103 lines
3.0 KiB
TypeScript
103 lines
3.0 KiB
TypeScript
import type { SecretInput } from "./types.secrets.js";
|
||
|
||
export type TtsProvider = string;
|
||
|
||
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 (default: false). */
|
||
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?: SecretInput;
|
||
baseUrl?: string;
|
||
voiceId?: string;
|
||
modelId?: string;
|
||
seed?: number;
|
||
applyTextNormalization?: "auto" | "on" | "off";
|
||
languageCode?: string;
|
||
voiceSettings?: {
|
||
stability?: number;
|
||
similarityBoost?: number;
|
||
style?: number;
|
||
useSpeakerBoost?: boolean;
|
||
speed?: number;
|
||
};
|
||
};
|
||
/** OpenAI configuration. */
|
||
openai?: {
|
||
apiKey?: SecretInput;
|
||
baseUrl?: string;
|
||
model?: string;
|
||
voice?: string;
|
||
/** Playback speed (0.25–4.0, default 1.0). */
|
||
speed?: number;
|
||
/** System-level instructions for the TTS model (gpt-4o-mini-tts only). */
|
||
instructions?: string;
|
||
};
|
||
/** Legacy alias for Microsoft speech configuration. */
|
||
edge?: {
|
||
/** Explicitly allow Microsoft speech 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;
|
||
};
|
||
/** Preferred alias for Microsoft speech configuration. */
|
||
microsoft?: {
|
||
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;
|
||
};
|