Now with Claude Desktop MCP Integration & Structured Outputs

Build voice agents &
text chatbots in minutes

Real-time speech-to-speech, voice-to-text, and text chat orchestration. Failover, RAG, structured outputs, cost tracking — one API, zero infrastructure.

3
Pipeline Modes
20+
AI Models
30+
API Endpoints
<2s
Response Latency
your-website.html
<div id="chat"></div>
<script src="https://api.neuralspeak.ai/sdk/neuralspeak.js"></script>
<script>
  NeuralSpeak.init({ apiKey: 'ns_pub_...', containerId: 'chat' });
</script>
// That's it. All config lives in the dashboard.

Voice agents, text chatbots, or both

Same SDK. Same dashboard. Same billing. Same API keys. Pick the mode per service.

🎙

Voice Agent

Full speech-to-speech conversations. User speaks, AI responds with natural voice. Real-time NDJSON streaming with parallel TTS and sub-2s perceived latency.

STT → LLM → TTS
💬

Text Chatbot

LLM-powered chatbot with RAG knowledge base. Markdown rendering, structured outputs, zero audio overhead. Deploy customer support, sales, or FAQ bots instantly.

LLM + RAG
🔀

Voice-to-Text

User speaks, AI responds with text. Perfect for medical intake forms, dictation, accessibility tools, and voice-driven search.

STT → LLM

The orchestration engine

You send audio or text. The engine handles the rest — routing, failover, caching, analysis — and streams back the response.

🎙 Voice Agent Flow
User speaks
Recording audio...
AI responds with voice
PROCESSING EXCHANGE
NeuralSpeak
👤
Input
audio / text
📤
Output
streaming
📊
Structured
hidden output
🎧
Transcription
🧠
AI Response
🔊
Voice Synthesis
📚
Knowledge
📊
Analysis
🔄
Failover
Failover ready
Parallel TTS
Cache active
Cost tracking
💬 Text Chat Flow
 
 

Choose your path

Start simple and go deeper when you need to. Both paths lead to production.

EASY MODE

Zero code. 3 minutes.

No tech skills needed. Set it up yourself in minutes — the dashboard guides you step by step. Add 3 lines of code to your product, and you're live.

1

Configure in Dashboard

Pick a mode (voice/text/both), write prompts, select providers, upload docs, customize colors. All visual, all clicks.

2

Copy & paste the snippet

One <script> tag + one line of JavaScript. The SDK auto-loads all settings from your dashboard.

3

Done. It's live.

Voice agent or chatbot on your site. Change prompts, providers, or theme in dashboard — instant update, zero redeploy.

<script src=".../neuralspeak.js"></script>
<script>
  NeuralSpeak.init({ apiKey: 'ns_pub_...' });
</script>
OR
FULL CONTROL

Your backend. Your rules.

For teams who need dynamic context, custom UIs, user-specific data, and deep integration.

1

Build your backend proxy

Your server holds the secret key (ns_sec_). Proxy requests to NeuralSpeak API. Inject CRM data, user profiles, order history mid-conversation.

2

Use REST API or SDK

Build your own UI with the headless REST API. Or use the SDK with custom themes, layouts, and callbacks. Structured outputs trigger your automations.

3

Scale with confidence

Failover chains, rate limiting, webhooks, usage analytics, session history, per-key CORS — production-grade from day one.

# Your backend (Python/Node/any)
resp = requests.post(
  f"{API}/v1/sessions/message",
  headers={"Authorization": f"Bearer {SEC_KEY}"},
  json={"text": user_input, "project_id": pid}
)

Or connect Claude via MCP and let AI set up NeuralSpeak for you.

Everything you need. Built in.

🔄

Automatic Failover

STT, LLM, and TTS each have failover chains. Groq down? Deepgram takes over. Azure timeout? ElevenLabs kicks in. Zero downtime for your users.

Parallel TTS + Reordering

Multiple sentences synthesized simultaneously via Semaphore(3), reordered for sequential playback. Sub-2s perceived latency.

📚

RAG / Knowledge Base

Upload PDFs, TXT, DOCX. Auto-chunked, embedded via OpenAI, stored in pgvector. Top-K retrieval per query. Configurable per service.

🧠

Structured Outputs

Hidden LLM analysis after each exchange. Lead scoring, medical triage, ticket categorization. JSON schema validation, preset templates, webhook delivery.

🤖

AI Action Execution

Bot proposes actions, user confirms, system executes. Whitelist-based, confirmation flow, audit log. Our own help bot showcases this live.

💰

NST Token Billing

Transparent cost tracking per exchange: STT + LLM + TTS + RAG. 5 subscription tiers, NST top-up packs (never expire), CSV export, projected costs.

🎨

Customizable Widget

15+ settings: themes (dark/light/auto/custom), layouts (full/compact/minimal), positions, colors, branding, custom CSS, word highlight animation. All from dashboard.

🔑

API Key Security

Public keys (ns_pub_) for frontend, secret keys (ns_sec_) for backend. Per-key project binding, IP allowlist, domain CORS, TTL expiry, rate limiting, scope enforcement.

