Captioning generates captions that are aligned with your audio track and include speech, music and background cues, to make your content inclusive. This article takes you through the whole journey: create the project, follow its jobs, review the captions and download them.
You provide: audio or video files, or your own caption files if you choose the Only Review workflow.
You get: captions in the source language that you can edit and download as VTT, SRT, TXT, CSV or JSON.
Review: yes, in the review editor.
Create a captioning project
- Select New in the left sidebar. On the Start a project page, select the Captioning card. Feltiv shows what the service does, the languages it supports and the file formats you can upload. Select Start Project.
[[IMAGE 1 - kb-screenshots/captioning/00-start-a-project-wide.jpg: the Start a project page. It also shows the Audio Description card, which is not ready to publish, so crop it out or retake the screenshot. Delete this line after you add the image.]]
- In Start a Captioning Project, choose a workflow. Captioning with AI generates same-language captions for your content from scratch using AI. Only Review skips AI generation, so you bring your own captions and use Feltiv for quality checking. If you already have captions, read Already have captions? Use Only Review below.
- Enter a Project Name. It must be 3 to 100 characters and cannot contain single or double quotes. You can add a short Description. Select Start.
[[IMAGE 2 - kb-screenshots/captioning/01-start-captioning-window.jpg: the Start a Captioning Project window. Delete this line after you add the image.]]
- On the create page, choose the Source Language and a Model. Both are required. The models you can choose depend on the language, and each one shows its price in credits, so you can see the cost before you create the project.
- Set the options you want, as described below.
- Add your audio or video files. Choose Upload (from your device), OneDrive, Google Drive, Amazon S3 or Azure BLOB. Each file must be under 2 GB, and you can upload up to 20 files at a time. The upload panel lists the supported file types, which are WAV, MP4, MPEG, MP3, MOV and MPG for captioning. See the article on uploading files for the upload messages.
- Select Create Project. Feltiv takes you to the project's details page.
Options that appear with Google Gemini models
When you choose a Google Gemini model, extra options appear on the create page. With other models they do not.
[[IMAGE 3 - kb-screenshots/captioning/02-create-page-gemini-options.jpg and 03-create-page-additional-configuration.jpg: the create page with a Gemini model selected. Delete this line after you add the images.]]
| Option | What it does |
| Instructions / Context | Background for the AI, such as the genre or character names, up to 2000 characters. Write a rough version and select Enhance to polish it with AI, free of charge. |
| Sound Cues | Includes non-speech sound cues, such as music and sound effects. Choosing a Gemini model ticks it for you, and you can untick it. |
| Transliteration in English | Converts text from any language into Latin characters while keeping the original pronunciation. For example, a Russian greeting becomes its Latin-letter spelling. |
| Additional configuration: Max CPL, Max CPL Tolerance, Max Lines | Characters per line, the allowed overrun, and lines per caption. |

Captioning gives captions in the same language as your audio. To get translated text, use the Subtitling service, or select Add Translation on a finished captioning job.
Already have captions? Use Only Review
Choose Only Review when you already have caption files and want them reviewed and quality-checked in Feltiv. You can have the review done by your own team or assign it to a professional QC vendor through the Feltiv QC Vendor Marketplace.
- Choose the Source Language. There is no model or option field in this workflow.
- Upload your media files first.
- Add one caption file for each media file, in SRT, XLSX or CSV format. Use the sample download links to see the layout.
- Every media file needs its captions before you can create the project.
Track your jobs
Open the project to see one row for each file. Use Group by Content or Group by Job to change the layout. Each row shows the model used, the credits debited for the job, a progress tag and a review status. Statuses, the progress tag and Retry work as described in the article on the project details page.
Review and complete
- When the review status shows that the AI output is ready, select Review. For an Only Review job, the editor opens your uploaded captions.
- Fix the text and timing with the tools in the review editor. In captioning, Re-generate also offers the Transliteration in English checkbox. The Speakers button shows every speaker in one place and lets you merge duplicates.
- If someone reviewed the file outside Feltiv, you can upload the reviewed SRT or VTT file back into the job, preview the changes, and confirm it as the Final version. See the article on the review editor.
- Select Mark as Complete and choose Language QC, Timecode QC or both.
To translate finished captions, select Add Translation on the job, or + Translation in the project header. Both need permission.
Download your captions
Select the download icon on the job and choose VTT, SRT, TXT, CSV or JSON. Include speakers is available when SRT is selected. See the article on downloading your output for the timecode, offset and cloud storage options.
Need help?
If a job fails again after a retry, write to support@feltiv.com with the project name and the file name.