Razi Text Generation

Rewrite text you already have so it reads less like model output — fewer stock phrases, more contractions, varied sentence rhythm. Returns JSON { humanizedText }. Meaning is meant to be preserved but wording is not: never use it on text that must stay verbatim, such as quotes, legal copy or code. Use generate_text to produce new prose from a prompt and draft_email for a whole email; this one only transforms text it is given. Requires a signed-in razi.pro account — an anonymous call is rejected with 401. Paid model call; input capped at 10,000 characters and output at roughly 2,000 tokens, so long passages come back truncated. 30 calls per hour per account, and identical inputs may return a cached result.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The passage to rewrite. Plain text. Maximum 10,000 characters; longer input is rejected with 413."
    },
    "level": {
      "type": "string",
      "enum": [
        "light",
        "medium",
        "strong"
      ],
      "description": "How far the rewrite may drift from the original voice. 'light' strips AI tells but stays professional, 'medium' (the default, also used for any unrecognised value) turns it conversational with contractions, 'strong' rewrites it casually with short punchy sentences."
    }
  },
  "required": [
    "text"
  ]
}

Write a business email body from a short brief. Returns JSON { email, cached } containing the body only — no subject line, no recipient, and nothing is sent anywhere. Choose this over generate_text when the output should be a whole email; use humanize_text to rewrite an email you already drafted. Paid model call. Anonymous callers get 3 per hour per IP and are then refused with 401; signed-in callers get 15 per minute per IP. Length is capped at roughly 400 tokens. Identical briefs may return a cached draft.

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "What the email needs to say: purpose, recipient context, and any facts to include. A sentence or two is enough. Required and must not be blank."
    },
    "tone": {
      "type": "string",
      "enum": [
        "formal",
        "casual",
        "friendly"
      ],
      "description": "Register of the writing. Default formal. Passed to the model as an instruction, so it shapes wording rather than enforcing a fixed template."
    }
  },
  "required": [
    "prompt"
  ]
}

Produce a markdown heading structure for a blog post — title, introduction, numbered sections with subsections, conclusion and an FAQ block. Returns JSON { outline } holding the markdown. It writes the skeleton only, not the article: use generate_text for body prose and humanize_text to rework text that already exists. Paid model call, capped at roughly 1,000 tokens, so a large section count yields thinner sections. 10 calls per minute per IP; identical requests may return a cached outline.

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "The subject of the post, or a comma-free keyword phrase to build it around. The first thing supplied is treated as the primary keyword and the rest as secondary keywords to work in."
    },
    "sections": {
      "type": "number",
      "description": "How many main sections to plan between the introduction and the conclusion. Default 5; a non-numeric or zero value also falls back to 5."
    }
  },
  "required": [
    "topic"
  ]
}

Translate a natural-language request into a SQL statement. Returns JSON { sql } containing the query text and nothing else — no validation report, no complexity score, and the query is never executed or checked against a real database. It has no knowledge of your schema beyond what the request states, so table and column names are guesses unless you supply them. Review before running, especially anything that writes. Paid model call. Anonymous callers get 3 per hour per IP and are then refused with 401; signed-in callers get 15 per minute per IP. Capped at roughly 500 tokens. Answers are cached, so the same request returns the same query.

{
  "type": "object",
  "properties": {
    "description": {
      "type": "string",
      "description": "What the query should do, in plain language. Include the table and column names you want used, otherwise the model invents plausible ones. Required and must not be blank."
    },
    "dialect": {
      "type": "string",
      "enum": [
        "mysql",
        "postgresql",
        "sqlite"
      ],
      "description": "Intended SQL dialect. Accepted for forward compatibility but NOT currently passed to the model, so the generated SQL is generic and may need adjusting for your engine."
    }
  },
  "required": [
    "description"
  ]
}

Compare two blocks of text line by line. Returns JSON { identical, linesCompared, changeCount, changes[] }, where each change carries a 1-based line number, a change of 'added' | 'removed' | 'modified', and the before/after text. Lines are matched by POSITION, not by content: this is not an LCS diff, so inserting one line near the top reports every following line as modified. There is no character-level or word-level detail, and no unified-diff patch output. Whitespace and case are significant; \r\n and \n line endings are treated the same. Runs locally and costs nothing.

{
  "type": "object",
  "properties": {
    "text1": {
      "type": "string",
      "description": "The baseline text, reported as `before` in each change."
    },
    "text2": {
      "type": "string",
      "description": "The revised text, reported as `after` in each change."
    }
  },
  "required": [
    "text1",
    "text2"
  ]
}

Produce placeholder person records for testing and fixtures. Returns JSON { type, count, records } where records is an array of strings, or of objects when type is 'user'. The values are drawn from a fixed word list by index, so they are DETERMINISTIC: the same arguments always return the same records, and asking twice does not give you fresh data. Emails all use example.com and phone numbers all use the +1-555 reserved range. It fabricates people only — for lorem-style prose use generate_text.

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "name",
        "email",
        "address",
        "phone",
        "user"
      ],
      "description": "Shape of each record. 'name', 'email', 'address' and 'phone' each return a plain string; 'user' returns an object with all four fields. Required; any other value is rejected."
    },
    "count": {
      "type": "number",
      "description": "How many records to return. Default 1, clamped to the range 1-100, and truncated to a whole number. Records are always the same sequence, so count 10 is the first 5 of count 5 plus 5 more."
    }
  },
  "required": [
    "type"
  ]
}

Generate filler prose — lorem ipsum, random copy or sentences — for mockups and placeholder content. Returns JSON { text, provider, cached } with the blocks separated by newlines. A language model writes it, so it is a paid call and the output is approximate: type, length and count are phrased into the prompt rather than enforced, and the result will not match a requested character count exactly. For placeholder people (names, emails, addresses) use generate_fake_data, which is exact, free and deterministic. For a real email use draft_email, and to rework existing text use humanize_text. 15 calls per minute per IP; capped at roughly 1,500 tokens; identical requests may return a cached result.

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "lorem",
        "random",
        "sentence"
      ],
      "description": "Flavour of filler to ask for: classic latin lorem ipsum, arbitrary English copy, or standalone sentences. Default lorem. Used as a prompt hint, so it steers the style rather than guaranteeing it."
    },
    "length": {
      "type": "number",
      "description": "Rough size of each block in characters. Default 100. Requested in the prompt, so treat it as a target, not a limit."
    },
    "count": {
      "type": "number",
      "description": "How many separate blocks to return. Default 1. Large values are bounded in practice by the ~1,500 token output cap."
    }
  },
  "required": [
    "type"
  ]
}