Portuguese Speech to Text
LiveToka writes spoken Portuguese as text in real time and can translate it live. It works for Brazilian and European Portuguese, in meetings, classes, interviews or livestreams.
New accounts get 10 free minutes. Sign in with Google — no credit card required.
Portuguese transcription: what to expect
- One Portuguese model covers both Brazilian and European speakers; accents from Portugal, Brazil, Angola or Mozambique are all transcribed.
- Accents and cedillas (ã, ç, é, ô) are written correctly, with punctuation added automatically.
- Fast, informal speech is common in Brazilian conversation; the transcript follows it as long as speakers do not talk over each other.
Popular uses
- Meetings with Brazilian or Portuguese teams
- Transcribing interviews and podcasts recorded in Portuguese
- Live translation for Portuguese-speaking church congregations
- University lectures for exchange students
How to start
- Click Start Portuguese transcription above and sign in with Google.
- Portuguese is pre-selected as the source language. Choose Transcribe Only, or Transcribe + Translate and a target language.
- Click Start Service and allow microphone access. Text appears as people speak.
Translating a call or livestream playing on your computer? See how to route meeting audio.
Translate Portuguese
Other languages
Frequently asked questions
Is Brazilian Portuguese supported?
Yes. Choose Portuguese as the source language; it covers Brazilian and European Portuguese.
Can I translate into Spanish instead of English?
Yes. Portuguese can be translated into Spanish, English and 100+ other languages.
Is there a free trial?
Yes. New accounts get 10 free minutes after signing in with Google — no credit card. Transcription uses credits at 1× and translation at 2×, so that is up to 10 minutes of transcription or 5 minutes of translation. Paid plans start at $9.9/month.
Do I need to install anything?
No. LiveToka runs in the browser. The latest Chrome, Edge or Safari is recommended.
Is my audio used to train AI?
No. Your voice recordings and transcripts are not used to train AI models.