Personal learning

Import Lesson

One course JSON. Paste or upload it, preview Vocabulary, Grammar and quizzes, then confirm. Your external AI prepares the content; this app does not analyze recordings or generate lessons.

One course package

V1 and V2 JSON accepted. V2 can contain Vocabulary, Grammar flashcards and lesson-specific quizzes together. PDF, YouTube, transcript and classroom-note sources keep their real references. No raw audio upload.

Current AI prompt & schema

Prepare ONE complete course JSON object/file from the source I provide, without Markdown fences. It may contain vocabulary, grammarLessons (including quizQuestions), or both. The app validates it; no internal AI generates missing content.
Use schemaVersion 2 and the CURRENT schema below. source.type is pdf, youtube, transcript or class-notes. Use the actual source title/filename; only YouTube includes its verified HTTPS video URL. Include source.date as YYYY-MM-DD only when known. If the source or captions are inaccessible, stop and say so. Do not claim full-session coverage from partial excerpts.
Supply a stable courseKey slug and explicit positive contentVersion (start at 1; increment for corrections/expansion). Keep word, lesson, card and question IDs stable across versions. Preserve the same source metadata when updating an explicitly selected owned course. Omitted content is retained, not deleted. Do not change a word ID to a different lemma/partOfSpeech: add a distinct item instead. Never merge unrelated courses by title.
Vocabulary is source-ordered; each entry has a stable id, actual spanish expression, dictionary lemma without noun articles, partOfSpeech, english, optional chinese/gender and examples. Translate the observed expression (estoy = I am; lemma estar), not a substituted lemma. The app groups distinct lemma+partOfSpeech items into up to 25 per Vocabulary lesson. Preserve accents and ñ.
Choose meaningful Grammar lesson boundaries: NO fixed card count or 25-card rule. Supply stable lowercase slug IDs and unique positive order. Write explanation and useful cards with front/back; optional summary, pattern, watchOut and teachingNote are supported. These explanations/cards are authored teaching, not instructor quotations. Each lesson needs at least one exact original Spanish source example with an author-checked reference in sourceReferences. Mark examples provenance source or ai-practice. Source quotations are verbatim, including captured ASR errors; do not silently repair or reconstruct omitted speech. AI-practice examples have NO source location. Label uncertain transcription and any editorial clarification outside the quotation.
References: PDF page (one-based), YouTube timestampSeconds from VERIFIED captions, transcript segment or verified timestampSeconds, class-notes segment. segment may be an actual positive numbered passage or supplied stable ID such as excerpt-a/excerpt-b. Never invent pages, timestamps, segment contents or quotations. The app validates reference shape, not source truth.
Each lesson may include quizQuestions: 0–60 externally authored questions, preferably 12–15 defensible questions. A 0–9-question bank is saved as incomplete and cannot start a graded quiz; never invent filler to reach ten. Each question needs stable id, prompt, exactly four distinct options, correctIndex 0–3, explanation, mistake feedback, and optional provenance ai-practice or owner-authored. Use provenance ai-practice for AI-authored questions. Verify one unambiguously correct answer, semantic alternatives, accents, regional usage and varied relevant lesson skills. Questions are practice, not source quotations. Owner review is required; structural validation cannot prove linguistic correctness. Never invent scores/mastery/certification.
Optional speakerGender describes actual speaker metadata, not noun gender. Use male/female only when established; otherwise omit/use unknown. Never rewrite original text to fit audio. observedForms contains only actually observed forms, not generated paradigms.
Use plain text only, no HTML/Markdown, audio URLs, profile/database IDs or app instructions. No app AI analysis, transcription or audio generation occurs during import. Maximum combined 512 KiB, 500 Vocabulary rows, 100 Grammar lessons, 100 cards per lesson, 1,000 cards total. Omit absent sections, never add empty placeholder lessons. Include available translations without inventing source content.
CURRENT JSON Schema:
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Spanish Trainer course import v2",
  "type": "object",
  "properties": {
    "schemaVersion": {
      "type": "integer",
      "enum": [
        2
      ]
    },
    "source": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "pdf",
            "youtube",
            "transcript",
            "class-notes"
          ]
        },
        "title": {
          "type": "string",
          "minLength": 1,
          "maxLength": 240
        },
        "url": {
          "type": "string",
          "minLength": 1,
          "maxLength": 2048
        },
        "date": {
          "type": "string",
          "minLength": 1,
          "maxLength": 10
        }
      },
      "required": [
        "type",
        "title"
      ],
      "additionalProperties": false
    },
    "courseKey": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "contentVersion": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000000
    },
    "vocabulary": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "spanish": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "partOfSpeech": {
            "type": "string",
            "enum": [
              "noun",
              "verb",
              "adjective",
              "adverb",
              "pronoun",
              "preposition",
              "conjunction",
              "phrase",
              "other"
            ]
          },
          "english": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "chinese": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "gender": {
            "type": "string",
            "enum": [
              "masculine",
              "feminine",
              "both"
            ]
          },
          "speakerGender": {
            "type": "string",
            "enum": [
              "male",
              "female",
              "unknown"
            ]
          },
          "examples": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "spanish": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "english": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "chinese": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "location": {
                  "type": "object",
                  "properties": {
                    "page": {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    "timestampSeconds": {
                      "type": "integer",
                      "minimum": 0,
                      "maximum": 604800
                    },
                    "segment": {
                      "anyOf": [
                        {
                          "type": "integer",
                          "minimum": 1,
                          "maximum": 100000
                        },
                        {
                          "type": "string",
                          "minLength": 1,
                          "maxLength": 64,
                          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                        }
                      ]
                    }
                  },
                  "required": [],
                  "additionalProperties": false
                },
                "speakerGender": {
                  "type": "string",
                  "enum": [
                    "male",
                    "female",
                    "unknown"
                  ]
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "source",
