Telnyx Voice AI Agents
"Carrier-grade Voice AI from Telnyx. Sub-200ms latency, 80+ languages, A-level STIR/SHAKEN attestation, and one platform that replaces 5 vendors." [1]
Telnyx Voice AI Agents is a carrier-grade platform for building inbound and outbound voice AI, covering customer support automation, appointment scheduling, healthcare, and call center use cases across 45+ countries. Pricing is usage-based at $0.05 per minute with self-serve signup and no sales call required. The platform supports bring-your-own LLM and voice, function calling, SIP trunking, and SDKs for Node.js, Python, PHP, Java, Ruby, and Go. It holds SOC 2 Type II, HIPAA, GDPR, ISO 27001, and PCI DSS certifications, and customers include Dialpad, Alibaba, and Grupo Bimbo.
Best for / Avoid if
Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box
Avoid if: You want to try it free before paying
Pricing & procurement
- Pricing model
- Usage-based [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✗ No [4]
- Self-serve signup
- ✓ Yes
- Requires sales call
- ✗ No
- Enterprise plan
- ✓ Yes [5]
| Item | Per | Amount | Source |
|---|---|---|---|
| Conversational AI base rate (Voice AI agent orchestration) | minute | $0.05 | source |
| Call Control (telephony API call management) | minute | $0.002 | source |
| WebRTC (browser/SDK calling leg) | minute | $0.002 | source |
| SIP Trunking - inbound local calls (US) | minute | $0.0032 | source |
| SIP Trunking - outbound calls (US, starting rate) | minute | $0.005 | source |
| SIP Trunking - inbound toll-free calls (US) | minute | $0.015 | source |
| Speech-to-Text (STT) — included in Conversational AI base rate | minute | $0 | source |
| Text-to-Speech — Telnyx Natural/NaturalHD/Qwen3/Ultra voices (included in base rate) | character | $0 | source |
| Text-to-Speech — Amazon Polly Standard (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — Resemble TTS / Murf TTS (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — Inworld Mini TTS (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — Inworld Max TTS (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — Amazon Polly Neural / Rime TTS (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — Qwen3 TTS (premium TTS in Voice AI) | character | $0 | source |
| Text-to-Speech — MiniMax speech-2.8-turbo (premium TTS in Voice AI) | character | $0 | source |
| LLM — Telnyx Qwen3-235B (input, hosted in Voice AI) | 1M tokens | $0.6 | source |
| LLM — Telnyx Qwen3-235B (output, hosted in Voice AI) | 1M tokens | $2 | source |
| LLM — Kimi-K2.5 (input, hosted in Voice AI) | 1M tokens | $0.6 | source |
| LLM — Kimi-K2.5 (output, hosted in Voice AI) | 1M tokens | $3 | source |
| LLM — Kimi-K2.6 (input, hosted in Voice AI) | 1M tokens | $0.665 | source |
| LLM — Kimi-K2.6 (output, hosted in Voice AI) | 1M tokens | $4 | source |
| LLM — GPT-4o (input, via Telnyx in Voice AI) | 1M tokens | $2.5 | source |
| LLM — GPT-4o (output, via Telnyx in Voice AI) | 1M tokens | $10 | source |
| LLM — GPT-5.4 (input, via Telnyx in Voice AI) | 1M tokens | $2.5 | source |
| LLM — GPT-5.4 (output, via Telnyx in Voice AI) | 1M tokens | $15 | source |
| LLM — Claude Haiku 4.5 (input, via Telnyx in Voice AI) | 1M tokens | $1 | source |
| LLM — Claude Haiku 4.5 (output, via Telnyx in Voice AI) | 1M tokens | $5 | source |
| Cloud Storage (call recordings) — Standard | GiB per month | $0.006 | source |
| Cloud Storage (call recordings) — Embedded | GiB per month | $0.6 | source |
Capabilities
