5e58242997
Adds configurable output format for ElevenLabs TTS, allowing users to override the default mp3_44100_128 format. This is useful for channels like WhatsApp that require specific audio formats (e.g., 24kHz, 48kbps, mono) that differ from the defaults. Changes: - Add outputFormat field to elevenlabs config in types.tts.ts - Add outputFormat to zod schema validation - Use configured outputFormat in tts.ts, falling back to channel defaults - Infer file extension from custom outputFormat when specified Example config: messages.tts.elevenlabs.outputFormat: "mp3_22050_32"
85 lines
2.5 KiB
TypeScript
85 lines
2.5 KiB
TypeScript
export type TtsProvider = "elevenlabs" | "openai" | "edge";
|
|
|
|
export type TtsMode = "final" | "all";
|
|
|
|
export type TtsAutoMode = "off" | "always" | "inbound" | "tagged";
|
|
|
|
export type TtsModelOverrideConfig = {
|
|
/** Enable model-provided overrides for TTS. */
|
|
enabled?: boolean;
|
|
/** Allow model-provided TTS text blocks. */
|
|
allowText?: boolean;
|
|
/** Allow model-provided provider override. */
|
|
allowProvider?: boolean;
|
|
/** Allow model-provided voice/voiceId override. */
|
|
allowVoice?: boolean;
|
|
/** Allow model-provided modelId override. */
|
|
allowModelId?: boolean;
|
|
/** Allow model-provided voice settings override. */
|
|
allowVoiceSettings?: boolean;
|
|
/** Allow model-provided normalization or language overrides. */
|
|
allowNormalization?: boolean;
|
|
/** Allow model-provided seed override. */
|
|
allowSeed?: boolean;
|
|
};
|
|
|
|
export type TtsConfig = {
|
|
/** Auto-TTS mode (preferred). */
|
|
auto?: TtsAutoMode;
|
|
/** Legacy: enable auto-TTS when `auto` is not set. */
|
|
enabled?: boolean;
|
|
/** Apply TTS to final replies only or to all replies (tool/block/final). */
|
|
mode?: TtsMode;
|
|
/** Primary TTS provider (fallbacks are automatic). */
|
|
provider?: TtsProvider;
|
|
/** Optional model override for TTS auto-summary (provider/model or alias). */
|
|
summaryModel?: string;
|
|
/** Allow the model to override TTS parameters. */
|
|
modelOverrides?: TtsModelOverrideConfig;
|
|
/** ElevenLabs configuration. */
|
|
elevenlabs?: {
|
|
apiKey?: string;
|
|
baseUrl?: string;
|
|
voiceId?: string;
|
|
modelId?: string;
|
|
/** Output format (e.g. mp3_22050_32, mp3_44100_128, pcm_16000, pcm_22050, pcm_24000). */
|
|
outputFormat?: string;
|
|
seed?: number;
|
|
applyTextNormalization?: "auto" | "on" | "off";
|
|
languageCode?: string;
|
|
voiceSettings?: {
|
|
stability?: number;
|
|
similarityBoost?: number;
|
|
style?: number;
|
|
useSpeakerBoost?: boolean;
|
|
speed?: number;
|
|
};
|
|
};
|
|
/** OpenAI configuration. */
|
|
openai?: {
|
|
apiKey?: string;
|
|
model?: string;
|
|
voice?: string;
|
|
};
|
|
/** Microsoft Edge (node-edge-tts) configuration. */
|
|
edge?: {
|
|
/** Explicitly allow Edge TTS usage (no API key required). */
|
|
enabled?: boolean;
|
|
voice?: string;
|
|
lang?: string;
|
|
outputFormat?: string;
|
|
pitch?: string;
|
|
rate?: string;
|
|
volume?: string;
|
|
saveSubtitles?: boolean;
|
|
proxy?: string;
|
|
timeoutMs?: number;
|
|
};
|
|
/** Optional path for local TTS user preferences JSON. */
|
|
prefsPath?: string;
|
|
/** Hard cap for text sent to TTS (chars). */
|
|
maxTextLength?: number;
|
|
/** API request timeout (ms). */
|
|
timeoutMs?: number;
|
|
};
|