Saaya Agents

Define once. Run everywhere.

The agent runtime at the heart of Saaya. Wire up identity, knowledge, voice, avatar, tools, and channels in one config, deploy to phone, web, and WhatsApp from the same definition.

What it is

Agents that actually feel like agents.

A Saaya Agent is a single configuration object, prompt, knowledge, tools, voice, avatar, language, and channel, that compiles to a real-time pipeline. The same agent picks up phone calls, joins WhatsApp threads, and shows up on your website chat bubble. No three-platform Frankenstein.

You version every change. You roll forward and back. You A/B test prompt blocks against each other in production. You watch live transcripts and replays of every session. The boring engineering parts, the orchestration, the model swaps, the retries, the consent flows, Saaya handles. You write the agent.

Under the hood, Saaya is provider-agnostic by design. OpenAI, Anthropic, or Gemini for the brain. ElevenLabs, Cartesia, or Sarvam for the voice. Anam, Simli, or Tavus for the avatar. Switch any layer with a config flag. No rewrites, no lock-in.

Capabilities

Everything you need under the hood.

Agents ships with the boring-but-load-bearing pieces every production deployment needs.

Multimodal in one config

Voice, chat, and video are first-class on every agent. One prompt, three channels, Saaya handles the channel-specific rendering (no bullets read aloud over voice, no awkward silences on chat).

Provider-agnostic stack

Swap LLM, TTS, STT, and avatar providers per agent or per session. No rewrites. Cost-route to Haiku for triage, Opus for complex calls.

Versioned prompts

Every agent change is a new version. Roll forward, roll back, A/B test individual prompt blocks in production traffic. Audit who changed what, when.

Native tool use

Connect calendars, CRMs, payment systems, internal APIs as tools. Saaya handles function-calling schemas and retry logic out of the box.

20+ languages, including Indic

Hindi, Tamil, Telugu, Kannada, Marathi, Bengali, Gujarati, Punjabi, Malayalam, all native-quality. Code-switching supported (Hinglish actually works).

Production-grade safety

Strict-citation knowledge grounding, sentiment-based escalation, per-region consent flows, PII redaction on transcripts. All on by default.

How it works

Four steps from blank canvas to production.

A new agent is live in fifteen minutes. Iteration after that is single-file edits.

  • 01

    Define identity

    Write the system prompt, pick a voice, pick an avatar (optional), pick a language. XML-tagged template starters for every common use case.

  • 02

    Connect knowledge

    Attach one or more Knowledge Bases. The agent answers from your docs with citations, strict-citation refuses to hallucinate.

  • 03

    Wire tools & channels

    Add functions for the things the agent should do (book a meeting, refund an order). Pick channels: phone, WhatsApp, web, video.

  • 04

    Deploy & version

    Ship the agent. Watch the session viewer. Iterate the prompt and bump the version. Roll back if a release goes sideways.

  • For developers

    A working agent, in fifteen lines.

    The same agent definition compiles to phone, web, and WhatsApp, no per-channel code.

    TypeScript SDK
    import { createAgent } from '@saaya/sdk'
    
    export const maya = createAgent({
      name: 'maya-inbound',
      identity: {
        role: 'Inbound sales qualifier at Acme.',
        objective: 'In under 180s, qualify and book a demo.',
        voice: { provider: 'elevenlabs', voiceId: 'rachel' },
        language: 'en-US',
      },
      knowledge: ['kb_product_docs', 'kb_pricing'],
      tools: ['get_calendar_availability', 'book_meeting', 'send_whatsapp'],
      channels: ['phone', 'whatsapp', 'web'],
      guardrails: {
        strictCitation: true,
        consent: 'auto-by-region',
        escalateOnSentimentBelow: 0.3,
      },
    })
    Pricing

    On every tier, what you get.

    Agents are the core product. Every plan includes the runtime; the difference is volume and provider freedom.

    Free

    1 production agent · 100 voice minutes/month · 1K chat messages · OpenAI + ElevenLabs only · Saaya branding on disclosures.

    Growth

    Unlimited agents · 5K voice minutes · 100K chat messages · all LLM/TTS providers · Custom branding · Strict-citation mode · Versioning & rollbacks.

    Enterprise

    SSO + SOC2 + DPA · BYO model keys · Self-hosted KB option · EU/India residency · Dedicated success manager · 99.95% SLA.

    See it in context

    Pair this with the right Solution.

    FAQ

    Frequently Asked Questions.

    Final step

    Build your first agent.

    Free tier ships a working agent in fifteen minutes. No credit card. Early-bird pricing locked in for life on paid plans.

    Get started with AgentsTalk to founders

    Free plan · No credit card · 15-min setup