Speech Transcription

Posted by

Automated Speech Transcription automatically processes real-time or recorded audio streams into editable text.

Supported languages: Romanian, 50 other languages supported, including cross-language content: Afrikaans (afr), Arabic (ara), Chinese (zho), Croatian (hrv), Czech (ces), Danish (dan), Dutch (nld), English (eng), Estonian (est), Finnish (fin), French (fra), Welsh (glg), German (deu), Greek (ell), Hebrew (heb), Hindi (hin), Indonesian (ind), Italian (ita), Japanese (jpn), Russian (rus), Kazakh (kaz), Korean (kor), Latvian (lav), Lithuanian (lit), Macedonian (mkd), Malay (msa), Marathi (mar), Maori (mri), Nepali (nep), Norwegian (nor), Persian (fas), Polish (pol), Portuguese (por), Swedish (swe), Thai (tha), Turkish (tur), Ukrainian (ukr), Urdu (urd).

Key features:

  • Automatic detection of languages from the audio source.
  • Multi-language transcription capability, being able to transcribe audio files containing multiple languages.
  • Sentence merging to unify segments from the same speaker using punctuation.
  • Audio volume gain capabilities for low-volume audio recordings.
  • High-quality audio transcriptions, achieving a Word Error Rate (WER) of 3.0 in the FLEURS dataset for key languages (comparable to human transcription).