Any Video to Text

Interview transcription,with every speaker labelled.

Upload an interview, podcast, meeting or phone call and get the transcript split by speaker: who said what, and when. Rename Speaker A and B to real names, then copy or download.

Speakers labelled: who said whatUp to 2 hoursRename Speaker A to a real nameTXT · SRT · VTT

What you get back

A real result: 77 seconds of a podcast, uncut, with speakers labelled and timestamped.

Reflections After Artemis II

Houston We Have a Podcast, NASA

Speakers labelled60:17EN
Gary Jordan But just to have that ascent go as clean as possible was truly.
Gary Jordan It was wonderful because you could kind of step into the magic a little bit instead of just worrying about what the problem
Jeremy Hansen there is. This aspect of having never flown on that vehicle before any of us.
Gary Jordan Yeah,
Jeremy Hansen you do have a lot of these moments of like, is that normal?
Jeremy Hansen And then you're like, oh, I guess it was because we're still.
Jeremy Hansen We're still alive. Yeah. But there is a lot of that.
Jeremy Hansen You know, the, The. The how long the thrust dropped off as we were getting rid of the solids kind of surprised me a little bit, what that
Jeremy Hansen felt like. Felt like we were carrying them maybe just a little longer than I anticipated.
Jeremy Hansen But in the sim, you never have those feelings. You never have the other inputs and, and those are the ones that.
Jeremy Hansen Cause your br. Like, okay, we're gonna be okay.
Gary Jordan Yeah,
Jeremy Hansen you have a lot of those going uphill,
Gary Jordan it's like playing like a. Like a race car video game with the steering wheel.
Gary Jordan Like, I mean, you can kind of get the feel of it, but you actually don't.
Gary Jordan Like, it's a totally different thing to be in the car.
Gary Jordan Right. You actually feel the road, you feel the wind.
Gary Jordan Not that I'm a race car driver, but I'm trying to equate it to just like normal driving and playing a video game. But,
Jeremy Hansen yeah, absolutely.
Gary Jordan What an experience. Just to hear it from your perspective.
Timestamps onCopy textTXTSRTVTT

Episode 441 of NASA's Houston We Have a Podcast. Public domain, from nasa.gov.

How do I transcribe an interview with speaker labels?

Sign in, tick Label speakers and drop the recording (MP3, M4A, WAV, MP4 or MOV) on the box on this page. You get the transcript split by speaker, with timestamps, and can rename Speaker A and B to real names. It costs 3 credits per 10 minutes; without names it's free up to 30 minutes.

PriceFree: 5 a day, no sign-up. Credits (no subscription): $5 for 200, $15 for 1,000, $39 for 5,000.
Works withMP3, M4A, WAV, AAC, OGG, FLAC and WebM audio; MP4, MOV and WebM video
LengthUp to 30 minutes free, up to 2 hours with credits (1 credit per 10 minutes)
HowWhisper speech recognition; the file stays on your device
SpeakersOptional speaker labels (who said what), renameable, 3 credits per 10 minutes
LanguagesAbout 100, detected automatically
ExportCopy, TXT, SRT or VTT, with or without timestamps
Sign-upNot needed. Google sign-in only to buy credits

How it works

  1. Upload the recording

    MP3, M4A, WAV, voice memos, Zoom, Teams or phone recordings, or a video (MP4, MOV). Up to 2 hours.

  2. Speakers are told apart

    AI speech recognition transcribes the audio and detects each voice, so every line is tagged Speaker A, Speaker B and so on.

  3. Name them and export

    Tap a speaker to rename them everywhere, then copy the text or download TXT, SRT or VTT with the names in it.

rice-speech.vttSubtitles
WEBVTT

00:09:03.000 --> 00:09:06.000
We choose to go to the moon.

00:09:06.000 --> 00:09:18.000
We choose to go to the moon in this decade and do the other things,

00:09:18.000 --> 00:09:22.000
not because they are easy, but because they are hard,
The same transcript as a VTT subtitle file (SRT too), ready for a video editor or YouTube.