🔔

Webhooks

Session completed, usage threshold, analysis ready. HMAC-SHA256 signing, delivery logs, retry logic. Push events to your backend in real-time.

🌍

Multi-Provider

Groq Whisper, Deepgram Nova-3, OpenAI GPT-4o, Anthropic Claude, Azure Speech, ElevenLabs. Pick per service. Switch providers with zero code changes.

📊

Analytics Dashboard

4 charts (NST, exchanges, cost, prediction), per-service breakdown, session transcripts, request logs with pipeline detail. Filter by period, export CSV.

🧩

Dynamic Context Injection

Inject user-specific data mid-conversation via PUT /sessions/{id}/context. Personalize responses with CRM data, user profiles, order history — in real time.

Built for every industry

Same platform, different prompts. Configure once, deploy everywhere.

🏢

Customer Support

Voice or text support agent with RAG over your docs. Auto-categorize tickets via structured outputs.

🎓

Education

Language tutors, exam prep, interactive lessons. Voice-based with real-time translations and proficiency assessment.

🏥

Healthcare

Medical intake forms, symptom collection, triage. Structured outputs for EHR integration. Never diagnoses — just collects.

💼

Sales

Lead qualification bots, product demos, pricing queries. Dynamic context from CRM. Intent scoring via structured outputs.

📱

Telecom

Plan comparison, account info, top-up assistance. Text chatbot with RAG over offer documents. Multi-language support.

🍽

Hospitality

Restaurant concierge, hotel booking, menu recommendations. Voice agent in any language with time-aware prompts.

🚀

Your Industry

Anywhere a voice or text AI can help — HR onboarding, legal intake, insurance claims, real estate, fitness coaching, and more. Same platform, your prompts.

From zero-code to full control

Four ways to integrate. All battle-tested with real showcase apps.

Easiest

Plug & Play

Static HTML + SDK. All config in dashboard. Zero backend needed.

<script> NeuralSpeak.init({ apiKey: 'ns_pub_...', containerId: 'chat', }); </script>
Custom UI

Themed Widget

SDK with custom theme, labels, layout. Override server config locally.

NeuralSpeak.init({ apiKey: 'ns_pub_...', containerId: 'chat', theme: { accentColor: '#e11d48' }, labels: { ready: 'Tap to talk' }, });
Backend proxy

Own Backend

Your server proxies requests. Inject CRM/user data mid-conversation.

// Your backend (ns_sec_ key): fetch(API + '/sessions/' + sid + '/context', { method: 'PUT', body: JSON.stringify({ mode: 'prepend_next', text: userContext }) });
Full control

Headless REST API

No SDK. Build your own UI. Full pipeline control.

curl -X POST \ $API/v1/sessions/message \ -H "Authorization: Bearer $KEY" \ -d '{"text":"Hello", "project_id":"..."}'

Simple, transparent pricing

Billed in NST (NeuralSpeak Tokens). Voice exchange ≈ 3 NST. Text exchange ≈ 0.5 NST. No hidden fees.

Free
$0/mo
500 NST included
~40 min voice · ~1K texts
  • 1 service
  • 2 API keys
  • All AI providers
  • 3 pipeline modes
  • RAG / knowledge base
  • Help bot
  • Structured outputs
  • Analytics + CSV
  • Webhooks
  • White-label
  • Custom LLM
  • SSO / SAML
  • On-premise
  • Community
  • SLA
Start free
Starter
$29/mo
10,000 NST
~14h voice · ~20K texts
  • 3 services
  • 10 API keys
  • All AI providers
  • 3 pipeline modes
  • RAG / knowledge base
  • Help bot
  • Structured outputs
  • Analytics + CSV
  • Webhooks
  • White-label
  • Custom LLM
  • SSO / SAML
  • On-premise
  • Email
  • SLA
Get started
Standard
$79/mo
30,000 NST
~42h voice · ~60K texts
  • 10 services
  • 50 API keys
  • All AI providers
  • 3 pipeline modes
  • RAG / knowledge base
  • Help bot
  • Structured outputs
  • Analytics + CSV
  • Webhooks
  • White-label
  • Custom LLM
  • SSO / SAML
  • On-premise
  • Email + chat
  • 99.5% SLA
Get started
Business
$199/mo
100,000 NST
~139h voice · ~200K texts
  • Unlimited services
  • Unlimited API keys
  • All AI providers
  • 3 pipeline modes
  • RAG / knowledge base
  • Help bot
  • Structured outputs
  • Analytics + CSV
  • Webhooks
  • White-label
  • Custom LLM
  • SSO / SAML
  • On-premise
  • Priority
  • 99.9% SLA
Get started
Enterprise
Custom
Unlimited NST
volume pricing · custom rates
  • Unlimited services
  • Unlimited API keys
  • All + custom
  • 3 pipeline modes
  • RAG / knowledge base
  • Help bot
  • Structured outputs
  • Analytics + CSV
  • Webhooks
  • White-label
  • Custom LLM
  • SSO / SAML
  • On-premise
  • Dedicated AM
  • Custom SLA
Contact us

Need more NST? Buy top-up packs anytime — they never expire. See top-up pricing

Everything you need to get started

From 3-line embed to full backend integration. Comprehensive guides for every skill level.

