# HubTalk AI

## Conversation Platform v4

### Get Started

- [Introduction](https://docs.hubtalk.ai/v4/introduction.md): HubTalk AI v4 is the next generation conversational platform for voice agents.
- [Getting Started](https://docs.hubtalk.ai/v4/getting-started.md): Quick start guide for using HubTalk AI v4.

### Platform Guide

- [Dashboard](https://docs.hubtalk.ai/v4/platform/dashboard.md): Configurable dashboards built from a widget catalog: what gets counted and over which period.
- [Copilot](https://docs.hubtalk.ai/v4/platform/copilot.md): AI assistant that helps you build and edit agent flows in HubTalk AI v4.
- [Incidents](https://docs.hubtalk.ai/v4/platform/incidents.md): Review and investigate incidents affecting HubTalk AI v4.
- [Telephony](https://docs.hubtalk.ai/v4/platform/telephony.md): Platform guide for telephony setup in HubTalk AI v4.
- [Demo links](https://docs.hubtalk.ai/v4/platform/demo-links.md): Share a temporary link that lets anyone talk to your agent in a browser.
- [Roles and access](https://docs.hubtalk.ai/v4/platform/roles.md): What an administrator, a developer and a member can each do in the dashboard.

#### Agents

- [Agents](https://docs.hubtalk.ai/v4/platform/agents.md): Voice agents in HubTalk AI v4: what they are, how to create your first one, and where everything is documented.
- [The agent list and access](https://docs.hubtalk.ai/v4/platform/agents/list.md): The agent table, organization folders and the Visible to members setting.
- [Flow nodes](https://docs.hubtalk.ai/v4/platform/agents/nodes.md): Nine node types: what each one does and which fields it has.
- [Working in the editor](https://docs.hubtalk.ai/v4/platform/agents/building.md): Document search, agent variables, error checking and testing the flow.

#### Agent settings

- [Agent settings](https://docs.hubtalk.ai/v4/platform/agent-settings.md): Configuring the behaviour and voice of a HubTalk AI v4 agent: where to start and where everything lives.
- [Prompt, models and knowledge](https://docs.hubtalk.ai/v4/platform/agent-settings/prompt-and-models.md): The global prompt, variables in authored text, model overrides, cache warm-up, knowledge bases and flex mode.
- [Voice: STT, TTS and VAD](https://docs.hubtalk.ai/v4/platform/agent-settings/voice.md): Recognition, synthesis, speech detection and interruptions, background audio, turn language and the normalizer.
- [Phrase corrections and pauses](https://docs.hubtalk.ai/v4/platform/agent-settings/speech-corrections.md): The organization's replacement dictionary and [pause N] markup in the agent's text.
- [Recording and call control](https://docs.hubtalk.ai/v4/platform/agent-settings/call-control.md): Call recording, call timers, silence reminders and the transfer failure message.
- [Conversation goals](https://docs.hubtalk.ai/v4/platform/agent-settings/goals.md): What has to be established in a conversation, how the platform marks it, and what the mechanism does not do.
- [Analytics, observers and webhooks](https://docs.hubtalk.ai/v4/platform/agent-settings/analytics.md): Post-call analysis, custom fields, observers and post-call webhooks.

#### Pre- and post-call functions

- [Pre- and post-call functions](https://docs.hubtalk.ai/v4/platform/call-functions.md): Calls the agent makes into your systems before dialing and after the conversation: when they run, the Pipeline view, and where everything is documented.
- [Pre-call functions](https://docs.hubtalk.ai/v4/platform/call-functions/before.md): Configuring an HTTP function and a code function, result variables, ordering and parallelism, trial runs and late delivery.
- [Post-call functions](https://docs.hubtalk.ai/v4/platform/call-functions/after.md): The run condition, the call and analysis variables, waiting for post-call analysis, and testing a condition without a call.
- [Dial decisions in a campaign](https://docs.hubtalk.ai/v4/platform/call-functions/campaign-decision.md): How a pre-call function cancels a dial or defers a contact, and what happens to the attempt.
- [The integration contract](https://docs.hubtalk.ai/v4/platform/call-functions/contract.md): What the platform sends, what it expects back, how the mapping works, trial runs and configuration keys.
- [History, limitations and troubleshooting](https://docs.hubtalk.ai/v4/platform/call-functions/diagnostics.md): What the call event feed shows, what the mechanism does not do, and what each symptom means.