Transcribe an interview with speaker identification

Drop the recording on the box above with Label speakers ticked. The whole recording is transcribed in one go, so the same voice keeps the same label from the first minute to the last. Each change of speaker starts a new paragraph with the speaker's name and the time.

A one-hour interview usually takes under a minute once the upload is done.

Who it's for

  • Journalists and writers: quote an interview accurately and find any answer by its timestamp.
  • Researchers: qualitative interviews, focus groups and user research sessions, ready to code and quote.
  • Podcasters: show notes, quotes and a readable transcript of host and guest.
  • Hiring and HR: job interviews and exit interviews, with each person's answers kept apart.
  • Meetings and calls: Zoom, Teams or Meet recordings and phone calls, with a record of who agreed to what.

Price

Speaker labels use credits: 3 credits per started 10 minutes. A 30-minute interview is 9 credits and a 1-hour interview is 18, so the $5 pack (200 credits) covers about 11 hours of interviews. If the transcript fails, the credits come back automatically.

Don't need names? Untick Label speakers for a plain transcript: free up to 30 minutes, 5 a day, no sign-up.

Privacy

With speaker labels the recording is sent in one piece to our speech provider and deleted there as soon as the transcript is back. We keep the labelled transcript for one day so you can reload the page, then it's gone. For videos already online, paste the link on the video to text converter; for plain audio, use the audio to text converter.

Questions

Still stuck? Email us.

How do I transcribe an interview with speaker names?

Sign in, tick Label speakers and drop the recording on the box. You get the transcript split by speaker (Speaker A, Speaker B…). Tap a speaker's name to rename them everywhere, then copy or download it.

How many speakers can it tell apart?

As many as are in the recording; two to five is typical for interviews, panels and meetings. Clear audio, with people not talking over each other, gives the best results.

What does it cost?

3 credits per started 10 minutes, so a 1-hour interview is 18 credits. Credits start at $5 for 200, with no subscription. Without speaker labels, transcripts are free up to 30 minutes.

Which files work?

MP3, M4A (iPhone voice memos), WAV, AAC, OGG, FLAC and WebM audio, plus MP4, MOV and WebM video such as Zoom or Teams recordings. Up to 2 hours.

Do the speaker names show up in the downloads?

Yes. The TXT and copied text put the name before each turn, and SRT and VTT subtitle files carry the speaker on every line.

Is my recording kept?

No. It is deleted at the speech provider as soon as the transcript is ready, and the labelled transcript is kept one day so you can reload the page.

Is it really free?

Yes. You get 5 free transcripts a day with no account and no watermark. If you need more, credits start at $5 for 200 transcripts, with no daily limit, videos up to 2 hours and a bulk tool for lists and whole channels. No subscription.

How accurate is the transcript?

When the video has captions we use them as they are, which is the most accurate option. When it doesn't, the audio is transcribed by AI speech recognition (Whisper), which handles accents, fast talk and background music well. Names and slang can still need a quick check.

Which languages work?

Speech-to-text works in about 100 languages and detects the language for you. Captions come in whatever language the creator or platform added.

Can I get timestamps or subtitles?

Yes. Turn on Timestamps to see the time of each line, or download the transcript as an SRT or VTT subtitle file for video editors and YouTube.

Do you store my videos?

No. We never download or keep the video. We keep the text transcript of public videos for 30 days so the next person who asks for the same video gets it instantly. Files you upload never leave your device: only their audio track is sent for transcription, and neither the audio nor the transcript is kept.

The Any Video to Text toolkit

Transcribe

Any public video, any platform.

Subtitles and recordings

Files in, files out.

Go further

When one transcript isn't enough.

Transcribe your interviews with speaker labels

Credits from $5 for 200, no subscription. Speaker labels use 3 credits per 10 minutes, so a 1-hour interview is 18 credits (about 45 cents on the $5 pack). Plain transcripts without names are free up to 30 minutes.

  • $5200 transcripts
  • $151,000 transcripts
  • $395,000 transcripts
See pricing