en
Open studio

Speech to Text

From a recording to words you can use

Upload audio and get a transcript with speakers and word timings. Here is a real one.

Sample recording

Press play and follow along

Each word lights up as it is spoken, in the colour of the person speaking. Click any word to jump to it.

Team call, two speakersEnglish

0:24
  • Speaker 1
  • Speaker 2

  1. Speaker 10:00

    Thanks for joining. Let's start with the schedule for the launch.

  2. Speaker 20:03

    Sure. The studio is ready, and we plan to send the first invitations next week.

  3. Speaker 10:08

    Great. Can we confirm the voices for the French and Arabic versions?

  4. Speaker 20:13

    Yes, we picked two voices per language, and each one has a sample line.

  5. Speaker 10:17

    Perfect. I'll write the captions today and send them to the team.

  6. Speaker 20:21

    Sounds good. Let's meet again on Thursday to review everything.

0:24 · 2 speakers · 74 words

The recording was made with two Neurawaves voices, then transcribed by Speech to Text. Timestamps and speakers are switches in the studio.

Export

Subtitles, ready to export

The same transcript becomes captions you can use anywhere. This is the SRT file, following the audio above.

  • TXT
  • SRT
  • VTT
  • JSON
1
00:00:00,000 --> 00:00:00,960
Speaker 1: Thanks for joining.

2
00:00:01,440 --> 00:00:02,880
Speaker 1: Let's start with the schedule for the

3
00:00:02,880 --> 00:00:03,440
Speaker 1: launch.

4
00:00:03,520 --> 00:00:04,080
Speaker 2: Sure.

5
00:00:04,480 --> 00:00:06,720
Speaker 2: The studio is ready, and we plan to send

6
00:00:06,720 --> 00:00:08,480
Speaker 2: the first invitations next week.

7
00:00:08,640 --> 00:00:09,120
Speaker 1: Great.

8
00:00:09,520 --> 00:00:11,680
Speaker 1: Can we confirm the voices for the French

9
00:00:11,680 --> 00:00:12,800
Speaker 1: and Arabic versions?

10
00:00:13,200 --> 00:00:15,680
Speaker 2: Yes, we picked two voices per language,

11
00:00:15,920 --> 00:00:17,600
Speaker 2: and each one has a sample line.

12
00:00:17,760 --> 00:00:18,240
Speaker 1: Perfect.

13
00:00:18,560 --> 00:00:20,240
Speaker 1: I'll write the captions today and send

14
00:00:20,240 --> 00:00:20,960
Speaker 1: them to the team.

15
00:00:21,280 --> 00:00:22,080
Speaker 2: Sounds good.

16
00:00:22,480 --> 00:00:24,240
Speaker 2: Let's meet again on Thursday to review

17
00:00:24,240 --> 00:00:24,800
Speaker 2: everything.

You can also export plain text, VTT and JSON.

Try it in the studio

Everything you heard here is in the studio. Write your own line, pick a voice and hear it in seconds.

Open studio See pricing