- Supported actions
- realtime_conversation, inbound_telephony, outbound_telephony, sip_trunking, call_transfer, function_calling, tool_calling, interruption_handling, byo_llm, byo_voice, call_recording, web_widget, webrtc, speech_to_text, text_to_speech, knowledge_base, batch_calling, mcp_integration, dtmf_handling, noise_suppression, voicemail_detection, answering_machine_detection, multi_participant_calls, stir_shaken_attestation, conversation_history, dynamic_variables [6]
- Regions
- 45+ countries with licensed carrier operations, United States, European Union, APAC, Latin America [7]
- Languages
- 80+ languages and dialects (per product page), 100+ languages supported across STT (per STT product page) [8]
- Input types
- PSTN phone call, SIP, WebRTC, MMS (image during voice call)
- Output types
- audio stream, call transcript, webhook events, call recording, conversation insights, structured conversation history
- Webhooks
- ✓ Yes [9]
- Sandbox / test mode
- ✗ No [10]
- SDK languages
- Node.js, Python, PHP, Java, Ruby, Go [11]
- MCP server
- ✓ Yes [12]
Trust & compliance
- SOC 2
- SOC 2 Type II [13]
- HIPAA
- ✓ Yes [14]
- GDPR
- ✓ Yes [15]
- ISO 27001
- ✓ Yes [16]
- PCI DSS
- ✓ Yes [17]
- Published SLA
- ✓ Yes [18]
- Rate limits
- Trial accounts: 2 concurrent outbound calls, 10 min/call max, 100 outbound calls/day, 10/hour. Level 2 verification: 10 concurrent calls. Inbound/outbound channel limits are configurable per application; paid accounts may request higher limits via support. [19]
- Known restrictions
- Trial accounts limited to $5 credit, 2 concurrent outbound calls, 10 min/call max, 100 outbound calls/day, No dedicated sandbox environment - testing done in live environment with trial account, Machine-generated voices on trial accounts require abuse disclaimer prepended, BYO third-party TTS (ElevenLabs, Azure) billed via bring-your-own-key, not through Telnyx, HIPAA: Telnyx claims conduit exception (no BAA required) but will discuss BAA with customers on request, STT included in Voice AI base rate; premium TTS voices (non-Telnyx) incur additional per-character fees
Developer surface
Integration
- API style
- rest
- Base URL
- https://api.telnyx.com/v2
- Version
- v2
- Versioning
- url
- Stability
- ga
- Auth methods
- api_key
- Error format
- vendor-specific
- Webhook signing
- ed25519
- Rate limit
- 2 / concurrent calls
Adoption & maturity
- Launched
- 2009-01-01
- Notable customers
- Dialpad, Alibaba, AudioCodes, UJET, Grupo Bimbo, Teletext Holidays
Other Realtime Voice Agent APIs
ElevenLabs Conversational AI (ElevenAgents)
"Deploy human-like Conversational AI in minutes. ElevenLabs delivers low latency interactions in dozens of languages with enterprise-grade security."
OpenAI Realtime API (gpt-realtime)
"The Realtime API enables low-latency, bidirectional audio communication for building voice agents and audio applications."
Twilio ConversationRelay
"Twilio's Conversation Relay empowers you to build powerful AI voice experiences for your customers. Let Twilio handle the heavy lifting of speech recognition, text-to-speech, and voice synthesis."
Vapi
"Build and deploy voice agents that deliver the outcomes you want at the scale your customers need."
Cartesia Line
"Turn any text agent into a world-class conversational agent, deployed anywhere."
Pipecat Cloud (Daily)
"The fastest path to production voice AI" - a managed hosting platform for deploying and scaling Pipecat agents in production with built-in infrastructure.