                    "ai-practice"
                  ]
                }
              },
              "required": [
                "spanish"
              ],
              "additionalProperties": false
            },
            "maxItems": 10
          }
        },
        "required": [
          "spanish",
          "lemma",
          "partOfSpeech",
          "english",
          "examples"
        ],
        "additionalProperties": false
      },
      "maxItems": 500,
      "minItems": 1
    },
    "observedForms": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "form": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "tense": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "person": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "location": {
            "type": "object",
            "properties": {
              "page": {
                "type": "integer",
                "minimum": 1,
                "maximum": 100000
              },
              "timestampSeconds": {
                "type": "integer",
                "minimum": 0,
                "maximum": 604800
              },
              "segment": {
                "anyOf": [
                  {
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 100000
                  },
                  {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 64,
                    "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                  }
                ]
              }
            },
            "required": [],
            "additionalProperties": false
          }
        },
        "required": [
          "lemma",
          "form"
        ],
        "additionalProperties": false
      },
      "maxItems": 200
    },
    "grammarLessons": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "order": {
            "type": "integer",
            "minimum": 1,
            "maximum": 100000
          },
          "title": {
            "type": "string",
            "minLength": 1,
            "maxLength": 240
          },
          "explanation": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4000
          },
          "summary": {
            "type": "string",
            "minLength": 1,
            "maxLength": 400
          },
          "pattern": {
            "type": "string",
            "minLength": 1,
            "maxLength": 600
          },
          "watchOut": {
            "type": "string",
            "minLength": 1,
            "maxLength": 1000
          },
          "teachingNote": {
            "type": "string",
            "minLength": 1,
            "maxLength": 1600
          },
          "quizQuestions": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 64
                },
                "prompt": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1200
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 600
                  },
                  "maxItems": 4,
                  "minItems": 4
                },
                "correctIndex": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 3
                },
                "explanation": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "mistake": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "ai-practice",
                    "owner-authored"
                  ]
                }
              },
              "required": [
                "id",
                "prompt",
                "options",
                "correctIndex",
                "explanation",
                "mistake"
              ],
              "additionalProperties": false
            },
            "maxItems": 60,
            "minItems": 0
          },
          "sourceReferences": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "page": {
                  "type": "integer",
                  "minimum": 1,
                  "maximum": 100000
                },
                "timestampSeconds": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 604800
                },
                "segment": {
                  "anyOf": [
                    {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    {
                      "type": "string",
                      "minLength": 1,
                      "maxLength": 64,
                      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                    }
                  ]
                }
              },
              "required": [],
              "additionalProperties": false
            },
            "maxItems": 30,
            "minItems": 1
          },
          "cards": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 64
                },
                "front": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "back": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 4000
                },
                "pattern": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 600
                },
                "explanation": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "examples": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "spanish": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "english": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "chinese": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "location": {
                        "type": "object",
                        "properties": {
                          "page": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 100000
                          },
                          "timestampSeconds": {
                            "type": "integer",
                            "minimum": 0,
                            "maximum": 604800
                          },
                          "segment": {
                            "anyOf": [
                              {
                                "type": "integer",
                                "minimum": 1,
                                "maximum": 100000
                              },
                              {
                                "type": "string",
                                "minLength": 1,
                                "maxLength": 64,
                                "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                              }
                            ]
                          }
                        },
                        "required": [],
                        "additionalProperties": false
                      },
                      "speakerGender": {
                        "type": "string",
                        "enum": [
                          "male",
                          "female",
                          "unknown"
                        ]
                      },
                      "provenance": {
                        "type": "string",
                        "enum": [
                          "source",
                          "ai-practice"
                        ]
                      }
                    },
                    "required": [
                      "spanish",
                      "provenance"
                    ],
                    "additionalProperties": false
                  },
                  "maxItems": 10
                }
              },
              "required": [
                "id",
                "front",
                "back",
                "examples"
              ],
              "additionalProperties": false
            },
            "maxItems": 100,
            "minItems": 1
          }
        },
        "required": [
          "id",
          "order",
          "title",
          "explanation",
          "sourceReferences",
          "cards"
        ],
        "additionalProperties": false
      },
      "maxItems": 100,
      "minItems": 1
    }
  },
  "required": [
    "schemaVersion",
    "source"
  ],
  "additionalProperties": false
}

