Verba turns spoken notes into credible written output across English, 中文, español, français, and português. Raw transcript preserved. Ambiguity surfaced, not papered over. Drafts compared across providers, scored against a fixed rubric, and exportable as JSONL — all on the same Cloudflare edge that serves this site.
Drop audio. Whisper-style transcription with confidence-scored segments. Multilingual by default.
Rewrite, translate, or generate a prompt — three deliberate modes. Diff highlighted inline against the raw transcript.
Run the polished output through multiple providers in parallel. Side-by-side diff. Cost and latency captured per call.
Score outputs with a fixed rubric. Persist to D1. Export the eval log as JSONL for downstream analysis.