Voice agents that answer the phone.

Realtime voice agents on one all-in API, with no stitched stack and no spreadsheet bill.

$0.07/min: All-in on Pro, including LLM, speech, and telephony
60 minutes: Free every month, with commercial use

bash

curl -X POST https://api.speechify.ai/v1/agents \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Front desk",
    "prompt": "You book and reschedule appointments.",
    "voice_id": "beatrice_32"
  }'

Live

Talk to one right now.

A real agent on the same runtime you would ship, not a recording. Start the call and ask it to book or move an appointment.

Agent embed

Add a talking agent to any page.

bash

curl -X POST https://api.speechify.ai/v1/agents   -H "Authorization: Bearer $SPEECHIFY_API_KEY"   -H "Content-Type: application/json"   -d '{
    "name": "Support Agent",
    "prompt": "You are a friendly support agent. Help callers book or reschedule appointments and answer basic questions.",
    "first_message": "Hi, this is Sabrina. How can I help today?",
    "voice_id": "sabrina",
    "language": "en"
  }'

html

<script src="https://api.speechify.ai/v1/widget/agents.js"></script>
<speechify-agent agent-id="agent_01HS..."></speechify-agent>

Create an agent, allowlist your origin, then paste the widget snippet.

First request

Choose parameters inline, then copy the request.

bash

curl -X POST https://api.speechify.ai/v1/audio/speech \

-H "Authorization: Bearer $SPEECHIFY_API_KEY" \

-H "Content-Type: application/json" \

-d '{

"input": "The quick brown fox jumped over the lazy dog",

"model": "simba-3.2",

"voice_id": "",

"audio_format": "mp3"

curl -X POST https://api.speechify.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The quick brown fox jumped over the lazy dog",
    "model": "simba-3.2",
    "voice_id": "geffen_32",
    "audio_format": "mp3"
  }'

Input style updates the SSML in the request.

bash

curl -X POST https://api.speechify.ai/v1/voices \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -F "sample=@reference.wav" \
  -F "display_name=Demo narrator"

Clone once from a clean 10-30 second sample. Use the returned voice ID in the same speech endpoint you already use for built-in voices.

Live agent

Ask Sabrina to find a time.

Speak naturally. The transcript and scheduling tool update while you talk.

Production runtime

Acme clinic agent

Ready to connect

Try asking “Book me Tuesday afternoon.”

Your live transcript will appear here after you connect.

POST /v1/audio/speech

Run the request, then play the result.

Idle

Response appears here after the request completes.

Response JSON

Selected sample: Geffen, neutral.

Voice clone

Reference in, cloned narration out.

Ready

Reference voice

Clone response JSON

SpeechifyAI demos

SpeechifyAI Agents embed with the web component. SpeechifyAI Build supports text-to-speech, emotion control, voice selection, and voice cloning through the API.

curl -X POST https://api.speechify.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The quick brown fox jumped over the lazy dog",
    "model": "simba-3.2",
    "voice_id": "geffen_32",
    "audio_format": "mp3"
  }'

Build your own Explore the full API

Capabilities

Six things that ship in the platform.

Not add-ons, and not a stack you assemble. Every agent gets the same set behind one configuration.

Tools & function calling

Let agents call your APIs mid-conversation to look things up, take actions, and complete tasks in real time.

Explore

Knowledge base

Ground every answer in your own content with built-in retrieval. Upload documents, files, and sitemaps.

Explore

Memory

Agents remember context within a conversation — and across calls — for interactions that feel continuous.

Explore

Phone numbers & telephony

Inbound and outbound calling over SIP. Provision numbers and connect agents straight to the phone network.

Explore

Webhooks & events

Stream conversation events to your backend as they happen, with signed, verifiable payloads.

Explore

Testing & simulation

Validate behavior before you ship with reply, tool, and full-conversation simulation tests.

Explore

Benchmark

Fast enough to feel like a conversation.

The voice behind every agent is Simba 3.2, #1 on the Artificial Analysis TTS leaderboard at roughly a third of the price of the model closest to it.

Sub-100ms

First audio

Sub-1s

End to end, warm

20+

Realtime voices

Simba 3.2 on Artificial Analysis

See the models

Pricing

One line item per minute.

Most platforms quote a platform fee, then bill the LLM, the speech models, and the telephony on top. This is the whole bill.

$0.07/min

All-in on Pro

Included

LLM, STT & TTS

Free minutes / month

SOC 2 Type II

Certified

See full pricing How voice-agent pricing works

Industries

The API is the same; the workflows differ.

Prebuilt patterns and real sample calls for the verticals where the compliance posture matters as much as the transcript.

3 workflows

Healthcare

From inquiries and scheduling to triage, follow-up, and prescription management, SpeechifyAI voice agents automate patient and provider workflows without sacrificing care quality.

Learn more 3 workflows

Insurance

From claims intake and policy quotes to renewal reminders and Medicare enrollment, SpeechifyAI voice agents automate policyholder and prospect workflows while maintaining compliance.

Learn more 3 workflows

From lead qualification and showing scheduling to tenant support and maintenance requests, SpeechifyAI voice agents automate every phone-driven workflow across brokerages, property management, and mortgage.

Learn more

All industries

Compare

Priced against the alternatives.

The landscape is fragmented: platform fees, LLM passthrough, per-minute telephony, and compliance sold as extras. These put the whole bill side by side.

vs ElevenLabs

ElevenLabs Conversational AI is a voice-first agent layer built on the company's well-known TTS. SpeechifyAI is all-in

Compare

vs Vapi

Vapi is a flexible, API-driven way to build voice agents

Compare

vs Retell

Retell gives developers low-latency voice infrastructure with itemized pricing

Compare

All comparisons

FAQ

Frequently asked questions

What is SpeechifyAI Agents?

SpeechifyAI Agents is a platform for building realtime voice agents that listen, reason, and speak. Each agent combines speech-to-text, an LLM with tool calling, a knowledge base, per-caller memory, and telephony, billed as one all-in per-minute rate rather than a stack of separate vendor charges.

What can a voice agent do?

It can answer and place calls, resolve support questions, book and reschedule appointments, qualify leads, run outbound campaigns, and navigate other phone systems. It grounds answers in your knowledge base, calls your APIs mid-conversation, and hands off to a human when it should.

How much does it cost?

One all-in rate: $0.07/min on Pro, $0.068 on Scale, from $0.06 on Enterprise, with the LLM, speech, and telephony included. 60 minutes are free every month with commercial use, no card required.

How do I start?

Get an API key, create an agent with one POST to /v1/agents, and point it at a phone number or a web session. The Python and TypeScript SDKs and the docs cover tools, knowledge bases, memory, and testing.

Start building

Realtime voice agents on one all-in API, with no stitched stack and no spreadsheet bill.

Get an API key, free Talk to sales

Voice agents that answer the phone.

Talk to one right now.

Add a talking agent to any page.

Choose parameters inline, then copy the request.

Ask Sabrina to find a time.

Run the request, then play the result.

Reference in, cloned narration out.

Six things that ship in the platform.

Tools & function calling

Knowledge base

Memory

Phone numbers & telephony

Webhooks & events

Testing & simulation

Fast enough to feel like a conversation.

One line item per minute.

The API is the same; the workflows differ.

Healthcare

Insurance

Real Estate

Priced against the alternatives.

vs ElevenLabs

vs Vapi

vs Retell

Frequently asked questions

Start building