# VoiceLens

> VoiceLens grades every voice call in a call-center, whether an AI agent or a human agent is on the line: fault detection, latency outliers, slot capture, sentiment shifts and transcription quality, surfaced in a dashboard, an API and signed webhooks.

Every documentation page is also available as Markdown by appending `.md` to its URL. The complete documentation is concatenated in `llms-full.txt`.

## Documentation

- [VoiceLens documentation](https://voicelens.app/docs/index.md): Everything you need to grade voice calls with VoiceLens: how the analysis works, how to send calls in, how to read a scorecard, and how to integrate the results into your own systems.
- [Introduction](https://voicelens.app/docs/getting-started.md): What VoiceLens does, who it is for, and how a call travels from your phone system to a graded scorecard.
- [Quickstart](https://voicelens.app/docs/getting-started/quickstart.md): Create a workspace, grade your first call and connect your phone system, in that order.
- [Upload a recording or transcript](https://voicelens.app/docs/getting-started/upload-a-call.md): Every way a call can enter VoiceLens: dashboard upload, transcript analysis, the ingest API and provider callbacks, and what metadata to attach.
- [Reading a scorecard](https://voicelens.app/docs/getting-started/reading-a-scorecard.md): A tour of the call view: health score, fault list, latency panel, slots and questions, sentiment trajectory, transcript and line quality.
- [Health score](https://voicelens.app/docs/concepts/health-score.md): How the 0 to 100 health score is computed from faults, slot capture and question coverage, and how to tune it per rubric.
- [Fault codes](https://voicelens.app/docs/concepts/fault-codes.md): The fourteen faults VoiceLens detects, what triggers each one, its severity, the evidence attached, and which ones you can switch off per rubric.
- [Latency and dead air](https://voicelens.app/docs/concepts/latency.md): How per-turn agent latency is measured, which statistics are reported, and how the rubric's thresholds turn slow turns into faults.
- [Slot capture and question coverage](https://voicelens.app/docs/concepts/slot-capture.md): How VoiceLens tracks the details an agent had to collect and the questions it had to ask, and how both feed the health score.
- [Sentiment](https://voicelens.app/docs/concepts/sentiment.md): How caller sentiment is scored turn by turn, what a sentiment drop is, and how to read the trajectory on a scorecard.
- [Transcription quality](https://voicelens.app/docs/concepts/transcription-quality.md): Word confidence, speaker attribution and acoustic line quality: how VoiceLens tells you how much to trust a transcript, and what each signal means.
- [Channels and ingest tokens](https://voicelens.app/docs/guides/channels-and-ingest-tokens.md): Model your phone lines, bots and queues as channels, issue ingest tokens for integrations, configure sampling, providers and test calls.
- [Rubric templates](https://voicelens.app/docs/guides/rubric-templates.md): Define what a good call looks like: slots, questions, required and forbidden phrases, case branching, thresholds, detector toggles, scoring weights, versions and AI drafts.
- [Golden set and calibration](https://voicelens.app/docs/guides/golden-set-calibration.md): Mark reference calls with the score you expect, re-score them against a rubric, and read the calibration report and fault-precision statistics.
- [Alerts and weekly digest](https://voicelens.app/docs/guides/alerts-and-digest.md): Get notified when average health drops, danger or failure rates rise, or call volume changes, and receive a weekly summary for every workspace.
- [Embedded dashboards](https://voicelens.app/docs/guides/embedded-dashboards.md): Put a read-only, themed VoiceLens dashboard inside your own portal with one script tag: create an embed token, choose features, match your colours, remove branding.
- [Shareable scorecards](https://voicelens.app/docs/guides/shareable-scorecards.md): Send one call's scorecard to a coach, an agent or a client as a read-only link, with or without transcript and audio, and print it as a PDF.
- [Workspaces, roles and invites](https://voicelens.app/docs/guides/workspaces-and-roles.md): How workspaces isolate data, what each role can do, how to invite teammates and clients, and how to organise an agency with many clients.
- [Usage and billing](https://voicelens.app/docs/guides/usage-and-billing.md): How call minutes are counted, what each plan includes, what happens at the limit, and how to upgrade, manage payment and read invoices.
- [Authentication](https://voicelens.app/docs/api/authentication.md): The three credential types VoiceLens exposes to integrations: channel ingest tokens for sending calls, workspace API keys for reading data, and embed and share tokens for public surfaces.
- [Ingest API](https://voicelens.app/docs/api/ingest-audio.md): Send call recordings into a channel: multipart upload, download from a URL, or a pre-signed upload URL. Metadata fields, responses, idempotency and errors.
- [Conversations API](https://voicelens.app/docs/api/conversations.md): List, search and read analysed calls with a workspace API key: paging, filters, the summary shape and the full analysis object with faults, latency, slots, sentiment and transcript.
- [Analytics API](https://voicelens.app/docs/api/analytics.md): Workspace-level aggregates with a workspace API key: summary, time series, fault trends, channels, agents, capture gaps, latency histogram, review queue and fault precision.
- [Webhooks](https://voicelens.app/docs/api/webhooks.md): Receive completed analyses, failures, threshold breaches and alerts as signed HTTP deliveries: event types, payloads, headers, HMAC verification in Node, .NET and Python, retries and troubleshooting.
- [embed.js reference](https://voicelens.app/docs/api/embed-js.md): Every attribute the embed loader understands, the window.VoiceLensEmbed API, the postMessage protocol, and the public embed endpoints behind it.
- [Security and privacy](https://voicelens.app/docs/security.md): How VoiceLens stores and protects call recordings and transcripts: isolation, access control, credentials, encryption in transit, retention and deletion, and what to tell your own security team.
- [Frequently asked questions](https://voicelens.app/docs/faq.md): Short answers to the questions teams ask before and after connecting VoiceLens: agents and bots, languages, accuracy, integrations, pricing and data.
- [Changelog](https://voicelens.app/docs/changelog.md): Notable changes to VoiceLens, newest first: new analysis signals, integration features and documentation.

## Optional

- [Privacy policy](https://voicelens.app/privacy)
- [Terms of service](https://voicelens.app/terms)