Translate a file

This guide covers the complete signed-in workflow in the web app. The same work can be driven over the REST API or the MCP tools. The CLI can inspect and download translations but does not start them.

You never map columns by hand. You say what you want, read back what AI Glot understood, and correct it until it is right. Nothing is charged until you approve.

1. Upload the file

Open AI Glot and choose New translation. Drag a file in or use the file picker.

Twelve format families are accepted, each with its own size ceiling: 60 MB for CSV, 50 MB for Excel, 4 MB for a locale file. See Files and formats for the full table and what each format preserves.

2. Say what you want translated

AI Glot reads the file first and opens with what it found: the format, the structure it detected, and four suggested ways to start drawn from your actual file rather than a generic list.

Take a suggestion, or type your own instruction. Plain language is the interface:

• “Translate the product descriptions into German, leave the SKUs alone.”
• “Everything except the URLs.”
• “Only the rows where the French column is empty.”

Reading the file costs nothing, and neither does asking. You can ask as many times as you like.

3. Review the plan in three views

A plan comes back with measured counts: the real number of items and words found in your file, not an estimate from its size. The right-hand pane offers three ways to check it, and they answer different questions.

The item table is the cheapest insurance available. An instruction that quietly matched the wrong field is obvious there, before it has cost anything.

4. Refine until it is right

If the plan is close but not correct, say what to change: “actually, only the empty rows”, “keep the brand names in English”. A refinement keeps everything you already agreed to; a fresh instruction starts over and may reinterpret parts you were happy with.

This is the step that replaces column mapping. There is no grid of dropdowns to get wrong.

5. Choose quality and terminology

Standard costs approximately one credit per billable word. Paid plans can choose Lite, a lighter process for larger or less critical content, at about one third of the Standard cost.

If your workspace has a glossary for the language pair, AI Glot applies it automatically. Paid plans can also add instructions specific to this batch, up to 1,500 characters. Batch instructions change how the text is translated, never which text is translated. That is what the plan decides.

6. Approve the cost

Approval is the only step that spends credits. The estimate you approve is the plan’s measured word count at the quality you chose, so it is the number you were already looking at.

Credits are reserved atomically at that moment. A second job running at the same time cannot spend the same balance twice.

7. Follow progress and download

The translation page shows the current phase and percentage. You can close the tab. The work continues, and AI Glot emails you when the result is ready.

There is no reliable wall-clock estimate, and we would rather say so than invent one. Duration depends on the number of translated items, their length, how many destinations there are and how often a provider needs retrying, not on file size. Use the live percentage for the job in front of you.

When it finishes, click Download. The result keeps everything outside the translated scope byte for byte: structure, ordering, identifiers, whitespace and every value the plan did not touch.

Resuming a session

A prepare session survives leaving the page. Reopening an unfinished translation returns you to the conversation with its file, its suggestions and its current plan intact. Nothing has to be described twice.

If you do not have enough credits

Eligible accounts may receive a free quality sample when the full estimate is at least 7,000 credits and exceeds the available balance. AI Glot targets about 5,000 credits, rounds to complete rows and caps the sample at 500 rows. Samples consume zero credits.