCE_TYPE_PRESETS = [
   "Semicolon",
   "Enumerationcomma"
 ];
+var AUDIO_DURATION_DESCRIPTIONS = {
+  "5s": { ja: "5\u79D2", en: "5 seconds" },
+  "10s": { ja: "10\u79D2", en: "10 seconds" },
+  "30s": { ja: "30\u79D2", en: "30 seconds" }
+};
 var PHONEME_ALPHABET_PRESETS = ["ipa", "sapi", "ups", "x-sampa"];
 var VISEME_TYPE_PRESETS = ["redlips_front", "FacialExpression"];
 var SSML_ATTRIBUTE_PRESETS = {
@@ -364,6 +470,9 @@ var SSML_ATTRIBUTE_PRESETS = {
     type: SILENCE_TYPE_PRESETS,
     value: SILENCE_VALUE_PRESETS
   },
+  "mstts:audioduration": {
+    value: AUDIO_DURATION_PRESETS
+  },
   silence: {
     type: SILENCE_TYPE_PRESETS,
     value: SILENCE_VALUE_PRESETS
@@ -910,6 +1019,13 @@ var SSML_HOVER_COPY = {
         parameters: {
           type: { title: "type", description: "\u30D3\u30BC\u30FC\u30E0\u30A4\u30D9\u30F3\u30C8\u306E\u5F62\u5F0F\u3002" }
         }
+      },
+      "mstts:audioduration": {
+        title: "\u97F3\u58F0\u9577",
+        description: "\u5408\u6210\u97F3\u58F0\u306E\u76EE\u6A19\u6642\u9593\u3092\u6307\u5B9A\u3057\u307E\u3059\u3002",
+        parameters: {
+          value: { title: "value", description: "\u76EE\u6A19\u6642\u9593\u3002\u4F8B: `10s`\u3001`5000ms`\u3001`00:00:10`\u3002" }
+        }
       }
     }
   },
@@ -1067,6 +1183,13 @@ var SSML_HOVER_COPY = {
         parameters: {
           type: { title: "type", description: "The viseme event format." }
         }
+      },
+      "mstts:audioduration": {
+        title: "Audio duration",
+        description: "Sets the target duration of synthesized audio.",
+        parameters: {
+          value: { title: "value", description: "The target duration, such as `10s`, `5000ms`, or `00:00:10`." }
+        }
       }
     }
   }
@@ -1570,7 +1693,8 @@ var SSML_TAGS = {
   MSTTS_SILENCE: "mstts:silence",
   SILENCE: "silence",
   MSTTS_VISEME: "mstts:viseme",
-  VISEME: "viseme"
+  VISEME: "viseme",
+  MSTTS_AUDIO_DURATION: "mstts:audioduration"
 };
 var SSML_ATTRS = {
   VERSION: "version",
@@ -1697,6 +1821,9 @@ function getAttributes(element) {
     case SSML_TAGS.VISEME:
       addAttribute(attributes, SSML_ATTRS.TYPE, element.typeValue ?? element.visemeType);
       break;
+    case SSML_TAGS.MSTTS_AUDIO_DURATION:
+      addAttribute(attributes, SSML_ATTRS.VALUE, element.value);
+      break;
     case SSML_TAGS.PARAGRAPH:
     case SSML_TAGS.SENTENCE:
     case SSML_TAGS.WORD:
@@ -1721,6 +1848,8 @@ function getTagName(element) {
     case SSML_TAGS.VISEME:
     case SSML_TAGS.MSTTS_VISEME:
       return SSML_TAGS.MSTTS_VISEME;
+    case SSML_TAGS.MSTTS_AUDIO_DURATION:
+      return SSML_TAGS.MSTTS_AUDIO_DURATION;
     case "element":
     case "custom":
       return element.name;
@@ -2253,6 +2382,12 @@ function convertElement(node) {
       if (typeValue !== void 0) element.typeValue = typeValue;
       return finishElement(element, node, attributes);
     }
+    case SSML_TAGS.MSTTS_AUDIO_DURATION: {
+      const element = { type: SSML_TAGS.MSTTS_AUDIO_DURATION };
+      const value = readAttribute(attributes, SSML_ATTRS.VALUE);
+      if (value !== void 0) element.value = value;
+      return finishElement(element, node, attributes);
+    }
     default: {
       const element = {
         name: node.name,
@@ -2433,6 +2568,7 @@ var INTRINSICALLY_EMPTY_ELEMENTS = /* @__PURE__ */ new Set([
   "lexicon",
   "mark",
   "mstts:silence",
+  "mstts:audioduration",
   "mstts:viseme",
   "silence",
   "viseme"
@@ -3278,7 +3414,7 @@ function findSsmlVoiceContext(source, offset) {
 }
 
 // packages/ssml-editor-react/src/hooks/useSsmlEditorState.ts
-var TIMING_INSERTION_TAGS = /* @__PURE__ */ new Set(["break", "mstts:silence"]);
+var TIMING_INSERTION_TAGS = /* @__PURE__ */ new Set(["break", "mstts:silence", "mstts:audioduration"]);
 var PROSODY_INSERTION_TAGS = /* @__PURE__ */ new Set(["prosody", "mstts:express-as", "voice", "emphasis"]);
 var TEXT_INSERTION_TAGS = /* @__PURE__ */ new Set(["sub", "say-as", "phoneme", "w", "lang"]);
