← Niche Catalog

stt_transcription

Modality: modality_arm, video_generation · full deep dive — every ranked model, test result, and artifact.

5
Models
0
Benchmark Results
0
Media Artifacts
1
Resolutions

Ranked Models

Ranked by confidence-adjusted score (single/zero-sample, non-curated scores floored; curated empirical scores trusted as-is).

#ModelProviderAdj. ScoreRawEvidence
1whisper-large-v3openai0.9000.900curated
2deepgram-nova-2deepgram0.8500.850curated
3fal-whisper-large-v3fal0.8500.850curated
4groq-whisper-large-v3groq0.8500.850curated
5openai/whisper-1openai0.1501.000provisional (n≤1)

Test Results

No benchmark outputs recorded for this niche yet.

Resolved Here

Requests semantically routed into this niche.

RequestedMethodConfidenceWhen
speech_transcriptionsemantic0.5762026-05-20 17:26