How can we help?

Getting started is simple:

1. Sign up for a free account.
2. Upload your audio or video file using drag and drop or the file picker.
3. Choose your mode and language. On a free account the default is Recommended: your whole recording in V4-Flash plus a preview in V4-Pro. V4-Flash can detect the language automatically; V4-Pro needs the language selected.
4. Follow the progress in My Drive. When uploading several files, expand the processing list to see each file's status.
5. Open your finished transcript to play the recording, edit the text, and export it.

Yes. A free account transcribes your whole recording in V4-Flash, our fast mode, with no daily limit and no cut-off. With the Recommended upload option you also get a preview of the same file in V4-Pro, our most accurate mode, up to 10 previews a week. File translation previews and Canvas are included. No credit card is required. See The Free Tier for details and the pricing page for paid plans.

For audio and video transcription, the uploader recognizes every extension listed below. Match the ending of your filename (for example, interview.mp3) to the extension column. Uppercase extensions such as .MP3 work too.

Audio formats

File extension	Full format name
.aac, .adts	Advanced Audio Coding, in an Audio Data Transport Stream
.ac3	Dolby Digital (Audio Coding 3)
.aif, .aiff	Audio Interchange File Format
.aifc	Compressed Audio Interchange File Format
.amr	Adaptive Multi-Rate audio
.ape	Monkey's Audio
.au, .snd	Sun / NeXT audio
.awb	Adaptive Multi-Rate Wideband audio
.bwf	Broadcast Wave Format
.caf	Apple Core Audio Format
.dss	Digital Speech Standard
.dts	Digital Theater Systems audio
.dtshd	Digital Theater Systems High Definition audio (DTS-HD)
.eac3, .ec3	Enhanced Audio Coding 3 (Dolby Digital Plus)
.flac	Free Lossless Audio Codec
.m4a	MPEG-4 Audio
.m4b	MPEG-4 Audiobook
.m4r	MPEG-4 Ringtone
.mka	Matroska Audio
.mp1	MPEG Audio Layer I
.mp2	MPEG Audio Layer II
.mp3	MPEG Audio Layer III
.mpa, .mpga	MPEG Audio
.oga, .ogg	Ogg Audio
.oma	Sony OpenMG Audio
.opus	Opus Audio in an Ogg container
.qcp	Qualcomm PureVoice audio container
.qta	QuickTime Audio
.rf64	RF64, the 64-bit extension of the Waveform Audio File Format
.spx	Speex Audio in an Ogg container
.tak	Tom's lossless Audio Kompressor
.tta	True Audio
.voc	Creative Voice
.w64	Sony Wave64
.wav, .wave	Waveform Audio File Format
.weba	WebM Audio
.wma	Windows Media Audio
.wv	WavPack Audio

Video formats

Video files must contain an audio track to transcribe.

File extension	Full format name
.3g2	Third Generation Partnership Project 2 multimedia format (3GPP2)
.3gp	Third Generation Partnership Project multimedia format (3GPP)
.asf	Advanced Systems Format
.avi	Audio Video Interleave
.flv	Flash Video
.m2ts, .mts	MPEG-2 Transport Stream used by Blu-ray and AVCHD recordings
.m4v	MPEG-4 Video
.mkv	Matroska Video
.mov	Apple QuickTime Movie
.mp4	MPEG-4 Part 14
.mpeg, .mpg	Moving Picture Experts Group video (MPEG-1 / MPEG-2)
.mxf	Material Exchange Format
.ogv	Ogg Video
.ts	MPEG Transport Stream
.vob	DVD Video Object
.webm	WebM Video
.wmv	Windows Media Video

Don't see your extension? Convert the recording to MP3, WAV, or MP4 before uploading, or contact support with the file extension and the app or device that created it. Renaming the extension does not convert a file.

The file must contain readable, unencrypted audio. A recognized extension alone does not guarantee that every codec or recording variant can be processed. Raw PCM files without audio metadata are not supported directly; export them as WAV first.

Cockatoo is designed to produce accurate transcripts across a wide range of languages, accents, and recording conditions. Clear speech produces the best results, and accuracy can vary with the language, background noise, and overlapping speakers.

V4-Pro is our most accurate mode; see the published benchmark results for each language. A free account includes a V4-Pro preview next to the full V4-Flash transcript, so you can compare the two on your own recording.

Transcription speed depends on the mode you choose:

• V4-Flash transcribes at approximately 120× real time. A one-hour recording takes about 30 seconds to transcribe.
• V4-Thinking transcribes at approximately 20× real time. A one-hour recording takes about 3 minutes to transcribe.

These are approximate transcription times; uploading and preparing your file, additional processing, and current demand can add to the total wait. My Drive shows each file's progress. If you're uploading several files, expand the processing list to see their individual statuses.

Recommended (free accounts) gives you both of the modes below on one upload: the whole recording in V4-Flash and a preview in V4-Pro. Each appears as its own tab in the transcript.

V4-Flash is designed for the fastest transcription turnaround. It's a good choice for quickly extracting insights from long recordings, reviewing meetings or lectures, and working through large amounts of audio. V4-Flash is unlimited on every plan, including Free. It does not identify speakers; you can tag them yourself in the editor.

V4-Pro is our most accurate mode and identifies speakers. Free accounts get a preview: the first half of the recording, up to 10 minutes, or the whole recording if it is shorter than 5 minutes. Paid plans transcribe the whole recording, within the plan's usage allowance.

V4-Thinking is designed for higher accuracy than V4-Flash when getting the wording right matters. It takes more time to process, has a weekly usage limit, and is available on paid plans.

Select your mode in the uploader before starting a transcription.

Yes. Open a completed transcript to:

• Edit words or sentences directly in the browser
• Play the recording alongside the transcript and jump to a timestamp
• Rename speakers, reassign text to another speaker, or tag speakers yourself on a V4-Flash transcript
• Switch between speaker, paragraph, and sentence views
• Export as PDF, DOCX, TXT, SRT, VTT, CSV, or JSON

Go to Settings → Billing and click Manage billing to open the billing portal. You can manage or cancel your subscription at any time.

Yes. Cockatoo Voice Notes for iOS lets you record voice notes and transcribe them. You can also access the website in your mobile browser.