Course destinationCourse nameComplete course JSONCourse JSON file

Maximum 512 KiB. Updates merge by stable word/lesson/card/question IDs; omitted items are retained, not deleted. Changing a word's lemma or part of speech is rejected if it would reassign its SRS identity. Unrelated sources require a new course.

Advanced Import · Vocabulary JSON + Grammar JSON

Personal learning

Advanced Import

One source course · Two JSON inputs. Your external AI prepares the content; Spanish Trainer only validates and stores it.

Manage Courses

No AI API, PDF parser or transcription service is connected. Importing and opening lessons generate no audio.

V2 two-input AI prompt & schema

Advanced two-input import: prepare TWO JSON objects/files, Vocabulary JSON and Grammar JSON, with identical source, courseKey and contentVersion metadata. Vocabulary JSON contains vocabulary/optional observedForms only; Grammar JSON contains grammarLessons only. A combined V2 object may instead contain both sections.
Use schemaVersion 2 and the CURRENT schema below. source.type is pdf, youtube, transcript or class-notes. Use the actual source title/filename; only YouTube includes its verified HTTPS video URL. Include source.date as YYYY-MM-DD only when known. If the source or captions are inaccessible, stop and say so. Do not claim full-session coverage from partial excerpts.
Supply a stable courseKey slug and explicit positive contentVersion (start at 1; increment for corrections/expansion). Keep word, lesson, card and question IDs stable across versions. Preserve the same source metadata when updating an explicitly selected owned course. Omitted content is retained, not deleted. Do not change a word ID to a different lemma/partOfSpeech: add a distinct item instead. Never merge unrelated courses by title.
Vocabulary is source-ordered; each entry has a stable id, actual spanish expression, dictionary lemma without noun articles, partOfSpeech, english, optional chinese/gender and examples. Translate the observed expression (estoy = I am; lemma estar), not a substituted lemma. The app groups distinct lemma+partOfSpeech items into up to 25 per Vocabulary lesson. Preserve accents and ñ.
Choose meaningful Grammar lesson boundaries: NO fixed card count or 25-card rule. Supply stable lowercase slug IDs and unique positive order. Write explanation and useful cards with front/back; optional summary, pattern, watchOut and teachingNote are supported. These explanations/cards are authored teaching, not instructor quotations. Each lesson needs at least one exact original Spanish source example with an author-checked reference in sourceReferences. Mark examples provenance source or ai-practice. Source quotations are verbatim, including captured ASR errors; do not silently repair or reconstruct omitted speech. AI-practice examples have NO source location. Label uncertain transcription and any editorial clarification outside the quotation.
References: PDF page (one-based), YouTube timestampSeconds from VERIFIED captions, transcript segment or verified timestampSeconds, class-notes segment. segment may be an actual positive numbered passage or supplied stable ID such as excerpt-a/excerpt-b. Never invent pages, timestamps, segment contents or quotations. The app validates reference shape, not source truth.
Each lesson may include quizQuestions: 0–60 externally authored questions, preferably 12–15 defensible questions. A 0–9-question bank is saved as incomplete and cannot start a graded quiz; never invent filler to reach ten. Each question needs stable id, prompt, exactly four distinct options, correctIndex 0–3, explanation, mistake feedback, and optional provenance ai-practice or owner-authored. Use provenance ai-practice for AI-authored questions. Verify one unambiguously correct answer, semantic alternatives, accents, regional usage and varied relevant lesson skills. Questions are practice, not source quotations. Owner review is required; structural validation cannot prove linguistic correctness. Never invent scores/mastery/certification.
Optional speakerGender describes actual speaker metadata, not noun gender. Use male/female only when established; otherwise omit/use unknown. Never rewrite original text to fit audio. observedForms contains only actually observed forms, not generated paradigms.
Use plain text only, no HTML/Markdown, audio URLs, profile/database IDs or app instructions. No app AI analysis, transcription or audio generation occurs during import. Maximum combined 512 KiB, 500 Vocabulary rows, 100 Grammar lessons, 100 cards per lesson, 1,000 cards total. Omit absent sections, never add empty placeholder lessons. Include available translations without inventing source content.
CURRENT JSON Schema:
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Spanish Trainer course import v2",
  "type": "object",
  "properties": {
    "schemaVersion": {
      "type": "integer",
      "enum": [
        2
      ]
    },
    "source": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "pdf",
            "youtube",
            "transcript",
            "class-notes"
          ]
        },
        "title": {
          "type": "string",
          "minLength": 1,
          "maxLength": 240
        },
        "url": {
          "type": "string",
          "minLength": 1,
          "maxLength": 2048
        },
        "date": {
          "type": "string",
