> For the complete documentation index, see [llms.txt](https://evidano.gitbook.io/ailyze-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://evidano.gitbook.io/ailyze-docs/reference/supported-file-types.md).

# Supported File Types

What each Evidano workflow accepts as input and produces as output.

This page lists what each Evidano workflow accepts as input and what it gives you back.

Last verified against the staging app: 2026-10-14.

## Inputs by workflow

### [Document analysis](/ailyze-docs/getting-started/analyze-your-first-transcript.md)

* **Accepts:** `docx`, `pdf`, `txt`
* **Limit:** up to **50 files** per project, with the option to pay for more files per project
* Unlimited projects
* **Tip:** Text-based (not scanned) PDFs and DOCX files give the cleanest results.

### [Spreadsheet analysis](/ailyze-docs/getting-started/analyze-your-first-survey-dataset.md)

* **Accepts:** `xlsx`, `csv`
* **Limit:** **1 file** per project, \~**5,000 rows**, with the option to pay for more rows per project
* Unlimited projects
* **Shape:** one row per respondent, one column per question.

### [Transcribe audio/video](/ailyze-docs/prepare-research-data/transcribe-audio-and-video.md)

* **Accepts (audio):** `3ga, 8svx, aac, ac3, aif, aiff, alac, amr, ape, au, dss, flac, flv, m4a, m4b, m4p, m4r, mp3, mpga, ogg, oga, mogg, opus, qcp, tta, voc, wav, wma, wv`
* **Accepts (video):** `mp4, mov, wmv, mkv, webm, mpeg, mpg, m4v, 3gp, 3g2`
* **Limit:** up to **5 GB** per file and up to **1,000 files** per project.

### [Translate files](/ailyze-docs/prepare-research-data/translate-files.md)

* **All languages (Good and Best accuracy):** `docx`, `pptx`, `xlsx`, `html`, `txt`
* **Best-accuracy languages only:** `pdf`, `xliff`, `srt`
* **Limit:** up to **10 files**, **1,000,000 characters** each.
* **Note:** `csv` is **not** accepted for translation (it is accepted for analysis).

### [Image to Text](/ailyze-docs/prepare-research-data/convert-images-and-pdfs-to-text.md)

* **Accepts (images):** `png`, `jpg`, `jpeg`, `webp`, `heic`, `heif`, `bmp`, `tiff`
* **Accepts (documents):** `pdf`. Each PDF becomes its own project and is split into one image per page.
* **Limit:** up to **100 images** per project, or **100 PDFs** per upload. Images and PDFs cannot be mixed in one project.
* **Tip:** Photograph pages in even light with the page filling the frame. The model cannot read what the camera did not capture.

### [AI Detection](/ailyze-docs/analyze-data/detect-ai-written-text.md)

* **Accepts:** `txt`, `md`, `markdown`, `pdf`, `docx`, `csv`, `xlsx`, `xls`, or pasted text
* **Limit:** up to **20 MB** per file; up to **200 files** per bulk run. Scanned PDFs without selectable text cannot be read.
* **Note:** Files are read in your browser and never uploaded.

### [Get Social Media Web Data](/ailyze-docs/collect-research-data/collect-social-media-and-web-data.md)

* **Input:** URLs (pasted, one per line) or a `csv`/`xlsx` file with URLs in one column.

### Create [Survey](/ailyze-docs/collect-research-data/create-a-survey.md) or [AI Avatar Interviewer](/ailyze-docs/collect-research-data/create-an-ai-avatar-interviewer.md)

* **Input:** built in the app (no file upload needed).

## Outputs by workflow

| Workflow                  | Output                                                                                                                                                               |
| ------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Analyze docx/pdf          | On-screen report; export **DOCX** or **XLSX**; a **ZIP** per section (DOCX, XLSX, and chart images); **CSV** for the codebook and tables; invite collaborators       |
| Analyze xlsx/csv          | On-screen dashboards; export **DOCX**, **CSV**; chart **CSV/PNG**; invite collaborators                                                                              |
| Transcribe                | Editable transcript; download **DOCX**, **XLSX**, **SRT**, **VTT**, or **TXT** (translations too)                                                                    |
| Translate files           | Translated file in the **same format** as the input; multiple files as a ZIP                                                                                         |
| Image to Text             | Editable text per page; download the original image, **DOCX** for one page or the whole PDF, **XLSX** per page, a project **Spreadsheet**, or a ZIP of several pages |
| AI Detection              | On-screen score and highlights; export **HTML** report, **JSON** scores, **TXT** summary, or print to **PDF**; bulk **CSV**, **XLSX**, or a ZIP of HTML reports      |
| Get Social Media Web Data | **ZIP**: **XLSX**, **JSON**, and **CSV** per social or structured URL, one **DOCX** per general web page                                                             |
| AI Avatar Interviewer     | Survey answers as **XLSX**; interview transcripts as **DOCX**, **XLSX**, **SRT**, **VTT**, or **TXT**; recordings                                                    |

## Cross-workflow conversions

* **Audio or video → text:** Transcribe, then analyze the transcript.
* **Pictures of pages → text:** Image to Text, then upload the DOCX or spreadsheet to an analysis.
* **Foreign-language file → your language:** Translate, then analyze.
* **Web content → dataset:** Collect, download the ZIP, then re-upload it to an analysis.

## Next steps

* [Upload and manage files](/ailyze-docs/getting-started/upload-and-manage-files.md) — how to add files to a project.
* [Supported Languages](/ailyze-docs/reference/supported-languages.md) — which languages you can transcribe, translate, and analyze.
* [Plans, Limits & Credits](/ailyze-docs/reference/plans-limits-and-credits.md) — file counts, sizes, and costs.