speech-to-text

To transcribe audio recordings with multiple speakers, this Skill provides speaker diarization to identify who is speaking, word-level timestamps, and supports 90+ languages. It processes files up to 3GB or 10 hours long.

Yes, you can generate subtitles from video files automatically. The Skill supports diverse audio and video file types, converting spoken content into text transcripts with timestamps suitable for subtitle creation.

Audio transcription works effectively for long meetings and interviews, handling recordings up to 10 hours or 3GB in size to generate detailed minutes, searchable archives, and accurate text outputs.

Multilingual speech-to-text handles different languages by utilizing ElevenLabs Scribe v2 models, supporting over 90 languages to accurately convert spoken audio into searchable text transcripts.

Yes, you need an API key and internet access to convert spoken audio into text. The transcription process utilizes ElevenLabs Scribe v2 models, requiring external API connectivity for batch and real-time scenarios.