          "minLength": 1,
          "maxLength": 10
        }
      },
      "required": [
        "type",
        "title"
      ],
      "additionalProperties": false
    },
    "courseKey": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "contentVersion": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000000
    },
    "vocabulary": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "spanish": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "partOfSpeech": {
            "type": "string",
            "enum": [
              "noun",
              "verb",
              "adjective",
              "adverb",
              "pronoun",
              "preposition",
              "conjunction",
              "phrase",
              "other"
            ]
          },
          "english": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "chinese": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "gender": {
            "type": "string",
            "enum": [
              "masculine",
              "feminine",
              "both"
            ]
          },
          "speakerGender": {
            "type": "string",
            "enum": [
              "male",
              "female",
              "unknown"
            ]
          },
          "examples": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "spanish": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "english": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "chinese": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "location": {
                  "type": "object",
                  "properties": {
                    "page": {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    "timestampSeconds": {
                      "type": "integer",
                      "minimum": 0,
                      "maximum": 604800
                    },
                    "segment": {
                      "anyOf": [
                        {
                          "type": "integer",
                          "minimum": 1,
                          "maximum": 100000
                        },
                        {
                          "type": "string",
                          "minLength": 1,
                          "maxLength": 64,
                          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                        }
                      ]
                    }
                  },
                  "required": [],
                  "additionalProperties": false
                },
                "speakerGender": {
                  "type": "string",
                  "enum": [
                    "male",
                    "female",
                    "unknown"
                  ]
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "source",
                    "ai-practice"
                  ]
                }
              },
              "required": [
                "spanish"
              ],
              "additionalProperties": false
            },
            "maxItems": 10
          }
        },
        "required": [
          "spanish",
          "lemma",
          "partOfSpeech",
          "english",
          "examples"
        ],
        "additionalProperties": false
      },
      "maxItems": 500,
      "minItems": 1
    },
    "observedForms": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "form": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "tense": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "person": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "location": {
            "type": "object",
            "properties": {
              "page": {
                "type": "integer",
                "minimum": 1,
                "maximum": 100000
              },
              "timestampSeconds": {
                "type": "integer",
                "minimum": 0,
                "maximum": 604800
              },
              "segment": {
                "anyOf": [
                  {
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 100000
                  },
                  {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 64,
                    "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                  }
                ]
              }
            },
            "required": [],
            "additionalProperties": false
          }
        },
        "required": [
          "lemma",
          "form"
        ],
        "additionalProperties": false
      },
      "maxItems": 200
    },
    "grammarLessons": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "order": {
            "type": "integer",
            "minimum": 1,
            "maximum": 100000
          },
          "title": {
            "type": "string",
            "minLength": 1,
            "maxLength": 240
          },
          "explanation": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4000
          },
          "summary": {
            "type": "string",
            "minLength": 1,
            "maxLength": 400
          },
          "pattern": {
            "type": "string",
            "minLength": 1,
            "maxLength": 600
          },
          "watchOut": {
            "type": "string",
            "minLength": 1,
            "maxLength": 1000
          },
          "teachingNote": {
            "type": "string",
            "minLength": 1,
