How to get audio to text with timestamps
Audio to text with timestamps takes four steps here: choose the recording, pick its language, press Transcribe and switch the result to Timestamps. The SRT and VTT buttons save the same lines as caption files, numbered and timed, ready for YouTube, Premiere Pro, CapCut or a video player.
- Choose the audio or video
Pick an MP3, M4A, WAV, MP4 or MOV file up to 120 minutes. The length and credit price appear before upload.
- Pick the language
Auto-detect works for most single-language files; choosing the language helps short or noisy clips.
- Transcribe
Tick the consent box and press Transcribe. Parts of up to 2 minutes are timed separately and joined on one timeline.
- Download SRT or VTT
Use the Timestamps view to check the times, then download SRT (most editors and YouTube) or VTT (web players).
Timestamped transcript examples
The timestamped transcript examples below are four public-domain clips under a minute long, each shown with the line-by-line times the open-source Whisper large-v3-turbo model gave offline. Times are where each spoken line starts; nothing was corrected by hand. TranscribeBolt runs the same model on Cloudflare Workers AI, with different settings, so its times and wording for the same clip can differ.
1962 Moon speech at Rice University (outdoor stadium, applause)
A 60-second stretch of an outdoor speech with crowd noise and applause. The famous lines came through, but "We choose to go to the moon" appears one time more than it was said, and "postpone" came out as "postponed".
[00:00] may never come again. But why some say the moon? Why choose this as our goal? And they may well ask, [00:10] why climb the highest mountain? Why 35 years ago fly the Atlantic? Why does Rice play Texas? [00:18] We choose to go to the moon. We choose to go to the moon. [00:23] We choose to go to the moon in this decade and do the other things, not because they [00:34] are easy, but because they are hard. [00:38] Because that goal will serve to organize and measure the best of our energies and skills. [00:45] Because that challenge is one that we're willing to accept, one we are unwilling to [00:50] postponed and one we intend to win and the others too.
Apollo 13 air-to-ground radio (two speakers, static)
A 40-second radio exchange between the crew and Mission Control. Each radio call became its own short line, but nothing says who is speaking, and "main B bus undervolt" came out as "main B plus undervolt".
[00:00] Okay, Houston, we've had a problem here. [00:04] This is Houston, say again, please. [00:07] Houston, we've had a problem. [00:09] We've had a main B plus undervolt. [00:12] Roger, main B undervolt. [00:15] Okay, stand by 13, we're looking at it. [00:19] Okay, right now, Houston, the voltage is looking good. [00:25] And we had a pretty large bang associated with the caution and warning there. [00:33] And as I recall, main D was the one that had an amp spike on it once before.
Space-station podcast interview (two voices, studio sound)
A 56-second studio interview, host then guest. The show name "Houston We Have a Podcast" was split into a sentence, long answers became long lines, and a one-word line at 0:00 is left over from where the clip was cut.
[00:00] Yeah. [00:02] Tracy, welcome to Houston. We have a podcast. We are so happy to have you here. [00:06] Thank you. It's my pleasure. [00:08] So before we get into the topic of the space station, I want our listeners to get to know you. [00:13] So tell us a little bit about you, your background, and maybe when you joined NASA, [00:19] what things were like at that time. What was human spaceflight exploration looking like at that time? [00:23] I should go back to the year of 1997. I had finished up my PhD and submitted my dissertation in the month of June. And I think it was the next month, July, when I submitted my application for the astronaut program. [00:39] And then I went on and did a postdoctoral fellowship in Southern California at UC Irvine, and it was during that period of time that I got the notice that I was being offered an interview. [00:54] And so that kicked it off.
1941 address to Congress (old radio recording)
A 57-second clip of a scratchy 1941 broadcast with slow, formal delivery. Long pauses split the speech into short timestamped lines; the opening dropped the "and" in "and of the House of Representatives".
