Turn Turkish meetings, interviews and lectures into searchable text with speaker labels — with the Turkish alphabet written correctly.
iOS and Android. 30 minutes free, no card.
Does SozAI transcribe Turkish?
SozAI transcribes Turkish audio and video into text with automatic speaker labels and word-level timestamps. It writes the full Turkish alphabet, including the dotted and dotless i, ğ, ş and ç, and exports to TXT, DOCX, PDF, SRT and VTT. Recordings are processed in EU data centers and encrypted at rest, and every account gets 30 minutes a month without a card.
Türkçe, written the way it is actually written.
Specification
| Native name | Türkçe |
|---|---|
| ISO 639-1 code | tr |
| Writing system | Latin (Turkish alphabet) |
| Text direction | Left to right |
| Speakers worldwide | ~90 million |
| Varieties covered | Istanbul standard, Anatolian |
| Speaker labels | Yes — automatic diarization |
| Timestamps | Word level |
| Summaries | Yes, in the same language |
| Export formats | TXT, DOCX, PDF, SRT, VTT |
| Maximum file size | 500 MB |
| Free tier | 30 minutes per month, no card |
| Where data is stored | EU data centers, AES-256 at rest |
| Public transcripts in this language | 113 |
Workflow
Record straight into the app, upload a file up to 500 MB, or paste a YouTube link. SozAI reads m4a, mp3, wav, aac, mp4 and mov.
Choose Turkish, or leave detection on. Recordings that mix Turkish with English business vocabulary stay in a single transcript.
The transcript arrives with speaker labels and word timestamps. Search it, ask it questions, generate a summary in Turkish, or export SRT and VTT subtitles.
Field notes
Turkish is agglutinative: suffixes stack onto a root until a single written word carries what English needs a clause for. Each suffix changes meaning, so an error deep inside a long word is easy to miss and hard to spot when reading. This also means word counts and search behave differently than in European languages.
Turkish distinguishes i/İ from ı/I as separate letters. Software that lowercases "I" to "i" — the default nearly everywhere — silently corrupts Turkish text, and the classic result is a transcript where words look almost right and no longer match a search. SozAI writes the correct pair rather than normalising to ASCII.
The same grammatical suffix is written several different ways depending on the vowels in the root. Transcribing the sound is not enough; the system has to pick the harmonised form the language requires. Getting this wrong produces text that a Turkish reader recognises instantly as machine output.
SozAI targets the Istanbul standard used in broadcasting and business. Strong regional speech from eastern Anatolia or the Black Sea coast is noticeably harder, and accuracy drops on it. If a recording runs in heavy dialect, expect more correction than a standard-speech meeting would need.
From the archive
113 public Turkish transcripts so far — every one produced by the same engine described above. Read them in full, no account needed.
Çarşamba Belediyesi Temmuz Meclis Toplantısı — Transcript
Arda Saatçi, 600 KM’lik koşusunu anlattı | Hakan Çalhan… — Transcript
Amirjon Ergashev – Chaka ba chak — Transcript
Empati 12. Bölüm – Ayça Ayşin Turan @AhmetMumtazTaylanİ… — Transcript
Әке тәрбиесі және бала болашағы: Неге балаға сөзбен еме… — Transcript
СД Видео 6 сабақ Каруменен саптық әдістер — TranscriptSozAI transcribes over 100 languages. These have a page of their own.
Answers
Short answers you can quote. Longer ones live in the sections above.
Yes — ç, ğ, ı, İ, ö, ş and ü are all written properly, including the distinction between dotted and dotless i. This matters beyond appearance: naive case-folding maps "I" to "i" and quietly turns Turkish words into different ones, which is a common reason machine transcripts fail a search later.
Yes. Diarization works on the audio rather than the language, so each speaker gets a label and every turn a timestamp. For interviews and recorded meetings this is what makes the output usable as a record instead of one long block of text.
They are written as single words, which is correct Turkish. Word-level timestamps help here more than in most languages: when a long suffix chain comes out wrong, you can jump to the exact second it was spoken and fix it once rather than re-listening to the passage.
SozAI exports SRT and VTT in UTF-8 with word-level timing, so Turkish characters survive the trip into YouTube, Premiere Pro, Final Cut Pro and DaVinci Resolve. You should not need an encoding-repair pass.
Every account gets 30 minutes per month free without a card. Beyond that SozAI is a flat monthly subscription with a shared pool of minutes, and the price is the same whichever language you transcribe. Current plans are listed on the pricing page.
Where to use it
Everything below works in Turkish, with the same speaker labels and word timestamps.
Transcribe your first Turkish recording
Record, upload a file or paste a link. Speakers, timestamps and a Turkish summary come back together.
Free on iOS and Android. No account required for YouTube transcripts.
Point your camera
Scan the code to open the download page on iOS or Android. 30 minutes of transcription free, no card.
