Audio to text converter
Drop your audio or video file and let AI turn the speech into a timestamped transcript. Copy the text or download it as TXT.
Free · no sign-up · the file you upload is deleted within 24 hours
Drop your file and click Transcribe. The timestamped text appears here.
Sample output
The tool returns the speech as timestamped text; speaker separation comes with Starter and higher plans. The output below is an example showing the format.
- Speaker 100:00:02
Welcome, everyone. Today we're going over the first week of the new project.
- Speaker 200:00:07
Thanks. Let's start with the timeline: the design phase wraps up on Friday.
- Speaker 100:00:14
Great. When does the testing team come in?
- Speaker 200:00:18
Next Monday. The first version will be ready by then.
Other pages for this tool
- Video to text converter
- WhatsApp voice message to text
- TikTok transcript generator
- Instagram transcript generator
- Facebook transcript generator
- Audio translator
- Meeting and lecture summarizer
- Podcast transcript generator
- Interview transcription
- Song lyrics transcription
- MP3 to text
- MP4 to text
- WAV to text
- M4A to text
- OGG / OPUS to text
- MOV to text
- FLAC to text
- WEBM to text
How to use
- Drop your fileChoose an audio or video file such as MP3, WAV, M4A, OGG or MP4. The free trial transcribes recordings up to 10 minutes.
- Set the optionsLeave the language on auto-detect or pick it. Speaker separation is available in the studio on Starter and higher plans.
- Get the textClick Transcribe. The text appears with timestamps; copy it, download it as TXT or edit it in the studio.
How is audio converted to text?
Transcription (speech to text) turns spoken words into written text. The AI listens to the recording, detects the language, punctuates sentences and marks the second each segment starts. With speaker separation on, different voices are labeled Speaker 1, Speaker 2 and so on.
If you upload a video, its audio is extracted in your browser and only the audio is sent, so large videos upload much faster. For recordings longer than 10 minutes, the free trial transcribes the first 10 minutes.
Free trial vs. studio
| Feature | Free trial (no sign-up) | Transcription studio |
|---|---|---|
| Recording length | Up to 10 minutes | Long recordings |
| Daily use | 1 file a day | Based on your credits |
| File size | 50 MB | Large files |
| Output | On-screen text, copy, TXT | TXT, DOCX, PDF, SRT, VTT, XLSX and more |
| Editing | — | Segment editing, speaker names, find and replace, undo |
| AI steps | — | Summary, action items, translation, chat with your recording |
For a more accurate transcript
- Record in a quiet room with the microphone close to the speaker.
- If you know the language, select it instead of auto-detect; this is more reliable for short clips.
- Overlapping speech and background music reduce accuracy.
- Use the custom vocabulary in the studio for names and terminology.
When to use it
Meeting and lecture recordings
Transcribe the recording and pull out your notes fast.
Interviews and podcasts
Find quotes easily in a transcript split by speaker.
Video subtitles
Create an SRT or VTT file from the same transcript.
WhatsApp voice messages
Read long voice messages without listening.
Your recording may contain personal data. In the free trial, your file and transcript are deleted within 24 hours; only upload conversations you own or have permission to record. Details: Data protection.
Transcription by language
126 languages and dialects have their own page. On each one the transcription tool opens set to that language.