[00:00] Mr. Vice President, Mr. Speaker, members of the Senate, of the House of Representatives, [00:10] yesterday, December 7, 1941, a date which will live in infamy, [00:23] the United States of America was suddenly and deliberately attacked [00:29] by naval and air forces of the Empire of Japan. [00:36] The United States was at peace with that nation [00:40] and at the solicitation of Japan [00:45] was still in conversation with its government and its emperor [00:51] looking toward the maintenance of peace in the Pacific.
Can you get audio to text with timestamps for free?
No, audio to text with timestamps is not free: new accounts get no free credits right now, so a credit pack is needed before the first transcript. After that every file costs 2 credits per started minute with a 5-credit minimum, so 10 minutes is 20 credits, about $0.20. The smallest pack is $9.90 for 900 credits (about 450 minutes). Choosing a file and seeing its price costs nothing, and the text has no watermark.
How do you convert audio to text as an SRT file?
To convert audio to text as an SRT file, transcribe the recording and press the SRT button under the result. Each caption gets a number, a start and end time (hours:minutes:seconds,milliseconds) and its line of text. VTT is the same idea for web players: it starts with a WEBVTT line and uses a dot before the milliseconds.
1 00:00:00,000 --> 00:00:03,800 Okay, Houston, we've had a problem here. 2 00:00:04,600 --> 00:00:06,100 This is Houston, say again, please.
Upload the SRT to YouTube Studio under Subtitles, or import it into Premiere Pro or CapCut as a caption track.
Timestamped transcript pricing
A timestamped transcript costs the same as plain text on TranscribeBolt: 2 credits per started minute with a 5-credit minimum, and the SRT and VTT downloads are included. A 10-minute video is 20 credits (about $0.20) and a 60-minute podcast is 120 credits. From a zero balance the smallest purchase is the $9.90 Starter pack (900 credits, about 450 minutes), a one-time payment.
| Audio length | Credits | Price | Watermark |
|---|---|---|---|
| Up to 1 minute | 5 | $0.05 | None (text only) |
| 3 minutes | 6 | $0.06 | None (text only) |
| 10 minutes | 20 | $0.20 | None (text only) |
| 30 minutes | 60 | $0.60 | None (text only) |
| 60 minutes | 120 | $1.20 | None (text only) |
| 120 minutes | 240 | $2.40 | None (text only) |
Price at $0.01 per credit (Pro pack). Smaller packs cost slightly more per credit.
| Pack | Price | Credits | Covers |
|---|---|---|---|
| Starter | $9.90 | 900 | ≈ 450 minutes of audio (7.5 hours) |
| Plus | $24.90 | 2,400 | ≈ 1,200 minutes of audio (20 hours) |
| Pro | $49.90 | 4,990 | ≈ 2,495 minutes of audio (41.6 hours) |
Where the timestamps fall short
Audio to text timestamps here are per line, not per word, so you cannot build word-by-word karaoke captions from them. Lines can run long when someone talks without pausing, and the times can drift by a fraction of a second around music, laughter or long silence. There are no speaker labels in the SRT, and captions are not burned into the video.
- Timing: one start and end time per spoken line, not per word.
- Line length: long unbroken speech gives long captions; split them in your editor if needed.
- Drift: check the first and last captions against the video before you publish.
- No burned-in captions: you get SRT/VTT files, not a new video.
Timestamps FAQ
Do the timestamps line up across a long file?
Yes. Long files are sent in parts of up to 2 minutes, and each part starts at its exact offset in the original recording, so the times in the SRT count from the start of your file.
Can I edit the captions before downloading?
Not on this page; the download is exactly what Whisper returned. Open the SRT in a caption editor such as Subtitle Edit, YouTube Studio or your video editor to fix wording or split long lines.
Will the SRT work on YouTube and in CapCut?
The file uses the standard SubRip layout (number, time range, text, blank line) with UTF-8 text, which YouTube Studio, Premiere Pro and CapCut import. Use VTT for HTML5 video players.