Voice AI indistinguishable from humans.

SpeechifyAI is a research lab advancing the science of speech synthesis, voice cloning, emotional expression, and voice agents.

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 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": "",

"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-3.0",
    "voice_id": "george",
    "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.

Voice session

Agent handles the first turn.

Live flow

Acme support agent

Ready to connect

Agent: “Hi, this is Sabrina. How can I help today?”
Caller: “Can I move my appointment?”
Agent searches policy and checks calendar tool.
Agent: “Yes. I have Tuesday at 2:30 open.”

POST /v1/audio/speech

Run the request, then play the result.

Idle

Response appears here after the request completes.

Response JSON

Selected sample: Simba 3.0, George, 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-3.0",
    "voice_id": "george",
    "audio_format": "mp3"
  }'

Featured Model

Simba 3.0

Our flagship streaming-native model. Lower time-to-first-byte than previous generations, with finer-grained emotional control, zero-shot voice cloning, and SSML prosody. Language coverage is expanding.

Streaming-native architecture Emotional expression Zero-shot voice cloning SSML prosody control

Explore our models

“Every moment of light and dark is a miracle.”

Technology

Reference

Clone

Zero-Shot Voice Cloning

Clone any voice from a short reference clip. Simba captures speaker identity — timbre, cadence, and micro-expressions — from as little as 10 seconds of audio.

Neutral

Happy

Sad

Excited

Calm

Emotion Control

Generate the same text with different emotional expressions. Simba models emotion at the prosody level — not just speed and pitch, but the subtle rhythmic and tonal patterns that convey feeling.

en-US

es-MX

fr-FR

de-DE

ja-JP

pt-BR

Multilingual Synthesis

Native-quality speech across 30+ locales. Each language uses voices recorded in that locale for natural pronunciation and prosody, with mixed-language input handled automatically.

Build with our models

A single API to access all Speechify models. Streaming, voice cloning, emotion control — everything in a few lines of code.

Explore the API Documentation

bash

curl -X POST https://api.speechify.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, world.",
    "voice_id": "george",
    "audio_format": "mp3"
  }'

SpeechifyAI is building the future of voice

We're a research lab focused on speech synthesis, voice understanding, and audio intelligence. Our work spans fundamental research in neural speech generation, zero-shot voice cloning, and emotional expression modeling — turning the nuances of human speech into something machines can learn and reproduce.

Learn about our lab