#### Campaigns

- [Campaigns](https://docs.hubtalk.ai/v4/platform/campaigns.md): Manage outbound calling campaigns in HubTalk AI v4.
- [Campaign contacts](https://docs.hubtalk.ai/v4/platform/campaigns/contacts.md): The contact file and its requirements, adding batches, file retention and do-not-call screening.
- [Call frequency](https://docs.hubtalk.ai/v4/platform/campaigns/frequency.md): How often one number may be called: where the numbers come from, how to switch the limits off, and what the switch does not touch.
- [US campaigns](https://docs.hubtalk.ai/v4/platform/campaigns/us-market.md): Calling windows in the contact's local time, and the geography the file must carry.
- [Campaign launch](https://docs.hubtalk.ai/v4/platform/campaign-launch.md): The campaign wizard: five steps from the agent to the attestation signature.

#### History & reports

- [History & reports](https://docs.hubtalk.ai/v4/platform/campaign-history.md): Searching the conversation history: the table, the filters — and where to find call details and reports.
- [Call details](https://docs.hubtalk.ai/v4/platform/campaign-history/call-details.md): Transcript and events, turn latency, post-call analytics, health, the recording and webhook deliveries.
- [Reports: how to download](https://docs.hubtalk.ai/v4/platform/campaign-history/reports.md): What goes into the file, the build queue and which period is exported.
- [A report for one campaign](https://docs.hubtalk.ai/v4/platform/campaign-history/campaign-report.md): An export within the bounds of one campaign, the Campaign field, and ready-made forms for migration.
- [Report columns](https://docs.hubtalk.ai/v4/platform/campaign-history/report-columns.md): Presets, the transcript as a column, the column builder and columns for migrating from the previous version.
- [Report template](https://docs.hubtalk.ai/v4/platform/campaign-history/report-templates.md): Column labels, value replacements, extra columns, and the structure and language of the file.

### Webhooks

- [Webhooks](https://docs.hubtalk.ai/v4/webhooks.md): Platform guide for webhooks in HubTalk AI v4.

## API Reference

### How it works

- [Web API](https://docs.hubtalk.ai/v4/web-api.md): How your system launches campaigns on its own: where to start and where everything is documented.
- [The access key and getting ready](https://docs.hubtalk.ai/v4/web-api/start.md): Issuing a key, what must be ready before the first request, and the pre-launch checklist.
- [How a campaign runs](https://docs.hubtalk.ai/v4/web-api/how-it-works.md): What happens after the request, how to read the response, and why the idempotency key is mandatory.
- [Consent, the registry and who is responsible](https://docs.hubtalk.ai/v4/web-api/rules.md): Consent attestation, the do-not-call registry, and what the platform does itself.
- [When something goes wrong](https://docs.hubtalk.ai/v4/web-api/troubleshooting.md): The common refusals, what they mean and what to do about them.

### Technical reference

- [Calling the API](https://docs.hubtalk.ai/v4/web-api/reference.md): Base address, authentication, formats and the map of every request.
- [Creating a campaign](https://docs.hubtalk.ai/v4/web-api/campaign-create.md): `POST /v1/campaigns`: headers, request body, the order of refusals and the successful response.
- [The campaign object, blockers and warnings](https://docs.hubtalk.ai/v4/web-api/campaign-object.md): What comes back about a campaign, and how to read launch blockers and warnings.
- [Campaign fields](https://docs.hubtalk.ai/v4/web-api/campaign-fields.md): Retries, numbers, dial binding, consent attestation, registry screening and idempotency.
- [Managing a campaign](https://docs.hubtalk.ai/v4/web-api/campaign-manage.md): Launch, pause, cancel, progress, statistics and adding batches of numbers.
- [The upload report](https://docs.hubtalk.ai/v4/web-api/imports.md): What came back for each row of the file, and the row-level issue codes.
- [Individual calls](https://docs.hubtalk.ai/v4/web-api/calls.md): `POST /v1/calls/phone`, the call object, reading, ending and listing calls.
- [Call outcomes: `call_status` and `status_reason`](https://docs.hubtalk.ai/v4/web-api/call-status.md): The outcome axis: buckets, the reasons inside them, and how they fold into a verdict.
- [Webhooks](https://docs.hubtalk.ai/v4/web-api/webhooks.md): The `call_ended` and `call_analyzed` events, signing, retries and delivery order.
- [Error codes and an end-to-end example](https://docs.hubtalk.ai/v4/web-api/errors.md): The full list of codes and a working scenario in one piece.

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [Russian (81 pages)](https://docs.hubtalk.ai/_llms/ru.md): Documentation for Russian.