Voice Agent API

Build realtime voice agents on one API, with the benchmark voice model and a bill that fits on one line.

Get your free API key Read the docs

60 free agent minutes to start. Commercial use, no credit card.

  • $0.07/min all-in on Pro (LLM + STT + TTS + telephony)
  • $0.068/min on Scale, from $0.06/min on Enterprise
  • 60 free minutes every month with commercial use
  • Simba 3.2 statistically tied for #1 on the Artificial Analysis TTS leaderboard
  • Sub-100ms first audio from a streaming-native voice model
  • SOC 2 Type II certified
  • Python and TypeScript SDKs
  • Tool kinds: builtin, webhook, client, MCP
Start building

From key to production in three steps.

01

Get a key

Sign up and issue a key in under a minute. No credit card, and the free tier is cleared for commercial use.

02

Make the first call

One REST endpoint, with Python and TypeScript SDKs. The sample above runs as-is once your key is in.

03

Go to production

Rates drop as your volume grows, and SOC 2 Type II, SSO and a DPA are ready when procurement asks.

Get your free API key
Enterprise

Enterprise-ready when you are.

Start on the free tier today and bring procurement in later. SOC 2 Type II, SSO, a signed DPA and volume pricing are all here when you need them, and teams with heavy traffic or a regulated surface get a Forward Deployed Engineer building alongside them. Most ship their first use case in two to three weeks.

Talk to sales
FAQ

Frequently asked questions

What is a voice agent API?
A voice agent API is a developer interface for running a two-way voice conversation with an AI agent. It handles speech-to-text on the caller side, an LLM to reason and call tools, text-to-speech to answer back, and the orchestration that manages turns, interruptions, and telephony. SpeechifyAI bundles all four into one per-minute rate.
How much does the SpeechifyAI Voice Agent API cost?
One all-in rate per minute. Pro is $0.07/min, Scale is $0.068/min, and Enterprise starts from $0.06/min. The LLM, speech-to-text, text-to-speech, and telephony orchestration are all included, with no passthrough or per-token math. 60 minutes are free every month with commercial use.
How fast is it?
Simba 3.2, the voice model behind every agent, produces first audio in under 100ms and is statistically tied for first place on the Artificial Analysis text-to-speech leaderboard. Because it streams natively, replies start sounding while the rest of the sentence is still rendering.
Can a voice agent handle phone calls?
Yes. Agents take inbound calls on a provisioned number, take inbound calls on a SIP trunk you already own, make outbound calls, or run over WebRTC in a browser. The same agent config drives every surface.
Which SDKs are available?
Official Python and TypeScript SDKs, plus a plain REST endpoint at api.speechify.ai/v1/agents. Both SDKs read the SPEECHIFY_API_KEY environment variable.
Related
voice agent platform conversational AI Pricing Elevenlabs Vapi Deepgram

Start building in minutes.

Issue a key, paste the sample, and hear your first request come back. Free while you build, and priced per character the day you ship.

Get your free API key Read the docs

60 free agent minutes to start. Commercial use, no credit card. SOC 2 Type II.