Most audio and video formats
MP3, M4A, WAV, FLAC, OGG, AAC, OPUS and WebM audio, plus MP4, MOV and M4V video, up to 500 MB per file.
A free MP3 to text converter for podcasts, interviews and downloaded recordings.
To convert an MP3 to text, upload the file to Audio Notes AI in your browser and the full transcript is ready a minute or two later. It is made for podcasts, interviews, talks and any other MP3 with speech in it, and it adds a summary and key points.
Free account: 3 notes or 60 minutes. Works in Chrome, Edge, Safari and Firefox.
Welcome back to the show. Today we're talking about how small teams can run user interviews without a research budget. My guest has run more than two hundred of them, so let's start with the first question everyone asks: how many interviews are enough?
An episode on running user interviews on a small budget, starting with how many interviews a team needs.
Use your email or Google. It takes a minute, and the free account includes 3 notes or 60 minutes.
Or record in the browser. Long files are converted and sent in parts.
The transcript, a summary and action items, ready in about a minute. Download it as text.
MP3, M4A, WAV, FLAC, OGG, AAC, OPUS and WebM audio, plus MP4, MOV and M4V video, up to 500 MB per file.
An overview, key points and the to-dos, pulled from every recording.
Where do they talk about interview count?
Right at the start: the guest is asked how many interviews are enough.
Questions answered from the transcript, so you can find the part you need.
The transcript comes back in the language that was spoken, mixed-language speech included. Translate gives you a copy in another language.
An hour-long episode becomes searchable text: copy a quote, check what a guest said, or turn the interview into show notes. The summary and key points give you a first draft of the episode description, and Ask answers questions like "where do they talk about pricing?" from the transcript. More in our guide to transcribing interviews.
MP3 files up to 24 MB are sent as they are. Bigger files, up to 500 MB, are converted to compact speech audio in your browser first and sent in parts, so a long recording does not stall on a slow connection. On a free account a file can be as long as the minutes you have left (60 minutes in total); with Pro, up to 90 minutes per file.
Recorded on an iPhone? See M4A to text. Have a video instead? See MP4 to text.
Audio is sent over an encrypted connection, transcribed, and deleted from our servers after processing, always within 24 hours. Your notes are kept in your browser.
Updated
Yes. A free account includes 3 notes or 60 minutes of transcription in total. That is enough for a full podcast episode or a long interview.
Usually under a minute for a short file and a few minutes for an hour of audio. You can leave the tab in the background while it works.
Yes. It recognises 60+ languages and writes the transcript in the language that was spoken. Translate gives you a copy in another language.
Files up to 500 MB. Free accounts can transcribe up to the minutes they have left; Pro allows up to 90 minutes per file.
It is built for speech. Song lyrics over loud music come out poorly, and instrumental music produces no text.
Free account, transcript in about a minute.