AI Models

Choose Your Transcription Engine — Compare accuracy, speed, and language support across leading speech recognition models.

How to choose the right model

Mismunandi umsetingarmøguleikar eru vælegnaðir á ymiskum økjum. Notiskað hesa vegleiðing til at velja tann besta møguleikan til tykkara tørv.

Model WER Speed Languages Best For
STT.ai Enhanced 3.2% 160.0x 100 STT.ai's flagship speech-to-text model with best-in-class accuracy and speed. Optimized …
Whisper Large V3 4.2% 8.0x 99 OpenAI's largest and most accurate Whisper model. Excellent multilingual support …
Whisper Turbo 5.1% 32.0x 99 OpenAI's speed-optimized Whisper variant. 4x faster than Large V3 with …
NVIDIA Canary 3.5% 45.0x 4 NVIDIA's multi-task ASR model with top-tier accuracy on English. Built …
Moonshine 7.8% 80.0x 1 Ultra-lightweight ASR model designed for edge devices. Runs on Raspberry …
NVIDIA Parakeet 3.0% 55.0x 1 NVIDIA's CTC-based English ASR model. One of the most accurate …
SenseVoice 5.5% 50.0x 50 Multilingual speech understanding model with emotion recognition and audio event …
Distil-Whisper 5.8% 48.0x 99 Distilled version of Whisper Large V3. 6x faster with 49% …
Vosk 12.0% 100.0x 20 Lightweight offline speech recognition. Works without internet, ideal for privacy-sensitive …

What is the WER (Word Error Rate)?

Word Error Rate (WER) er standard metrikkin til at meta um nøgdina av talgildari talgilding. Hann rekur út prosentin av orðum í eini útskrift, sum eru ymisk frá tilvísingini. Ein WER á 5% merkir, at umleið 5 av hvørjum 100 orðum innihalda eina feil. Lægri er betri.

Tað er ein ógvuliga stór fólkavøkstur í Føroyum, ið er 4-5 % árliga, og tað er ein ógvuliga stór fólkavøkstur í Føroyum, sum er 4-5 % árliga.

Ert tú ikki vissur um, hvat tú skalt gera?

Prøv okkara standard - Whisper Large V3 Turbo gevur besta javnvág millum skjótleika og nákvæmni. Frítt at byrja, eingin skráseting krevst.

Start Transcribing Free