            "maxLength": 1600
          },
          "quizQuestions": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 64
                },
                "prompt": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1200
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 600
                  },
                  "maxItems": 4,
                  "minItems": 4
                },
                "correctIndex": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 3
                },
                "explanation": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "mistake": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "ai-practice",
                    "owner-authored"
                  ]
                }
              },
              "required": [
                "id",
                "prompt",
                "options",
                "correctIndex",
                "explanation",
                "mistake"
              ],
              "additionalProperties": false
            },
            "maxItems": 60,
            "minItems": 0
          },
          "sourceReferences": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "page": {
                  "type": "integer",
                  "minimum": 1,
                  "maximum": 100000
                },
                "timestampSeconds": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 604800
                },
                "segment": {
                  "anyOf": [
                    {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    {
                      "type": "string",
                      "minLength": 1,
                      "maxLength": 64,
                      "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                    }
                  ]
                }
              },
              "required": [],
              "additionalProperties": false
            },
            "maxItems": 30,
            "minItems": 1
          },
          "cards": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 64
                },
                "front": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "back": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 4000
                },
                "pattern": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 600
                },
                "explanation": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 1600
                },
                "examples": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "spanish": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "english": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "chinese": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 2000
                      },
                      "location": {
                        "type": "object",
                        "properties": {
                          "page": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 100000
                          },
                          "timestampSeconds": {
                            "type": "integer",
                            "minimum": 0,
                            "maximum": 604800
                          },
                          "segment": {
                            "anyOf": [
                              {
                                "type": "integer",
                                "minimum": 1,
                                "maximum": 100000
                              },
                              {
                                "type": "string",
                                "minLength": 1,
                                "maxLength": 64,
                                "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                              }
                            ]
                          }
                        },
                        "required": [],
                        "additionalProperties": false
                      },
                      "speakerGender": {
                        "type": "string",
                        "enum": [
                          "male",
                          "female",
                          "unknown"
                        ]
                      },
                      "provenance": {
                        "type": "string",
                        "enum": [
                          "source",
                          "ai-practice"
                        ]
                      }
                    },
                    "required": [
                      "spanish",
                      "provenance"
                    ],
                    "additionalProperties": false
                  },
                  "maxItems": 10
                }
              },
              "required": [
                "id",
                "front",
                "back",
                "examples"
              ],
              "additionalProperties": false
            },
            "maxItems": 100,
            "minItems": 1
          }
        },
        "required": [
          "id",
          "order",
          "title",
          "explanation",
          "sourceReferences",
          "cards"
        ],
        "additionalProperties": false
      },
      "maxItems": 100,
      "minItems": 1
    }
  },
  "required": [
    "schemaVersion",
    "source"
  ],
  "additionalProperties": false
}

