unpod logo
PlaygroundAboutBlogDocs
Github
Developer PlatformBuild, ship and observe voice agents on one platform.Platform
Build
IDE for Voice AgentsDesign and preview conversation flowsPlaybooksKick-start your agent with community playbooksFramework & SDKsPython, Node, REST and MCP
Ship
TelephonyCarrier-grade telephony, numbers, HD qualitySpeech InfraSTT, TTS models, fault-tolerant orchestrationContact CenterOpen-source contact center for large teams
Observe
Observability & AnalyticsMonitor and debug every call
unpod logo

Realtime voice + messaging infrastructure. An open-source conversation framework and CPaaS, on metered telephony + speech - so any agent can call and text the real world.

GitHubDocumentation

Products

  • Developer Platform
  • Unpod (OSS CPaaS)
  • SuperDialog

Developers

  • Documentation
  • GitHub
  • API reference

Company

  • About
  • Privacy
  • Terms
© 2026 Unpod.ai · All rights reservedMade in India ❤️ · Built for the world

The speech layer for any agent.

Streaming speech-to-text, text-to-speech and turn-taking over one real-time pipeline. Your code receives clean text and replies with text - we handle the audio.

Start Building →Read the docs
How it works

A real-time speech pipeline, in four steps.

Pick models, wire the pipeline and stream audio — with fault-tolerant orchestration.

  1. 01

    Pick your models

    Choose STT and TTS models per language, quality and latency budget.

  2. 02

    Configure the pipeline

    Set VAD, endpointing and barge-in so turns feel natural.

  3. 03

    Stream audio

    Audio streams in, text streams out — so an existing text agent or chatbot drops straight into voice.

  4. 04

    Tune & scale

    Swap models live and let orchestration fail over without dropping calls.

The flow · end-to-end

Phone → Speech → your playbook.

Unpod handles the phone and the speech. Text arrives at your SuperDialog playbook and you reply with text - the prompt, tools and customer data stay on your side.

inbound audiostreamed textoutbound audioreply textCaller+91 9XXXX XXXXXVoiceWhatsAppSMSOne number · inbound & outboundUnpodTelecom + Speech+91 80 4555 0142STTstreaming · voice → text~120msRouteunified webhook · threads~30msTTSneural · text → voice~180msAll-in60% less cost vs legacy stacks{ }Your playbookPOST /unpod✓Your SuperDialog flow✓Your LLM + tools✓Your customer data
Caller
+91 9XXXX XXXXX
VoiceWhatsAppSMS
↓inbound audio↑outbound audio
Unpod
Telecom + Speech
+91 80 4555 0142
STTstreaming · voice → text~120ms
Routeunified webhook · threads~30ms
TTSneural · text → voice~180ms
All-in60% less cost vs legacy stacks
↓streamed text↑reply text
{ }
Your playbook
POST /unpod
  • ✓Your SuperDialog flow
  • ✓Your LLM + tools
  • ✓Your customer data
Total end-to-end < 330ms·STT 120 + Route 30 + TTS 180
Capabilities

Natural voice, without the plumbing.

STT, TTS and turn-taking managed for you - your agent stays plain text while callers hear a real conversation.

STT

Streaming transcription

Converts caller audio to clean text in real time for your agent logic.

  • Low-latency STT
  • Word-level stream
  • Provider choice
TTS

Voice synthesis

Streams agent replies back as natural, neural speech to the caller.

  • Neural TTS
  • Streamed playback
  • Custom voices
VAD

Turn-taking & endpointing

Detects when the caller stops speaking so the agent replies at the right moment.

  • Voice activity detection
  • Endpointing
  • Natural turns
Barge-in

Barge-in handling

Lets callers interrupt mid-response, just like a real conversation.

  • Interrupt detection
  • Instant stop
  • Human feel
Profiles

Voice profiles + failover

Pre-built or custom STT/TTS combinations with automatic provider failover.

  • STT/TTS combos
  • Custom profiles
  • Auto failover
Channels

Phone + web, one pipeline

Accept users over PSTN/SIP or the browser and mobile SDK - no carrier setup required.

  • PSTN / SIP
  • Web + mobile SDK
  • No carrier setup

Give your agent a voice.

Drop the speech layer under any agent - phone or web - and ship natural, low-latency conversations.

Start Building →View on GitHub
✓ Streaming STT + TTS✓ Barge-in + VAD✓ No carrier setup
Speech Infra · Unpod