EnterpriseCall workspace
Public prototypeEC
Enterprise Call Summary and Data Extraction

MODEL EVALUATION

Build a benchmark

Select calls, compare models, and inspect the errors.

1. Define your test

Recordings

3 selected · 2.7 minutes of audio

Choose individual recordings (3 selected)
Advanced settings Split, repeats, terminology, and local runtime
Local hardware and runtime

This records your policy; it does not restart local models. The companion reports measured load time when available.

2. Choose STT models

Audio → transcript

0 selected
Needs key
Details & pricing $0.22 / audio hour

Speaker labels and conversational transcription. Compare accuracy on your recordings. Documentation ↗

Needs key
Details & pricing $0.10 / audio hour

Azure Speech key and resource endpoint required. Speaker labels enabled; use recordings shorter than 15 minutes during preview. WAV, MP3 or FLAC. Documentation ↗

Needs key
Details & pricing $0.21 / audio hour

Pinned to universal-3-5-pro with speaker labels. Supports terminology prompting. Documentation ↗

Needs key
Details & pricing $0.36 / audio hour

Uses gpt-4o-transcribe exactly. No speaker labels or segment timestamps; extraction must infer roles from the words. Documentation ↗

Needs key
Details & pricing $0.26 / audio hour

Terminology hints and speaker labels. Measure speed and word accuracy on the same recordings. Documentation ↗

3. Choose Extraction models

Transcript → structured fields

0 selected
Needs key
Details & pricing $0.2 in / $1.2 out per 1M

gpt-5.6-luna · Source ↗

Needs key
Details & pricing $0.3 in / $2.5 out per 1M

gemini-2.5-flash · Source ↗

Needs key
Details & pricing $2 in / $10 out per 1M

claude-sonnet-5 · Source ↗

Needs key
Details & pricing $1 in / $5 out per 1M

claude-haiku-4-5-20251001 · Source ↗

Needs key
Details & pricing $4 in / $20 out per 1M

gpt-5.6-sol · Source ↗

Connections and pricing notes

Cloud keys stay in deployment settings. Connection status means a key is configured, not that account/model access has been tested. Local models use the companion configured in Models & sources. STT hourly estimates come from your shortlist and are not verified account prices; speaker labels and subscription tiers may change the bill. Extraction uses published token rates checked September 21, 2026. Sol pricing is promotional; the additional Gemini 3.8 option also has introductory pricing. Edit rates to match your contract. Per-call costs are estimates from duration or returned token usage, not invoices. Published benchmark scores are not results on this dataset. OpenAI models use no reasoning; Gemini 2.5 uses thinkingBudget 0; Claude uses provider defaults.

Select at least one model.

3 calls · 0 STT requests · 0 extraction requestsSequential execution · includes human-transcript baselines. Saving setup does not run models.