Pithflow's transcription model is multilingual-first, not English with bolted-on translations. 100+ languages including Spanish (LATAM + Spain), Portuguese (BR + PT), French, German, Japanese, Mandarin, Hindi, Arabic — all with auto-detection per clip.
Leave Settings → Languages on Auto-detect (the default). Every clip is analyzed for what language was actually spoken, and the transcription matches. Speak English at 9am, Spanish at 10am, code-switch mid-sentence at 11am — no settings to flip.
Spanish dictation gets inverted question marks (¿), inverted exclamations (¡), and correct accent placement (está vs esta). The cleanup follows the punctuation rules of the language you spoke.
Many bilingual conversations switch languages mid-sentence — "Sí, send me the report" or "Vamos a hacer un meeting tomorrow". Pithflow handles this gracefully because the transcription model sees the entire utterance, not just the first word's language.
If you dictated Spanish, the cleanup pass cleans up Spanish (Spanish filler words, Spanish tone presets). It doesn't silently translate to English. The model is explicitly instructed: preserve the language unless asked to translate.
Auto-detect occasionally misjudges very short clips ("Sí." or "OK") because there isn't enough audio to be confident. For sessions in one language, pick only that one under Settings → Languages → Languages you speak — with a single language picked, Pithflow locks it in.
No. Auto-detect is the default and works out the language of each dictation. Pin a language only if you always dictate in one.
Yes. That is the case auto-detect is built for, and the cleanup keeps each part in the language you spoke.
Only if you ask it to. The language setting controls the output language: leave it on Auto-detect to keep what you spoke, or pin another language to get the text in that language.
On very short clips like “Sí” or “OK” it can be. Under Settings > Languages, “Languages you speak” limits auto-detect to your languages, and picking just one locks it in.