Legacy V1 compatibility and original prompt

Existing V1 PDF/YouTube files still work. Upload one below, or paste its full object into Vocabulary JSON with Grammar JSON empty. Legacy topics and completion are retained.

Extract a personal Spanish learning course ONLY from the PDF, accessible YouTube captions, transcript or class notes I provide. Work with any capable general-purpose assistant. If you cannot access the source or captions, say so; do not invent content.
Return ONE JSON object (no Markdown), conforming exactly to the JSON Schema below. schemaVersion must be 1. source.title must be the original PDF filename (including extension), verified YouTube title, or actual transcript/class-note title, not an invented course title. For YouTube include the verified HTTPS video URL; PDF, transcript and class-notes have no url.
Keep vocabulary in meaningful source order. Use dictionary lemmas without noun articles; include the observed Spanish word/phrase separately and translate that source expression, not a different lemma. Match partOfSpeech to the enum (greetings are phrase). Do not strip accents or ñ. Preserve original Spanish examples verbatim; include translations only when reliable. Examples arrays may be empty if none exists. Do not invent source examples, page numbers, timestamps or conjugation paradigms. Use location.page for PDF, timestampSeconds for YouTube, segment or a real timestampSeconds for transcript, segment for class-notes. segment is a one-based numbered passage in the actual supplied source, not a fake PDF page. Omit unavailable locations. observedForms contains forms actually observed, NOT generated paradigms; optional tense/person only when certain (stored tense keys: present, preterite, imperfect, future; person keys: yo, tu, el_usted, nosotros, vosotros, ellos_ustedes). Other labels remain unverified observations.
Optional speakerGender on a vocabulary expression or example describes its actual speaker, not grammatical gender. Use male/female only when explicitly established by the source; otherwise omit it or use unknown. Never infer the speaker from names, masculine nouns, third-person subjects or adjective endings alone. Do not rewrite any original sentence to fit a voice.
Use empty arrays for absent vocabulary, grammar or observedForms. No HTML/Markdown, profile IDs, database IDs, audio URLs, proficiency certification, or instructions to the application. New vocabulary is personal; no automatic audio synthesis. Maximum 500 words, 100 grammar topics, 200 observed forms, 512 KiB total. Split a larger source deliberately into separate imports, not truncated claims.
JSON Schema:
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "Spanish Trainer personal source course v1",
  "type": "object",
  "properties": {
    "schemaVersion": {
      "type": "integer",
      "enum": [
        1
      ]
    },
    "courseKey": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "contentVersion": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000000
    },
    "source": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "pdf",
            "youtube",
            "transcript",
            "class-notes"
          ]
        },
        "title": {
          "type": "string",
          "minLength": 1,
          "maxLength": 240
        },
        "url": {
          "type": "string",
          "minLength": 1,
          "maxLength": 2048
        },
        "date": {
          "type": "string",
          "minLength": 1,
          "maxLength": 10
        }
      },
      "required": [
        "type",
        "title"
      ],
      "additionalProperties": false
    },
    "vocabulary": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "spanish": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "partOfSpeech": {
            "type": "string",
            "enum": [
              "noun",
              "verb",
              "adjective",
              "adverb",
              "pronoun",
              "preposition",
              "conjunction",
              "phrase",
              "other"
            ]
          },
          "english": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "chinese": {
            "type": "string",
            "minLength": 1,
            "maxLength": 500
          },
          "gender": {
            "type": "string",
            "enum": [
              "masculine",
              "feminine",
              "both"
            ]
          },
          "speakerGender": {
            "type": "string",
            "enum": [
              "male",
              "female",
              "unknown"
            ]
          },
          "examples": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "spanish": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "english": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "chinese": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "location": {
                  "type": "object",
                  "properties": {
                    "page": {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    "timestampSeconds": {
                      "type": "integer",
                      "minimum": 0,
                      "maximum": 604800
                    },
                    "segment": {
                      "anyOf": [
                        {
                          "type": "integer",
                          "minimum": 1,
                          "maximum": 100000
                        },
                        {
                          "type": "string",
                          "minLength": 1,
                          "maxLength": 64,
                          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                        }
                      ]
                    }
                  },
                  "required": [],
                  "additionalProperties": false
                },
                "speakerGender": {
                  "type": "string",
                  "enum": [
                    "male",
                    "female",
                    "unknown"
                  ]
