Captions/Subtitles

Downloading Captions/Subtitles have the following options, some of which are for advanced users or require the usage of specific models.

Enhanced SRT Captions and Word Level Timestamps require transcribing using the Whisper, Qwen, and Cohere models. Gemini cannot render these subtitle styles due to limitations in the model.

Enhanced SRT captions (.srt)

• Manual edits on the View Transcription page will not be applied to Enhanced SRT captions.

• This style of captions requires transcribing with the OpenAI Whisper, Qwen3-ASR, or Cohere Transcribe model.

Enhanced SRT captions are word-level, meaning that each word has a timestamp to display subtitles timely at the cost of having to edit the subtitles within your video editing software.

Before downloading, you have the following options to alter how the captions are created:

• Max characters per line: How many characters are shown per line of caption. Long subtitles can be smaller and harder to read, while short subtitles may move on too quickly to read.

• Max lines per caption: How many lines of text to present at a time. Typically this is always 2 lines or less, depending on context of conversation.

Word-Level Timestamps (.json)

• Manual edits on the View Transcription page will not be applied to Enhanced SRT Captions.

• This style of captions requires transcribing with the OpenAI Whisper, Qwen3-ASR, or Cohere Transcribe model.

Word-Level Timestamps, similar to Enhanced SRT Captions, are word-level, meaning that each word has a timestamp to display subtitles timely at the cost of having to edit the subtitles within your video editing software.

This download creates a .json file instead of a .srt file, designed for certain software or manual editing of these captions.

Additional Options

The "Group Sentences" option is disabled for all caption-styled exports as sentence grouping is not relevant for subtitle generation.

Including Speaker Names in Captions

Each caption export has the ability to include speaker names. Simply select "Include Speaker Names" in the "Download Transcription" options before pressing Download.

Word-Level Timestamps (.json) always has the "Speaker Names" option engaged.