Text-to-Speech API

The text-to-speech API with the #1-benchmarked voice, from $6 per 1M characters.

50K free characters to start. Commercial use, no credit card.

bash

curl -X POST https://api.speechify.ai/v1/audio/speech \
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Ship production voice in a few lines of code.",
    "model": "simba-3.2",
    "voice_id": "george",
    "audio_format": "mp3"
  }'

Simba 3.2 statistically tied for #1 on Artificial Analysis
Sub-300ms first byte
POST /v1/audio/speech and POST /v1/audio/stream
5 audio formats, 13 emotions, SSML
From $6 per 1M characters

Try it

Hear it before you write a line.

This runs a real request against the API and plays what comes back. Pick a voice and an emotion, then run it.

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.

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"
  }'

Run this with your own key Free tier, no credit card.

SpeechifyAI at a glance

Top-ranked

Artificial Analysis leaderboard

per 1M characters

30+

languages, 1,500+ voices

300ms

streaming first byte

Why developers choose Speechify

Top-tier voice, without the top-tier bill.

Top-ranked quality

Simba is a leading model on the Artificial Analysis leaderboard, above every ElevenLabs, OpenAI, and Google model.

A fraction of the cost

A flat rate per character, where the closest-ranked model costs nearly three times more and ElevenLabs' flagship runs ten times higher.

Drop-in compatible

One REST API with Python and TypeScript SDKs. Move off your current provider with minimal code changes.

Streaming-native

Built for real-time agents and low latency, with emotion control, SSML prosody, and zero-shot voice cloning.

Get your free API key

The math

What will text-to-speech cost at your volume?

SpeechifyAI is one flat rate per character. Most providers bill by quality tier, or by credits that convert to characters at a rate that shifts with your plan. Drag your monthly volume and switch the provider to see the difference. Rates are from each vendor's public pricing.

Your monthly volume

10 million characters / mo

≈ 1.7 million words

1M chars200M chars

Compare against

SpeechifyAI · flat rate one rate

$100 /mo

$10/1M PAYG · from $6/1M on Scale

Flat per-character billing
Voice cloning included
Commercial use on every plan
No credits, no token math

The same rate whatever the script. No tier picker, no credit math.

ElevenLabs · credit-based

$1,000 /mo

Credit-based, roughly $100–300 per 1M on lower tiers

10×

the SpeechifyAI rate per character

Rates vary by plan tier, model, and annual commitment.

SpeechifyAI at $10/1M characters on pay-as-you-go, dropping to $6 per 1M on Scale. Competitor rates are the neural / quality tier most teams ship on; standard tiers are cheaper but noticeably lower quality.

Cost at common volumes

Monthly volume	SpeechifyAI ($10/1M)	ElevenLabs (~$100/1M)	You save
1M chars	$10/mo	~$100/mo	$90/mo $1,080/yr
10M chars	$100/mo	~$1,000/mo	$900/mo $10,800/yr
100M chars	$1,000/mo	~$10,000/mo	$9,000/mo $108,000/yr

Get your free API key See all pricing

Start building

From key to production in three steps.

Get a key

Make the first call

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

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 text-to-speech API?

A text-to-speech API turns written text into spoken audio over a network request. You send text and a voice choice; it returns audio, either as a complete file or as a stream. SpeechifyAI's API adds SSML control, emotion, voice cloning, and speech marks, on a model statistically tied for first place on the Artificial Analysis leaderboard.

How fast is it?

Simba 3.2 produces first byte in under 300ms and is streaming-native, so audio starts playing before the full clip is generated. That makes it fast enough for realtime apps like voice agents and live captioning.

What does it cost?

Per character: from $6 per 1M on Scale, $8 on Pro, $10 on Starter, with no credit conversion or token math. The Free plan includes 50,000 characters a month with commercial use.

Which audio formats are supported?

Five: wav, mp3, ogg, aac, and pcm. The batch endpoint returns a full file including WAV; the streaming endpoint returns chunked mp3, ogg, aac, pcm, or u-law for telephony.

realtime text-to-speech streaming text-to-speech voice cloning Pricing Elevenlabs Google Openai what is text to speech text to speech latency

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

50K free characters to start. Commercial use, no credit card. SOC 2 Type II.

Text-to-Speech API

Hear it before you write a line.

Add a talking agent to any page.

Choose parameters inline, then copy the request.

Agent handles the first turn.

Run the request, then play the result.

Reference in, cloned narration out.

Top-tier voice, without the top-tier bill.

Top-ranked quality

A fraction of the cost

Drop-in compatible

Streaming-native

What will text-to-speech cost at your volume?

Cost at common volumes

From key to production in three steps.

Get a key

Make the first call

Go to production

Enterprise-ready when you are.

Frequently asked questions

Start building in minutes.