01
Guide the AI
Choose the spoken language or automatic detection, identify speakers, and add context or key terms for names and specialist vocabulary.
Transcribe Audio and Video to Text You Can Review
Transcribe audio to text or convert video to text with AI transcription. Review uncertain phrases against the source media, rename speakers, and export TXT, Markdown, SRT, or VTT.
No credit card required
TRANSCRIPTION
Turn every recording into usable text
Upload one audio or video file and follow its progress from your browser.
Transcription settings
HOW IT WORKS
AI transcribes. You review what matters.
Guide the AI before transcription, then check uncertain phrases against the source media, save your corrections, and export the latest revision.
Basic converter
File → AI-generated text → Download
Transcribe to Text
Guide → Transcribe → Review → Save → Export
02
Generate the AI draft
Upload a supported audio or video file. AI generates a structured transcript draft with timestamps and speaker labels when enabled.
03
Review what matters
Use the low-confidence review queue to play the matching moment, edit the segment, mark phrases reviewed, and rename speakers.
04
Save and export
Corrections save as a new revision. Export the latest transcript as TXT, Markdown, SRT, or VTT.
LANGUAGE COVERAGE
Transcribe speech in 99 languages
Choose the recording’s spoken language, or use automatic detection when you are unsure.
102 selectable recognition options
99
supported languages
English recognition options
English includes General, Australia, United Kingdom, and United States options.
- English
- español
- français
- Deutsch
- português
- العربية
- हिन्दी
- বাংলা
- 中文
- 日本語
- 한국어
- русский
- ไทย
- Türkçe
- Tiếng Việt
- Kiswahili
View all 99 languagesHide the full language list
- Englishen · en_au · en_uk · en_us
- Spanishes
- Frenchfr
- Germande
- Italianit
- Portuguesept
- Dutchnl
- Afrikaansaf
- Albaniansq
- Amharicam
- Arabicar
- Armenianhy
- Assameseas
- Azerbaijaniaz
- Bashkirba
- Basqueeu
- Belarusianbe
- Banglabn
- Bosnianbs
- Bretonbr
- Bulgarianbg
- Burmesemy
- Catalanca
- Chinesezh
- Croatianhr
- Czechcs
- Danishda
- Estonianet
- Faroesefo
- Finnishfi
- Galiciangl
- Georgianka
- Greekel
- Gujaratigu
- Haitian Creoleht
- Hausaha
- Hawaiianhaw
- Hebrewhe
- Hindihi
- Hungarianhu
- Icelandicis
- Indonesianid
- Japaneseja
- Javanesejw
- Kannadakn
- Kazakhkk
- Khmerkm
- Koreanko
- Laolo
- Latinla
- Latvianlv
- Lingalaln
- Lithuanianlt
- Luxembourgishlb
- Macedonianmk
- Malagasymg
- Malayms
- Malayalamml
- Maltesemt
- Māorimi
- Marathimr
- Mongolianmn
- Nepaline
- Norwegianno
- Norwegian Nynorsknn
- Occitanoc
- Punjabipa
- Pashtops
- Persianfa
- Polishpl
- Romanianro
- Russianru
- Sanskritsa
- Serbiansr
- Shonasn
- Sindhisd
- Sinhalasi
- Slovaksk
- Sloveniansl
- Somaliso
- Sundanesesu
- Swahilisw
- Swedishsv
- Filipinotl
- Tajiktg
- Tamilta
- Tatartt
- Telugute
- Thaith
- Tibetanbo
- Turkishtr
- Turkmentk
- Ukrainianuk
- Urduur
- Uzbekuz
- Vietnamesevi
- Welshcy
- Yiddishyi
- Yorubayo
TRANSCRIPTION CAPABILITIES
Audio and video transcription you can review
A practical workspace for supported media, synchronized review, saved corrections, and reusable transcript exports.
