SV Scribe v2 is a verified current AI model with official specifications, pricing or access information, capabilities, practical use cases and limitations.
Scribe v2 is ElevenLabs' state-of-the-art speech recognition model with 90+ language support, word-level timestamps, speaker diarization, keyterm prompting, entity detection and audio tagging.
Scribe v2 is a current AI model verified from first-party ElevenLabs sources.
Scribe v2 is ElevenLabs’ state-of-the-art speech recognition model with 90+ language support, word-level timestamps, speaker diarization, keyterm prompting, entity detection and audio tagging. The verified context or usage limit is Audio transcription workflow; files up to 3 GB, with Text transcript with timestamps and metadata maximum output.
ElevenLabs lists Scribe v2 API speech-to-text pricing at $0.22 per hour. Optional keyterm prompting and entity detection can add usage cost.
Meeting transcription, Call analytics, Podcasts, Captions, Multilingual speech-to-text, Media indexing.
Accuracy depends on audio quality, Specialized terms may need keyterms, Realtime use requires the separate Scribe v2 Realtime model.
Transcribe this meeting with speaker labels.Generate word-level timestamps for this interview.Use these product names as keyterms while transcribing.ElevenLabs lists Scribe v2 API speech-to-text pricing at $0.22 per hour. Optional keyterm prompting and entity detection can add usage cost.
A highly practical current transcription model for teams that need accurate multilingual speech-to-text with timestamps, speaker labels and enterprise-oriented extraction features.