🚀

Quick Start

Get your first AI service running in under 5 minutes.

1 Sign up and create a service in the dashboard
2 Configure prompts and select AI providers
3 Copy the embed snippet to your website
<script src="/sdk/neuralspeak.js"></script> <script> NeuralSpeak.init({ apiKey: 'ns_pub_...', containerId: 'chat', }); </script>

That's it. Your AI is live. All configuration lives in the dashboard — no code changes needed.

🔐

Authentication

Three auth levels for different use cases.

TypePrefixUse
Public keyns_pub_Frontend SDK embed
Secret keyns_sec_Backend API calls
JWT tokenBearerDashboard management

Public keys are safe to expose in HTML. They can only start conversations. Secret keys have full API access — never put them in frontend code.

🔌

REST API Reference

30+ endpoints for complete platform control.

Sessions (Public API)

POST /v1/sessions/start Create a new session
POST /v1/sessions/{id}/speech Send audio, get streaming response
POST /v1/sessions/message Text chat (no audio)
POST /v1/sessions/initial Generate AI greeting
GET /v1/sessions/{id}/history Conversation history
PUT /v1/sessions/{id}/context Inject context mid-session

Management (JWT)

POST /v1/auth/register Create account
POST /v1/auth/login Get JWT tokens
GET /v1/projects List services
POST /v1/projects Create service
PUT /v1/projects/{id} Update service config
POST /v1/projects/{id}/context Upload knowledge base file
GET /v1/usage Usage analytics
GET /v1/sessions List all sessions
POST /v1/api-keys Generate API key
GET /v1/sdk/config Widget config for SDK

Full interactive reference with schemas and try-it available in the dashboard.

💻

JS SDK

Zero-dependency embeddable widget.

NeuralSpeak.init({ apiKey: 'ns_pub_...', containerId: 'chat', // All optional — configured // in dashboard by default: pipelineMode: 'text-chat', theme: { preset: 'dark' }, labels: { ready: 'Ask me anything' }, layout: 'compact', position: 'bottom-right', showCost: false, // Callbacks: onMessage: (msg) => { ... }, onAnalysis: (data) => { ... }, });

SDK auto-fetches config from dashboard via GET /v1/sdk/config. Local options override server defaults.

Streaming (NDJSON)

Real-time response format.

// Voice mode: {"type":"audio_chunk","index":0, "text":"Hello!", "audio_base64":"SUQz..."} // Text mode: {"type":"text_chunk","index":0, "text":"Hello! How can I"} // Completion: {"type":"complete", "cost":{"total_usd":0.003}, "analysis":{"intent":"greeting"}}

Structured outputs arrive in the complete event's analysis field — invisible to end users.

🔔

Webhooks

Real-time event notifications.

EventWhen
session.completedSession ends
usage.threshold80%/100% NST limit
analysis.readyStructured output done

HMAC-SHA256 signed. Delivery logs in dashboard. Configure in Webhooks settings.

🤖

Structured Outputs

Hidden AI analysis after each exchange.

// Configure per service: { "name": "Lead Scoring", "trigger": "after_every_exchange", "json_schema": { "intent": "string", "product": "string", "urgency": "high|med|low" }, "delivery": ["inline","webhook"] } // Result in complete event: {"type":"complete", "analysis": { "intent":"purchase", "product":"Premium 30GB", "urgency":"high" }}

Invisible to end users. Perfect for CRM integration, ticket routing, compliance monitoring.

📚

RAG / Knowledge Base

Upload docs, AI answers from your content.

1 Upload PDF, DOCX, or TXT files in dashboard
2 Files auto-chunked & embedded (pgvector)
3 Per query: top-K relevant chunks injected into AI prompt

Configurable per service: chunk size (100-2000), overlap (0-500), top-K (1-20), embedding model. Test queries in dashboard.

Manage everything from Claude

Connect Claude Desktop to NeuralSpeak via MCP (Model Context Protocol). Create services, configure prompts, upload knowledge base, set up webhooks — all through natural conversation.

Claude Desktop conversation
You: Create a customer support chatbot in Polish with RAG
Claude: Done! I've created "Support Bot" with:
✓ Pipeline: text-chat
✓ Language: Polish
✓ RAG: enabled (chunk_size: 400, top_k: 5)
✓ API key: ns_pub_a8Kx...
You: Set up dark theme with red accent
Claude: Widget updated: dark theme, accent #e11d48. ✓
40 MCP Tools
100% feature parity with dashboard
Services
Create, configure, delete
Knowledge Base
Upload docs, test RAG
Widget & Themes
Colors, layout, branding
Providers
STT, LLM, TTS selection
Structured Outputs
Hidden AI analysis
Webhooks
Create, test, manage
Security
CORS, rate limits, IP
Code Generation
Embed + backend code
Setup in 2 minutes: pip install neuralspeak-mcp → add config → restart Claude

Ready to ship AI conversations?

Free tier included. No credit card required. Deploy your first voice agent or chatbot in under 5 minutes.