Upload MP3, WAV, M4A, AAC, FLAC, OGG, or OPUS audio directly to private storage, then follow processing from the browser.
MP4, MOV, AVI, MKV, MPEG/MPG, and WebM are accepted for transcribing the spoken audio inside a video.
Clear speech, a good microphone, limited background noise, and fewer overlapping voices generally produce more useful text. Important names, quotations, and decisions should still be reviewed.
Authenticated, user-scoped storage and short-lived playback links keep media private. Delete it immediately or let the seven-day review window expire while keeping the transcript and exports.
TRANSCRIPTION USE CASES
Ways to use audio and video transcripts
Teams and Project Work
Meeting Transcription
A meeting transcript creates a written reference for decisions, project context, and follow-up after the conversation.
Journalists and Researchers
Interview Transcription
An interview transcript makes recorded answers easier to review, quote, compare, and organize during research or reporting.
Creators and Producers
Podcast Transcription
A podcast transcript can support show notes, episode archives, accessibility work, and content repurposing.
Students and Educators
Lecture Transcription
A lecture transcript gives students and educators a text reference for classes, webinars, and training recordings.
Editors and Marketers
Video Transcription
A video transcript turns spoken dialogue into source text for scripts, editing notes, captions, and content review.
Sales and Support Teams
Customer Call Transcription
A customer call transcript helps sales, support, and research teams revisit questions, feedback, and conversation context.
Flexible pricing for every workload
1 credit equals 1 minute. Every credit you receive or purchase is yours until you use it.
Free credits for your first transcription, or predictable capacity with monthly and annual billing.
TRANSCRIPTION FAQ
Questions about transcribing audio and video to text
Choose a supported audio file, set its spoken language and optional speaker labels, then start transcription. When processing finishes, open the review workspace to listen, correct segments, rename speakers, and export the latest saved revision.
Yes. Upload a supported MP4, MOV, AVI, MKV, MPEG/MPG, or WebM file and the service transcribes its spoken audio. You can review the result against the source video during the media retention window.
Supported files are AAC, AVI, FLAC, M4A, MKV, MOV, MP3, MP4, MPEG/MPG, OGG, OPUS, WAV, and WebM, up to 5 GB per file. A matching filename extension and media content type are required.
Audio clarity, microphone quality, background noise, accents, specialist terms, and overlapping speech can affect the result. The review queue groups lower-confidence phrases so you can replay and correct them; confidence is not presented as an accuracy guarantee.
Files upload directly to private, user-scoped storage. Source media remains available for review for up to seven days from task creation and can be deleted immediately. After deletion or expiry, the transcript, saved edits, history, and exports remain available without playback.
Transcribe to text means turning the spoken audio in a recording into written text. Upload a supported audio or video file, choose the spoken language and optional speaker settings, then review the saved transcript before exporting it.
Processing time depends on the recording length, media format, and audio complexity. The workbench shows the task status while transcription continues in the background; it does not promise a fixed completion time.
You can choose a known spoken language or use automatic detection when you are unsure. The language picker follows the languages currently supported by the transcription workflow, and the result should still be reviewed when the recording is difficult.
Yes. You can let the workflow detect speakers or provide a speaker count range, then rename speakers while reviewing the transcript. Clear turn-taking produces more useful labels than overlapping speech.
Yes. Add optional context or key terms before transcription when a recording contains specialist language. After processing, open the transcript, replay the source media, edit segments, correct low-confidence phrases, and save the latest revision before exporting.
Completed transcripts can be exported as TXT, Markdown, SRT, or VTT. TXT and Markdown are useful for documents and notes, while SRT and VTT preserve timing for subtitle workflows.
New accounts receive 10 one-time credits after registration. One credit represents one minute of transcription usage; paid plans and credit packs add more capacity, and purchased credits do not expire.
Make Recorded Content Easier to Revisit
Upload a supported recording, review uncertain phrases against the source media, and export the saved transcript in the format you need.