Skip to main content
AI Speech to Text turns recordings into text: meetings, interviews, podcasts, lectures, calls, and videos. The transcript shows who said what and when, and you can turn it into summaries, notes, and posts with AI Content.
1

Choose a source

Click AI Speech to Text in the sidebar, then Upload new.
Source options: Transcribe a YouTube Video, an Instagram Video, a TikTok Video, a Google Drive File, Import URL, Transcribe an Uploaded File, Record Audio, and Integrate with Zapier
2

Add the file or link

For a file, drag it in or click to choose it. Audio: MP3, M4A, WAV, FLAC, OGG, AAC, Opus, WMA. Video: MP4, MOV, WebM, AVI, MKV, FLV.
The upload form with front-desk-call.mp3 uploaded, Type of Audio Phone Call, Language spoken in the audio English, and Detect Speakers on
3

Set the options

Options: Detect Speakers on, Speakers expected 2, Enhanced Quality Transcription, Redact Personal Identifiable Information (PII), Specialized Terminology, Use Transcription 2.0 on, and a Transcribe button
Specialized Terminology and Enhanced Quality Transcription currently only affect the older engine, used when Use Transcription 2.0 is off.
4

Click Transcribe

The file uploads and transcription starts. Short recordings are done in a minute or two; long ones can take 10 to 20 minutes. You can leave the page; you’ll get an email when it’s ready.
The transcript page for front-desk-call.mp3 with the Transcription, AI Content, and AI Chat tabs and the message Transcription is in progress
Then read and work with the transcript.

​
YouTube videos

When a YouTube video has captions, the transcript is ready in seconds as plain text, without speakers or timestamps, and subtitle downloads aren’t available. Videos without captions are transcribed like a file, with speakers and timestamps.

​
Your transcriptions

AI Speech to Text lists your transcriptions, 20 per page, each with its status: Processing, Transcribed, No speech, or Failed. Click one, or Edit, to open it.
The AI Transcription page with Record Audio and Upload new buttons, and one item, Front desk call, marked Transcribed
On a Teams plan, transcriptions teammates share with the team appear here too.

​
If a transcription fails

  • Failed items are retried automatically. You can also open one and click Retry transcription; your file is kept.
  • No speech means no speech was found, for example a recording with the microphone muted. Check the recording and upload it again.

​
Dictate into a text box

The microphone button in Marky, the tools, and AI Images types what you say into the text box. Dictation doesn’t use transcriptions.

​
What it costs

Each new item uses one transcription from your plan, whatever its length. An item counts when you pick a source or start a recording, even if you don’t finish it or delete it later. Retries don’t count again. Check your usage on Settings > Usage and see Audio plans and limits. AI Content and AI Chat use words.

​
For developers

Transcribe from your own code with POST /api/transcriptions, which needs a paid plan. See Create transcription.

Work with a transcript

Speakers, subtitles, AI Content, and AI Chat.

Record & Transcribe

Record a meeting in your browser.