From ab24ef5c48a8a0b535b7883a6c444b9f19e9fba4 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Sat, 24 Jan 2026 19:32:45 +0000 Subject: [PATCH] Add FAQ for generating SRT/VTT captions with speaker labels Co-Authored-By: Lee Vaughn --- fern/docs.yml | 3 +++ .../export-srt-or-vtt-caption-files.mdx | 12 ++++++++++++ ...erate-srt-or-vtt-captions-with-speaker-labels.mdx | 9 +++++++++ 3 files changed, 24 insertions(+) create mode 100644 fern/pages/faq/async/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels.mdx diff --git a/fern/docs.yml b/fern/docs.yml index c5267e95..fbab6d7d 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -1110,6 +1110,9 @@ navigation: - page: Does it cost extra to export SRT or VTT captions? path: pages/faq/async/does-it-cost-extra-to-export-srt-or-vtt-captions.mdx slug: /does-it-cost-extra-to-export-srt-or-vtt-captions + - page: Is there a way to generate SRT or VTT captions with speaker labels? + path: pages/faq/async/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels.mdx + slug: /is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels - page: Does it cost more to transcribe an audio or video? path: pages/faq/async/does-it-cost-more-to-transcribe-an-audio-or-video.mdx slug: /does-it-cost-more-to-transcribe-an-audio-or-video diff --git a/fern/pages/02-speech-to-text/pre-recorded-audio/export-srt-or-vtt-caption-files.mdx b/fern/pages/02-speech-to-text/pre-recorded-audio/export-srt-or-vtt-caption-files.mdx index 37ae26a6..af891852 100644 --- a/fern/pages/02-speech-to-text/pre-recorded-audio/export-srt-or-vtt-caption-files.mdx +++ b/fern/pages/02-speech-to-text/pre-recorded-audio/export-srt-or-vtt-caption-files.mdx @@ -583,3 +583,15 @@ file_put_contents("transcript_" . $transcript_id . ".vtt", $vtt_response); ``` + +## Additional resources + + + + Learn how to create caption files that include speaker identification. + + diff --git a/fern/pages/faq/async/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels.mdx b/fern/pages/faq/async/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels.mdx new file mode 100644 index 00000000..20c148ed --- /dev/null +++ b/fern/pages/faq/async/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels.mdx @@ -0,0 +1,9 @@ +--- +title: "Is there a way to generate SRT or VTT captions with speaker labels?" +--- + +The [export captions endpoint](/docs/api-reference/transcripts/get-subtitles) does not include speaker label information by default, but you can generate captions with speaker labels using the information from the JSON response for the completed transcript. + +When you enable [Speaker Diarization](/docs/speech-to-text/pre-recorded-audio/speaker-diarization) in your transcription request, the response includes speaker information for each word and utterance. You can use this data along with the word-level timestamps to build custom SRT or VTT files that include speaker identification. + +See the [Create Subtitles with Speaker Labels](/docs/guides/speaker_labelled_subtitles) cookbook for a step-by-step guide on how to accomplish this.