openclaw/extensions/elevenlabs/tts.ts

import {
  normalizeApplyTextNormalization,
  normalizeLanguageCode,
  normalizeSeed,
  requireInRange,
} from "openclaw/plugin-sdk/speech";

const DEFAULT_ELEVENLABS_BASE_URL = "https://api.elevenlabs.io";

function isValidVoiceId(voiceId: string): boolean {
  return /^[a-zA-Z0-9]{10,40}$/.test(voiceId);
}

function normalizeElevenLabsBaseUrl(baseUrl?: string): string {
  const trimmed = baseUrl?.trim();
  if (!trimmed) {
    return DEFAULT_ELEVENLABS_BASE_URL;
  }
  return trimmed.replace(/\/+$/, "");
}

function assertElevenLabsVoiceSettings(settings: {
  stability: number;
  similarityBoost: number;
  style: number;
  useSpeakerBoost: boolean;
  speed: number;
}) {
  requireInRange(settings.stability, 0, 1, "stability");
  requireInRange(settings.similarityBoost, 0, 1, "similarityBoost");
  requireInRange(settings.style, 0, 1, "style");
  requireInRange(settings.speed, 0.5, 2, "speed");
}

export async function elevenLabsTTS(params: {
  text: string;
  apiKey: string;
  baseUrl: string;
  voiceId: string;
  modelId: string;
  outputFormat: string;
  seed?: number;
  applyTextNormalization?: "auto" | "on" | "off";
  languageCode?: string;
  voiceSettings: {
    stability: number;
    similarityBoost: number;
    style: number;
    useSpeakerBoost: boolean;
    speed: number;
  };
  timeoutMs: number;
}): Promise<Buffer> {
  const {
    text,
    apiKey,
    baseUrl,
    voiceId,
    modelId,
    outputFormat,
    seed,
    applyTextNormalization,
    languageCode,
    voiceSettings,
    timeoutMs,
  } = params;
  if (!isValidVoiceId(voiceId)) {
    throw new Error("Invalid voiceId format");
  }
  assertElevenLabsVoiceSettings(voiceSettings);
  const normalizedLanguage = normalizeLanguageCode(languageCode);
  const normalizedNormalization = normalizeApplyTextNormalization(applyTextNormalization);
  const normalizedSeed = normalizeSeed(seed);

  const controller = new AbortController();
  const timeout = setTimeout(() => controller.abort(), timeoutMs);

  try {
    const url = new URL(`${normalizeElevenLabsBaseUrl(baseUrl)}/v1/text-to-speech/${voiceId}`);
    if (outputFormat) {
      url.searchParams.set("output_format", outputFormat);
    }

    const response = await fetch(url.toString(), {
      method: "POST",
      headers: {
        "xi-api-key": apiKey,
        "Content-Type": "application/json",
        Accept: "audio/mpeg",
      },
      body: JSON.stringify({
        text,
        model_id: modelId,
        seed: normalizedSeed,
        apply_text_normalization: normalizedNormalization,
        language_code: normalizedLanguage,
        voice_settings: {
          stability: voiceSettings.stability,
          similarity_boost: voiceSettings.similarityBoost,
          style: voiceSettings.style,
          use_speaker_boost: voiceSettings.useSpeakerBoost,
          speed: voiceSettings.speed,
        },
      }),
      signal: controller.signal,
    });

    if (!response.ok) {
      throw new Error(`ElevenLabs API error (${response.status})`);
    }

    return Buffer.from(await response.arrayBuffer());
  } finally {
    clearTimeout(timeout);
  }
}