References
- ↑Description: telnyx.com
- ↑Pricing model: telnyx.com · telnyx.com
- ↑Published pricing: telnyx.com
- ↑Free tier: developers.telnyx.com
- ↑Enterprise plan: telnyx.com
- ↑Supported actions: telnyx.com · telnyx.com
- ↑Regions: telnyx.com
- ↑Languages: telnyx.com · telnyx.com
- ↑Webhooks: developers.telnyx.com
- ↑Sandbox: developers.telnyx.com
- ↑SDK languages: telnyx.com
- ↑MCP server: telnyx.com · developers.telnyx.com
- ↑SOC 2: telnyx.com · support.telnyx.com
- ↑HIPAA: support.telnyx.com · telnyx.com
- ↑GDPR: telnyx.com · telnyx.com
- ↑ISO 27001: telnyx.com · telnyx.com
- ↑PCI DSS: telnyx.com · telnyx.com
- ↑Published SLA: telnyx.com
- ↑Rate limits: support.telnyx.com · developers.telnyx.com
Change history
- 2026-06-21 Capabilities: {} → {"byo_models":true,"multilingual":true,"outbound_calling":true,"telephony_inclu…
- 2026-06-21 Summary Md: (none) → Telnyx Voice AI Agents is a carrier-grade platform for building inbound and out…
- 2026-06-21 Score Setup Speed: (none) → 60
- 2026-06-21 Score Docs Quality: (none) → 60
- 2026-06-21 Score Procurement Friction: (none) → 85
- 2026-06-21 Score Agent Friendliness: (none) → 80
- 2026-06-21 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
- 2026-06-21 Avoid If: (none) → You want to try it free before paying
- 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-21 Score Trust Readiness: (none) → 100
- 2026-06-21 Score Pricing Transparency: (none) → 85
- 2026-06-21 Docs URL: (none) → https://developers.telnyx.com/docs/overview
- 2026-06-21 Llms Txt Present: (none) → Yes
- 2026-06-21 Llms Txt URL: (none) → https://telnyx.com/llms.txt
- 2026-06-21 Rendering: (none) → static
- 2026-06-21 Has Structured Data: (none) → Yes
- 2026-06-21 Robots Allows Agents: (none) → No
- 2026-06-21 Openapi Spec URL: (none) → https://telnyx.com/openapi.json
- 2026-06-21 Status Page URL: (none) → https://status.telnyx.com
- 2026-06-21 Markdown Docs Served: (none) → Yes
- 2026-06-21 Markdown Docs URL: (none) → https://telnyx.com/products/voice-ai.md
- 2026-06-21 Output Types: set to audio stream, call transcript, webhook events, call recording, conversation ins…
- 2026-06-21 Webhooks Supported: set to Yes
- 2026-06-21 Sandbox Available: set to No
- 2026-06-21 SDK Languages: set to Node.js, Python, PHP, Java, Ruby, Go
- 2026-06-21 SDK Packages: set to Node.js, Python, PHP, Java, Ruby, Go
- 2026-06-21 MCP Server Available: set to Yes
- 2026-06-21 Pricing Model: set to usage_based
- 2026-06-21 Has Published Pricing: set to Yes
- 2026-06-21 Free Tier Available: set to No
- 2026-06-21 Self Serve Signup: set to Yes
- 2026-06-21 Requires Sales Call: set to No
- 2026-06-21 Enterprise Plan Available: set to Yes
- 2026-06-21 SOC 2: set to type_2
- 2026-06-21 HIPAA: set to Yes
- 2026-06-21 GDPR: set to Yes
- 2026-06-21 ISO 27001: set to Yes
- 2026-06-21 PCI DSS: set to Yes
- 2026-06-21 SLA Published: set to Yes
- 2026-06-21 Data Retention Policy URL: set to https://telnyx.com/privacy-policy
- 2026-06-21 Documented Rate Limits: set to Trial accounts: 2 concurrent outbound calls, 10 min/call max, 100 outbound call…
- 2026-06-21 Rate Limit Requests: set to 2
- 2026-06-21 Rate Limit Window: set to concurrent calls
- 2026-06-21 Known Restrictions: set to Trial accounts limited to $5 credit, 2 concurrent outbound calls, 10 min/call m…
- 2026-06-21 Auth Methods: set to api_key
- 2026-06-21 Auth Docs URL: set to https://developers.telnyx.com/auth.md
- 2026-06-21 API Style: set to rest
- 2026-06-21 Base URL: set to https://api.telnyx.com/v2
- 2026-06-21 API Version: set to v2
- 2026-06-21 Versioning Scheme: set to url
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/telnyx-voice-ai \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/telnyx-voice-ai/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'