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "source",
                    "ai-practice"
                  ]
                }
              },
              "required": [
                "spanish"
              ],
              "additionalProperties": false
            },
            "maxItems": 10
          }
        },
        "required": [
          "spanish",
          "lemma",
          "partOfSpeech",
          "english",
          "examples"
        ],
        "additionalProperties": false
      },
      "maxItems": 500
    },
    "grammar": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "minLength": 1,
            "maxLength": 64
          },
          "title": {
            "type": "string",
            "minLength": 1,
            "maxLength": 240
          },
          "explanation": {
            "type": "string",
            "minLength": 1,
            "maxLength": 4000
          },
          "examples": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "spanish": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "english": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "chinese": {
                  "type": "string",
                  "minLength": 1,
                  "maxLength": 2000
                },
                "location": {
                  "type": "object",
                  "properties": {
                    "page": {
                      "type": "integer",
                      "minimum": 1,
                      "maximum": 100000
                    },
                    "timestampSeconds": {
                      "type": "integer",
                      "minimum": 0,
                      "maximum": 604800
                    },
                    "segment": {
                      "anyOf": [
                        {
                          "type": "integer",
                          "minimum": 1,
                          "maximum": 100000
                        },
                        {
                          "type": "string",
                          "minLength": 1,
                          "maxLength": 64,
                          "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                        }
                      ]
                    }
                  },
                  "required": [],
                  "additionalProperties": false
                },
                "speakerGender": {
                  "type": "string",
                  "enum": [
                    "male",
                    "female",
                    "unknown"
                  ]
                },
                "provenance": {
                  "type": "string",
                  "enum": [
                    "source",
                    "ai-practice"
                  ]
                }
              },
              "required": [
                "spanish"
              ],
              "additionalProperties": false
            },
            "maxItems": 10
          }
        },
        "required": [
          "title",
          "explanation",
          "examples"
        ],
        "additionalProperties": false
      },
      "maxItems": 100
    },
    "observedForms": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "lemma": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "form": {
            "type": "string",
            "minLength": 1,
            "maxLength": 160
          },
          "tense": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "person": {
            "type": "string",
            "minLength": 1,
            "maxLength": 80
          },
          "location": {
            "type": "object",
            "properties": {
              "page": {
                "type": "integer",
                "minimum": 1,
                "maximum": 100000
              },
              "timestampSeconds": {
                "type": "integer",
                "minimum": 0,
                "maximum": 604800
              },
              "segment": {
                "anyOf": [
                  {
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 100000
                  },
                  {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 64,
                    "pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$"
                  }
                ]
              }
            },
            "required": [],
            "additionalProperties": false
          }
        },
        "required": [
          "lemma",
          "form"
        ],
        "additionalProperties": false
      },
      "maxItems": 200
    }
  },
  "required": [
    "schemaVersion",
    "source",
    "vocabulary",
    "grammar",
    "observedForms"
  ],
  "additionalProperties": false
}

One course, two content inputs

Paste the objects your external AI prepared below. Either section may be empty. A combined V2 object also works in either box alone—you can split it before importing. PDF, YouTube, transcript and classroom notes are supported; raw prose is not JSON.

Combined maximum 512 KiB · 500 vocabulary rows · 100 grammar lessons · 1,000 grammar cards. Grammar follows authored lesson boundaries, not 25-card batches.

Course destinationCourse name

Append requires explicit course selection and exact matching source metadata. Existing sections cannot be replaced. Repeated identical content reuses its owned course and title; matching titles alone never merge courses.

Vocabulary JSON

Grammar JSON

JSON file · Alternative to text inputs

V1 file, either V2 section, or combined V2 file. Read locally; PDFs/videos/audio are never uploaded.

Add valid Vocabulary JSON, Grammar JSON, or a JSON file to see the shared source and combined preview.

Private to your signed-in learner profile. Keep your source JSON and recovery code. AI-authored content and references require your own review; no quiz score or mastery is inferred.

Courses belong to your signed-in learner profile. Keep the source JSON and your recovery code. No audio, AI call or paid synthesis occurs during import/update. Source quotations and linguistic accuracy require owner review.