Audio & Video Transcriber - Speech to Text With Timestamps
Pricing
from $17.50 / 1,000 audio minute transcribeds
Audio & Video Transcriber - Speech to Text With Timestamps
Transcribe any public audio or video file URL — MP3, M4A, WAV, MP4, WebM and more — into timestamped passages with Whisper running inside the Actor. No API key, nothing sent to a third-party speech service. 20 languages. Pay per minute of audio transcribed.
Pricing
from $17.50 / 1,000 audio minute transcribeds
Rating
0.0
(0)
Developer
Kobkoon Janngam
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
11 hours ago
Last modified
Categories
Share
Audio & Video Transcriber — speech to text with timestamps
Turn any public audio or video file into text. Paste links to MP3, M4A, WAV or MP4 files and get the transcript back as timestamped passages. Each passage is about 30 seconds of speech with its start and end time, so you can cite it, search it or feed it to an AI agent. The transcription is done by Whisper inside the Actor: there's no API key and nothing is sent to a speech service.
Quick start: press Start with no configuration. It transcribes the first 3 minutes of two short news podcasts. Then paste your own file links.
Sample output
| startTime | text |
|---|---|
| 0:00 | Welcome to NASA Daily, where we bring you all of NASA's previous days' proceedings in four minutes or less… |
| 0:25 | NASA's Dragonfly mission completed its most comprehensive simulated flight on Saturn's Moon Titan… |
| 0:55 | Its research archive remains publicly available. The Near Earth Object Surveyor completed testing… |
| 1:22 | Meanwhile, cyclone Arnob struck India with winds around 130 kilometers per hour… |
These rows come from the default run on 31 October 2026.
Every row also carries:
mediaUrlandfileNamepassageandpassageCountstartSecondsandendSecondstranscribedSecondslanguagestatus- a plain-English
notewhen something needs explaining
What you can do with it
- Make meetings, webinars and interviews searchable. Each passage has a timestamp, so a match takes you to the right moment.
- Give an AI agent the audio. It gets text in passages that fit its context, instead of a file it cannot hear.
- Write show notes, quotes and summaries from a recording without listening to the whole thing.
- Build a RAG index from audio. Each passage is a ready-made chunk.
Input
| Field | Default | Notes |
|---|---|---|
mediaUrls | 2 samples | Direct file links: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WebM. Up to 100 per run, and each must open without signing in. |
language | en | The spoken language. 20 are supported, including Spanish, German, Japanese, Chinese, Arabic, Hindi and Thai. |
maxMinutesPerFile | 60 | Transcribe at most this many minutes from the start of each file. You pay only for minutes transcribed. |
passageSeconds | 30 | The length of each passage, from 10 to 300 seconds. |
Only the minutes you ask for are read. A two-hour file with a 10-minute limit streams only its first 10 minutes. It is not downloaded in full.
Every file gets an answer
| status | Meaning | Charged |
|---|---|---|
ok | Transcribed, one row per passage | Yes, per started minute |
no-speech | The audio has no recognisable speech | Yes, per started minute (the audio was processed) |
not-media | The link is a web page, or the file has no audio track | No |
download-failed | The link is dead or private | No |
One bad link never fails the run. The run respects your spending limit: it stops before a minute it cannot charge for.
Good to know
- Page links are not files. For YouTube and similar sites, use a tool built for that site. This Actor needs the file's own URL.
- Set the language for non-English audio. Whisper transcribes in the language you choose. It does not detect it.
- Accuracy is that of Whisper base. It is very good for clear speech and podcasts, and weaker for heavy accents, crosstalk and music.
Pricing
You pay per started minute of audio transcribed. Links that fail and web pages cost nothing.
Works well with
Same publisher, same output conventions, same honest-failure rules:
- podcast-transcriber — Type a podcast name, get its latest episodes as timestamped text.
Disclaimer
This Actor reads only the files you link to. It scrapes no website and calls no third-party API: the speech model runs inside the Actor. Make sure you have the right to transcribe the recordings you submit.
