🇪🇺
EU residency guaranteed
AssemblyAI EU (Dublin), Whisper local on Hetzner DE, R2 EU bucket. No US sub-processor accesses your audio.
AI transcription
Spanish that sounds like Spanish, transcribed in Europe
Hybrid transcription with AssemblyAI EU endpoint as primary and on-prem Whisper as fallback. 8 Spanish regional variants. ES↔EN code-switching. Your audio never crosses the Atlantic.
🌎
8 Spanish regional variants
Iberian, Mexican, Argentine, Colombian, Chilean, Venezuelan, Peruvian, Uruguayan — each fine-tuned, not lumped as "Spanish".
🔀
ES↔EN code-switching
Per-segment language detection. If your meeting mixes Spanish and English, the transcript does too. Otter/Fathom break here.
🎙️
Speaker diarization native
Who said what, with names you can edit. Bundled in every paid tier, not gated to Enterprise.
🔁
Hybrid resilience
AssemblyAI primary + Whisper sidecar fallback. Outage of one doesn't stop transcription.
📊
Public WER benchmarks
/benchmark publishes our WER per Spanish variant. Caja negra is not our model.
Which engine do you use?+
Primary: AssemblyAI Universal-2 via the EU endpoint (api.eu.assemblyai.com). Fallback: faster-whisper large-v3-turbo on our dedicated Hetzner DE server. Both run with multilingual support including ES↔EN code-switching.
What's the WER for Spanish?+
7–9% on Iberian Spanish (vs ~14.7% on Whisper genérico). Per-variant benchmarks are public at /benchmark with sample audios and methodology.
Do you store my audio?+
Optionally. You can keep audio in our EU R2 bucket for re-listen, or delete it after transcription. Either way, your transcript stays accessible. Granola, by contrast, doesn't store audio at all.
What about file formats?+
MP3, MP4, MOV, WAV, M4A, FLAC, WebM, MKV, OGG and more. Up to 5GB and 10h per file. Auto-detects format and metadata.
You may also like
Transcribe your next conversation
120 free minutes per month. No credit card. Iberian + LATAM Spanish ready.
Try for free