@ai-sdk/google-vertex/src/gemini-transcription/google-vertex-gemini-transcription-model-options.ts

import {
  lazySchema,
  zodSchema,
  type InferSchema,
} from '@ai-sdk/provider-utils';
import { z } from 'zod/v4';
import type { GoogleVertexModelIds } from '../google-vertex-model-catalog';

export type GoogleVertexGeminiTranscriptionModelId =
  | GoogleVertexModelIds['geminiTranscription']
  | (string & {});

/**
 * Speech recognition options for Gemini transcription models on Vertex,
 * shared by unary (`gemini-3.5-transcribe`) and live
 * (`gemini-3.5-transcribe-live`) variants. Maps onto Google's
 * `AudioTranscriptionConfig`.
 */
export const googleVertexGeminiTranscriptionModelOptions = lazySchema(() =>
  zodSchema(
    z.object({
      /**
       * BCP-47 language codes providing hints about the languages present in the
       * audio. If omitted or empty, defaults to automatic language detection.
       */
      languageCodes: z.array(z.string()).optional(),

      /**
       * Custom vocabulary phrases, which bias the speech recognition model
       * toward recognizing specific terms.
       */
      customVocabulary: z.array(z.string()).optional(),

      /**
       * Enables word-level timestamp generation.
       */
      wordTimestamp: z.boolean().optional(),

      /**
       * Enables speaker diarization.
       */
      diarization: z.boolean().optional(),

      /**
       * Transcription output formatting mode.
       *
       * - `VERBATIM` (default): exact literal transcript preserving filler
       *   words, repetitions, and false starts.
       * - `SMART`: cleans up and structures the transcript in real time —
       *   disfluency removal, inline self-corrections, structured formatting
       *   (lists, numbers, dates, paragraph breaks), and grammar/casing polish.
       */
      mode: z.enum(['SMART', 'VERBATIM']).optional(),
    }),
  ),
);

export type GoogleVertexTranscriptionModelGeminiOptions = InferSchema<
  typeof googleVertexGeminiTranscriptionModelOptions
>;