Telnyx Voice AI (AI Assistants)
Carrier-owned voice-agent platform: Telnyx runs STT, TTS and orchestration on its own GPUs next to its telephony network for one engine rate, with LLM tokens and carrier minutes added on top.
Overview
Best for: High-volume phone agents where carrier + AI on one bill and low telephony cost matter.
At a glance
Latency is a vendor marketing claim (sub-500 ms). $0.05/min engine includes Telnyx-hosted STT and TTS; LLM tokens and carrier minutes extra. 500 concurrent on pay as you go. 60-second per-call rounding. HIPAA listed but Voice AI BAA scope unverified.
Phone/SIP; WebSocket to assistant
Same
Not verified per voice; depends on STT/TTS chosen.
Vendor claims sub-500 ms end-to-end on marketing pages (vendor claim, not verified).
Owned network with 100+ PoPs; regional inference (e.g. Paris) per Telnyx pages.
Site footer lists ISO, PCI, HIPAA, GDPR, SOC 2 Type II; Voice AI BAA scope not verified.
Features
- turn detection
- interruptions
- tools/function calls
- knowledge base
- telephony (own carrier network)
- no-code portal builder
- MCP server
- WebSocket assistant access
Pricing
| What | Price | Unit |
|---|---|---|
| Voice AI engine (STT+TTS+orchestration) | $0.05 | per minute |
| LLM | ~$0.006 (Kimi on Telnyx GPUs) or provider rates | per minute equivalent |
| Inbound SIP trunking | from $0.0032 | per minute |
| Voice API platform fee | $0.002 | per minute |
Telnyx's own 'realistic all-in' is about $0.06/min (example: ~$13,700/month at 230,000 minutes) with an open model on Telnyx GPUs. High end assumes a frontier OpenAI/Anthropic model and outbound calls. Excludes 60-second per-call rounding.
Free tier: No free usage credits listed; $0 monthly fee on pay as you go.
Source: telnyx.com
Setup
- Create a Telnyx account and API key; buy a number.
- Create an assistant in the portal (no-code) or via POST /v2/ai/assistants with name, instructions and model.
- Assign the assistant to the number (portal) and call it; or connect over WebSocket for web clients.
Endpoint
POST https://api.telnyx.com/v2/ai/assistantsAuthentication
Authorization: Bearer <TELNYX_API_KEY>
Quick start javascript
// Create a Telnyx AI Assistant (then attach it to a number in the portal)
const res = await fetch("https://api.telnyx.com/v2/ai/assistants", {
method: "POST",
headers: { Authorization: "Bearer " + process.env.TELNYX_API_KEY,
"Content-Type": "application/json" },
body: JSON.stringify({
name: "Front desk",
instructions: "You are the front desk for Acme Dental. Disclose you are an AI. Book appointments; keep replies short.",
// model: optional; Telnyx applies a default if omitted (see API reference for voice/transcription objects)
}),
});
console.log(await res.json());Written from the current docs. Check the vendor's SDK version before you ship.
Warnings
60-second rounding
Telnyx says its estimates exclude per-call rounding to 60-second increments, so a 10-second call can bill as a full minute.
LLM not in the $0.05
Engine rate covers STT/TTS/orchestration only; LLM tokens and carrier minutes are extra. Prompt size drives LLM cost when using OpenAI/Anthropic.
No free credits
Unlike most platforms there is no free usage allowance; testing costs money from the first call.
BAA terms unclear
Site lists HIPAA, SOC 2 Type II, PCI, ISO and GDPR, but an explicit BAA covering Voice AI was not found; get it in writing.
Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.
Limits
- Pay as you go: 500 concurrent calls, 100 API requests/s
- Per-call rounding to 60-second increments
Models and products
| Name | Status |
|---|---|
| Voice engine | GA |
| LLM | GA |
| Plans | GA |
Docs and sources
Docs
Sources used
- telnyx.com/pricing/voice-ai
- developers.telnyx.com/api-reference/assistants/create-an-assistant
- developers.telnyx.com/docs/inference/ai-assistants
- telnyx.com/products/llm-library
Exact voice/transcription JSON fields; LLM per-token tables; latency claim.