English (United States)
English (United Kingdom)
English (Australia)
English (Canada)
English (Ghana)
English (Hong Kong)
English (India)
English (Ireland)
English (Kenya)
English (New Zealand)
English (Nigeria)
English (Philippines)
English (Singapore)
English (South Africa)
English (Tanzania)
Turkish (Turkey)
German (Germany)
Spanish (Spain)
French (France)
Italian (Italy)
Portuguese (Brazil)
Russian (Russia)
Japanese (Japan)
Polish (Poland)
Show all languages (126)
Dutch (Netherlands)
Hindi (India)
Afrikaans (South Africa)
Amharic (Ethiopia)
Arabic (Algeria)
Arabic (Bahrain), (Modern Standard)
Arabic (Egypt)
Arabic (Iraq)
Arabic (Israel)
Arabic (Jordan)
Arabic (Kuwait)
Arabic (Lebanon)
Arabic (Libya)
Arabic (Morocco)
Arabic (Oman)
Arabic (Palestinian)
Arabic (Qatar)
Arabic (Saudi Arabia)
Arabic (Syria)
Arabic (Tunisia)
Arabic (United Arab Emirates)
Arabic (Yemen)
Armenian (Armenia)
Azerbaijani (Azerbaijan)
Bengali (India)
Bulgarian (Bulgaria)
Burmese (Myanmar)
Catalan (Spain)
Chinese (Cantonese, Traditional)
Chinese (Mandarin, Simplified)
Chinese (Taiwanese Mandarin)
Croatian (Croatia)
Czech (Czech Republic)
Czech (Czech)
Danish (Denmark)
Dutch (Belgium)
Estonian (Estonia)
Filipino (Philippines)
Finnish (Finland)
French (Belgium)
French (Canada)
French (Switzerland)
Galician (Spain)
Georgian (Georgia)
German (Austria)
German (Switzerland)
Greek (Greece)
Gujarati (Indian)
Hebrew (Israel)
Hungarian (Hungary)
Icelandic (Iceland)
Indonesian (Indonesia)
Italian (Switzerland)
Javanese (Indonesia)
Kannada (India)
Kazakh (Kazakhstan)
Khmer (Cambodia)
Korean (Korea)
Latvian (Latvia)
Lithuanian (Lithuania)
Macedonian (North Macedonia)
Malay (Malaysia)
Maltese (Malta)
Marathi (India)
Mongolian (Mongolia)
Nepali (Nepal)
Norwegian (Bokmål, Norway)
Persian (Iran)
Portuguese (Portugal)
Romanian (Romania)
Serbian (Serbia)
Slovak (Slovakia)
Slovenian (Slovenia)
Spanish (Argentina)
Spanish (Bolivia)
Spanish (Chile)
Spanish (Colombia)
Spanish (Costa Rica)
Spanish (Cuba)
Spanish (Dominican Republic)
Spanish (Ecuador)
Spanish (El Salvador)
Spanish (Equatorial Guinea)
Spanish (Guatemala)
Spanish (Honduras)
Spanish (Mexico)
Spanish (Nicaragua)
Spanish (Panama)
Spanish (Paraguay)
Spanish (Peru)
Spanish (Puerto Rico)
Spanish (Uruguay)
Spanish (USA)
Spanish (Venezuela)
Swahili (Kenya)
Swahili (Tanzania)
Swedish (Sweden)
Telugu (India)
Thai (Thailand)
Ukrainian (Ukraine)
Uzbek (Uzbekistan)
Vietnamese (Vietnam)
Common questions
Is converting audio to text free?
Yes. Without an account you can transcribe 1 file a day, up to 10 minutes long. Create a free account for longer recordings and more export formats.
Which file formats are supported?
MP3, WAV, M4A, AAC, OGG, OPUS, FLAC and WEBM audio, plus MP4, MOV, WEBM and MKV video. For videos, the audio is extracted in your browser.
How are speakers separated?
On Starter and higher plans, with Separate speakers on, the AI tells different voices apart and assigns each segment to a speaker; you can replace the labels with real names in the studio. The free trial and the Free plan don’t include speaker separation.
What if my recording is long?
In the free trial, the first 10 minutes are transcribed and we tell you so on screen. Continue in the studio for the full recording.
Can I get the text as subtitles?
Yes. The subtitle generator creates SRT and VTT files from the same transcript, and you can set the line length.
Related tools
- Video to text converterTurn the speech in a video into a timestamped transcript.
- Subtitle generatorCreate SRT and VTT subtitle files from video automatically.
- YouTube transcript generatorGet a timestamped transcript from a YouTube link.
- WhatsApp voice message to textTurn WhatsApp voice messages (.opus/.ogg) into readable text.
- Meeting and lecture summarizerTranscribe meeting and lecture recordings and summarize them.
- Free text to speechHave AI read your text aloud, then play it and download it as MP3.
Move to the studio for more.
Long files, saved projects and advanced export are in the studios. Start with a free account.