Tagalog and Filipino audio to text
Filipino, the national language of the Philippines, is based on Tagalog. The speech model lists the language as Tagalog, so choose Tagalog for recordings in either. This page preselects it in the upload box.
Be realistic about results. The model has far less Tagalog training data than it has for English or Spanish. Clear audio of one or two people gives a draft that saves a lot of typing, but you should plan to review it line by line. Names, places, slang and fast casual speech are where most corrections happen. Noise, music and people talking over each other make the draft noticeably weaker.
You can raise the quality before you even upload. Record in a quiet room, keep the phone close to whoever is talking, and if you edit vlogs, upload a version without background music when you have one. Then review with the synced player: it highlights each line as it plays, and clicking a line jumps back to that moment so you can hear a word again.
Taglish and English words
Most Filipino conversation mixes in English, from single words to whole sentences. Since both languages use the Latin alphabet, English words in a Tagalog transcript usually keep their English spelling. Spanish-origin words such as "pero" or "siguro" are part of everyday Tagalog and are written as Tagalog.
Choose the language by what dominates. A family call that is mostly Tagalog with English mixed in should stay on Tagalog. A work meeting in English with a few Tagalog phrases will do better with English selected. Auto-detect can misjudge Taglish, short clips and recordings that start in English, which is another reason to set the language yourself.
Spelling and other Philippine languages
Informal Tagalog spelling varies, and the transcript will not always match how you write. You may see "hindi" where a speaker said "'di", a full form where you would use a contraction like "'yan", or "ng" and "nang" used differently from your preference. Fix these in place while you listen back.
Respect markers like "po" and "opo" are short and easy to miss in fast speech. If they matter for your transcript, as they often do in interviews with elders, listen for them during review.
Cebuano (Bisaya), Ilocano, Hiligaynon, Waray and other Philippine languages are not in the language list. If you upload them with Tagalog selected, the output will be unreliable and will often read like broken Tagalog. Tagalog-only recordings, or Tagalog mixed with English, are what this page covers.
Who uses Tagalog transcription
Typical files are video calls and voice messages from family in the Philippines, interviews for research on Filipino communities abroad, church and community events, podcasts, and vlogs that need subtitles. Small businesses use it for customer calls they want to keep a written record of. Students and researchers transcribe interviews so they can quote and code them.
Files come in as they are. WhatsApp voice notes, phone recordings and MP4 videos upload without any conversion, and you can also record straight from your microphone in the browser.
Speaker labels help with interviews and group conversations. They are available on paid plans or with a Minute Pack. On the free plan you get the full text without labels.
What you can do with the transcript
Export DOCX to edit in Word or Google Docs, TXT for plain notes, PDF to share a fixed copy, SRT or VTT for subtitles on a vlog, and CSV for research spreadsheets. Timestamps and speaker names can be switched on or off in each export.
To read the content in English, open the Google Translate link on the transcript. For a summary of a long call, use the AI prompt export and paste it into ChatGPT or Claude.