Developer Platform

Build voice into your product. Keep control of the experience.

Use APIs, realtime clients and embedded conversations to make voice part of your application. Bring your own agent brain or compose the speech, knowledge and action capabilities your product needs.

THE OUTCOME

A production voice journey connected to your application’s identity, context and business logic.

Embedded voice · application boundaryProduct preview

A conversation, connected to your business.

Your applicationUser journey and business logic
Session accessShort-lived authorized voice session
ConversationRealtime audio + scoped context
Return pathAction result and signed events
AuthorizeConnectConverseHandle result
Illustrative product previewVagary Voice
01

Meet your application where it is

Choose the interface that matches your product and delivery channel.

  • Build with public REST and GraphQL APIs and language SDKs.
  • Stream audio through realtime clients or embed a voice widget.
  • Support browser and mobile experiences with application-aware conversation context.
02

Bring your own intelligence

Connect an existing agent system or compose the capabilities you need.

  • Use a customer-hosted agent brain with Vagary voice infrastructure.
  • Connect tools over MCP or expose Voice through its MCP server.
  • Access speech and retrieval capabilities without designing a receptionist workflow.
03

Operate beyond the first demo

Give developers the controls needed for reliable customer traffic.

  • Scope API keys to organizations and plan capabilities.
  • Use short-lived embed tickets, idempotency and versioned API contracts.
  • Inspect debug sessions, test in a sandbox and consume signed events.
THE WORKFLOW

From a conversation
to a completed task.

Connect the steps that make the outcome possible.

  1. 01

    Choose an integration shape

    Decide between an embedded agent, a realtime client or individual capabilities.

  2. 02

    Connect application context

    Authenticate the session and supply only the data the conversation needs.

  3. 03

    Verify a complete task

    Exercise speech, business logic and the result returned to your application.

  4. 04

    Prepare production behavior

    Configure event handling, quotas, failures and the intended deployment environment.

PUT IT TO WORK

Make it useful
in your business.

Start with a specific conversation, connect the right systems, and define what a successful outcome looks like.

01

An in-app assistant that completes account-related tasks.

02

A vertical SaaS product with a branded voice interface.

03

An existing agent framework that needs phone and browser channels.

A CLOSER LOOK

Useful questions.
Straight answers.

Discuss your requirements
Can I keep my existing agent framework?

Yes. BYO agent support lets your hosted brain participate in the voice journey. Decide which system owns reasoning, state and tools so behavior stays understandable across the boundary.

Do I need a full Voice workflow for standalone speech?

No. Speech recognition and synthesis have a capability entry path. Start with the relevant API documentation and shared organization context rather than configuring an unrelated business agent.

Can I embed an agent without exposing a long-lived key?

Short-lived embed session tickets support bounded client sessions. Keep privileged credentials on your server and use the documented authentication contract for your chosen client.

MAKE YOUR NEXT CONVERSATION COUNT

Give every conversation
somewhere better to go.

Start with one agent. Build an operation around what works.