Findable
Once the spoken words are on the episode page as text, both search engines and listeners can find the episode by searching for what was said.
Podcast and YouTube transcripts
A transcript for every episode and video you publish.
Upload the audio or video file for your episode or video to get a transcript with timestamps and speaker labels.
Live demo
Runs in your browser.
You can pull show notes and quotes from the text, and upload the SRT file as captions wherever you publish.
- Timestampsjump to any line in the audio
- Speakershost and guest separated
- SRT · TXT · DOCXcaptions and text from one transcript
- 100+languages transcribed
Why transcribe your show
Search engines can't index spoken audio, and listeners can't skim it. Putting the words on the page fixes both problems.
Accessible
Deaf and hard of hearing people, along with anyone who prefers reading, can follow the episode. Captions do the same job for video.
Reusable
You don't have to listen to the episode again just to pull quotes, write show notes, add chapter titles, or draft a newsletter.
What to export for podcasts and YouTube
One transcript gives you the files you need for different platforms.
For a podcast
Export a TXT or DOCX transcript to post on the episode page, with speaker names labeled so readers can tell the host and guest apart.
For YouTube
Export an SRT file to use as your video's captions. YouTube lets you upload subtitle files directly; check their help pages for the current steps.
For both
Use a summary for the description box, and use the timestamps to write your chapter titles.
How to transcribe an episode
Upload the file
Upload the audio or video file of your episode or video, or one you have the rights to use. Pick the language yourself or let KolWrite detect it.
Transcribe
You get the text with timestamps, plus speaker labels for conversations.
Fix names
Start by fixing guest names, brand names, and jargon. Then add the speakers' names so the text reads like a conversation.
Export
Download a TXT or DOCX file for your webpage, an SRT or VTT file for captions, and a summary for the description.
For developers and AI agents
You can also run everything KolWrite does with a recording through our API. Send the address of an audio or video file from your own code or an AI coding agent, and you'll get back the transcript with word timings, speaker labels, and an SRT file if you request one.
Word timings and speakers
The JSON output gives you the start and end time for every segment, plus individual word timings on models that support alignment. Turn on speaker separation to include a speaker label on each segment.
SRT and translation
Pass output_format as srt if you want subtitles directly from the API. If you are using the Oracle models, you can also set translate_to to get the text back in another language.
Built for agents
The API console publishes plain-text instructions for an agent to read before writing code. This includes agent-instructions.md, along with llms.txt, which links to the full reference.
Example request. The key comes from an environment variable, and the console has the full reference.
curl -X POST https://app.kolwrite.com/transcribe \
-H "x-api-key: $KOLWRITE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"audio_url": "https://example.com/episode.mp3", "model": "oracle", "include_diarization": true, "output_format": "txt"}'
# Returns {"jobId": "..."}. Poll GET https://app.kolwrite.com/transcribe/{jobId}
# until status is COMPLETED. The result is the file or the JSON you asked for.Questions
How do I get a transcript of my podcast episode?
Upload the episode's audio file to KolWrite and run the transcription. Once you fix any names or terms, you can export the text as a TXT or DOCX file. If you turn on speaker labels, the host and guest will be marked separately.
How do I make a transcript of a YouTube video?
If it's your video, upload the video or audio file to KolWrite to transcribe it. Since KolWrite works from uploaded files, you'll need the owner's permission before transcribing someone else's video.
How do I add captions to my YouTube video?
Download an SRT file from KolWrite, then go to YouTube Studio and upload it as a subtitle file for your video. Check YouTube's help pages for their current upload steps.
Can it tell the host and the guest apart?
Yes. Speaker separation keeps the timestamps and labels each voice, and you can fill in their actual names. It is a good idea to check the sections where people talk over one another.
Does it work for podcasts in Hebrew, Arabic or other languages?
Yes. KolWrite transcribes over 100 languages. That includes Hebrew and Arabic, with proper right-to-left layout.
Can I automate transcripts for a whole feed?
You can use the KolWrite API to have a script send each episode's address and save the resulting transcript and SRT file. You'll find the instructions in the API console.
Try it on one episode.
Upload your latest episode, export the transcript, and read through it once to see how much you can reuse.