Spiant
AI AssistantVoice InterfaceArtifacts & CanvasMultimodal InputSilent CoreAgent SystemCustom AgentsScheduled TasksProjectsTeam WorkspacesConnectorsMemory System
DevelopersResearchersWriters & CreatorsProduct TeamsCode & BuildResearch & AnalysisDocument IntelligenceTeam AI
DocumentationBlogUse Case LibraryREST APIWebSocket Voice APISDKsChangelogSystem Status
OverviewSecurity & ComplianceSelf-HostedContact Sales
Pricing
Sign inStart
Developers

Voice at wire speed.

A WebSocket API for low-latency streaming voice: send binary audio frames, get transcription, agent-routed answers, and synthesized speech back on the same connection.

Persistent connection

One authenticated WebSocket carries the whole exchange - no per-utterance HTTP overhead.

Binary audio frames

Stream microphone audio directly; responses return as text plus base64 speech.

Full pipeline access

Voice traffic runs the same Silent Core routing and agents as text - build a voice product on the whole platform.

Authenticated WebSocketBinary frame streamingTTS responsesAgent routing included

Start building with Spiant

Free tier included. No credit card required.

Start freeView pricing