memos/proto/api/v1/ai_service.proto

syntax = "proto3";

package memos.api.v1;

import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";

option go_package = "gen/api/v1";

service AIService {
  // Transcribe transcribes an audio file using an instance AI provider.
  rpc Transcribe(TranscribeRequest) returns (TranscribeResponse) {
    option (google.api.http) = {
      post: "/api/v1/ai:transcribe"
      body: "*"
    };
    option (google.api.method_signature) = "provider_id,config,audio";
  }
}

message TranscribeRequest {
  // Required. The instance AI provider ID to use.
  string provider_id = 1 [(google.api.field_behavior) = REQUIRED];

  // Required. Transcription options.
  TranscriptionConfig config = 2 [(google.api.field_behavior) = REQUIRED];

  // Required. Audio input.
  TranscriptionAudio audio = 3 [(google.api.field_behavior) = REQUIRED];
}

message TranscriptionConfig {
  // Optional. A prompt to improve transcription quality.
  string prompt = 1 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The language of the input audio.
  string language = 2 [(google.api.field_behavior) = OPTIONAL];
}

message TranscriptionAudio {
  oneof source {
    // Inline audio bytes.
    bytes content = 1 [(google.api.field_behavior) = INPUT_ONLY];

    // URI for audio content. Reserved for future use.
    string uri = 2;
  }

  // Optional. The uploaded filename.
  string filename = 3 [(google.api.field_behavior) = OPTIONAL];

  // Optional. The MIME type of the input audio.
  string content_type = 4 [(google.api.field_behavior) = OPTIONAL];
}

message TranscribeResponse {
  // The transcribed text.
  string text = 1;
}