 var EMPTY_SELECTION_OVERLAY = {
@@ -3999,6 +4135,10 @@ var SSML_COMPLETION_SNIPPETS = [
     label: "mstts:express-as",
     insertText: `<mstts:express-as style="cheerful">\${1:text}</mstts:express-as>`
   },
+  {
+    label: "mstts:audioduration",
+    insertText: '<mstts:audioduration value="10s" />'
+  },
   {
     label: "sub",
     insertText: `<sub alias="\${1:\u8AAD\u307F}">\${2:\u6F22\u5B57}</sub>`
@@ -4274,7 +4414,7 @@ function registerSsmlCodeLens(monaco, editor, onOpenPopover) {
           break;
         }
         const tag = source.slice(tagStart, tagEnd + 1);
-        const tagName = tag.match(/^<\s*(prosody|break)\b/i)?.[1]?.toLowerCase();
+        const tagName = tag.match(/^<\s*(prosody|break|mstts:audioduration)\b/i)?.[1]?.toLowerCase();
         index = tagEnd + 1;
         if (!tagName) {
           continue;
@@ -4304,7 +4444,22 @@ function registerSsmlCodeLens(monaco, editor, onOpenPopover) {
               elementRange
             })
           );
-        } else if (/\/\s*>$/.test(tag)) {
+        } else if (tagName === "mstts:audioduration" && /\/\s*>$/.test(tag)) {
+          lenses.push(
+            createLens(
+              model,
+              tagStart,
+              tagEnd + 1,
+              `\u26A1 Duration: ${getAttributeValue(tag, "value") ?? "default"} (Click to edit)`,
+              { type: "attribute", insertionId: "mstts:audioduration", attributeName: "value", tagRange }
+            ),
+            createLens(model, tagStart, tagEnd + 1, "Delete", {
+              type: "delete",
+              tagRange,
+              elementRange
+            })
+          );
+        } else if (tagName === "break" && /\/\s*>$/.test(tag)) {
           lenses.push(
             createLens(
               model,
@@ -4640,6 +4795,17 @@ var SSML_TAG_DEFINITIONS = [
         values: VISEME_TYPE_PRESETS2
       }
     ]
+  },
+  {
+    name: "mstts:audioduration",
+    description: "Sets the target duration of synthesized audio.",
+    parameters: [
+      {
+        name: "value",
+        description: "The target duration, such as `10s`, `5000ms`, or `00:00:10`.",
+        example: "10s"
+      }
+    ]
   }
 ];
 var definitionsByName = /* @__PURE__ */ new Map();
@@ -5246,7 +5412,7 @@ function useSsmlMonaco({
 
 // packages/ssml-editor-react/src/SsmlEditor.tsx
 var UNGROUPED_TOOLBAR_GROUP = "__ssml-editor-ungrouped__";
-var TIMING_POPOVER_TAGS = /* @__PURE__ */ new Set(["break", "mstts:silence"]);
+var TIMING_POPOVER_TAGS = /* @__PURE__ */ new Set(["break", "mstts:silence", "mstts:audioduration"]);
 var PROSODY_POPOVER_TAGS = /* @__PURE__ */ new Set(["prosody", "mstts:express-as", "voice", "emphasis"]);
 var TEXT_POPOVER_TAGS = /* @__PURE__ */ new Set(["sub", "say-as", "phoneme", "w", "lang"]);
 function localizedText(value) {
@@ -5474,13 +5640,34 @@ var SSML_INSERTIONS = [
       suffix: "",
       mode: "insert"
     })
+  },
+  {
+    id: "mstts:audioduration",
+    icon: "\u25F7",
+    tagName: "mstts:audioduration",
+    selfClosing: true,
+    labels: { ja: "\u97F3\u58F0\u9577", en: "Audio duration" },
+    descriptions: {
+      ja: "\u5408\u6210\u97F3\u58F0\u306E\u76EE\u6A19\u6642\u9593\u3092\u6307\u5B9A\u3057\u307E\u3059\u3002",
+      en: "Sets the target duration of synthesized audio."
+    },
+    parameterDescription: {
+      ja: "\u76EE\u6A19\u6642\u9593\u3092\u9078\u629E\u3057\u307E\u3059\u3002",
+      en: "Selects the target duration."
+    },
+    options: createInsertionOptions(AUDIO_DURATION_PRESETS, AUDIO_DURATION_DESCRIPTIONS),
+    createTemplate: (value) => ({
+      prefix: `<mstts:audioduration value="${value}"/>`,
+      suffix: "",
+      mode: "insert"
+    })
   }
 ];
 var DEFAULT_INSERTION_GROUPS = [
   {
     id: "pauses",
     labels: { ja: "\u9593\u30FB\u7121\u97F3", en: "Pauses" },
-    insertionIds: ["break", "mstts:silence"]
+    insertionIds: ["break", "mstts:silence", "mstts:audioduration"]
   },
   {
     id: "prosody",