OpenAI & ElevenLabs Compatible

Text-to-Speech API
Natural. Fast. Affordable.

Turn text into lifelike speech with 35+ AI voices in 9 languages. Streaming support, word-level timestamps, and up to 90% savings vs ElevenLabs.

Get API Key →View Docs

Available voices

42+ voices across 9 languages

English (US)

A

Alloy

Neutral, balanced

N

Nova

Bright, friendly

E

Echo

Warm, conversational

O

Onyx

Deep, authoritative

H

Heart

Warm, engaging

B

Bella

Smooth, natural

M

Michael

Clear, professional

A

Aoede

Melodic, pleasant

K

Kore

Youthful, vibrant

J

Jessica

Friendly, approachable

N

Nicole

Polished, articulate

R

River

Calm, steady

S

Sarah

Warm, trustworthy

S

Sky

Light, airy

E

Eric

Confident, clear

F

Fenrir

Strong, resonant

L

Liam

Natural, versatile

P

Puck

Lively, expressive

A

Adam

Casual, relatable

S

Santa

Jolly, festive

English (UK)

A

Alice

Refined, elegant

E

Emma

Warm, natural

I

Isabella

Graceful, composed

L

Lily

Gentle, calming

D

Daniel

Confident, polished

F

Fable

Expressive, dynamic

G

George

Distinguished, clear

L

Lewis

Friendly, articulate

Japanese

H

Haruto

Clear, natural

Y

Yuki

Soft, gentle

Chinese

X

Xiaobei

Clear, modern

Y

Yunjian

Confident, natural

Spanish

C

Carlos

Warm, authoritative

M

Maria

Friendly, expressive

French

P

Pierre

Smooth, sophisticated

A

Amelie

Bright, engaging

Hindi

A

Arjun

Clear, professional

P

Priya

Warm, natural

Italian

L

Luca

Expressive, melodic

G

Giulia

Elegant, warm

Portuguese (BR)

P

Pedro

Friendly, clear

A

Ana

Warm, inviting

Code examples

OpenAI-compatible. Use your existing SDK — just change the base URL.

cURL
curl -X POST https://api.tryspeakeasy.io/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello, welcome to SpeakEasy!",
    "voice": "alloy"
  }' \
  --output speech.mp3
Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.tryspeakeasy.io/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="Hello, welcome to SpeakEasy!"
)
response.stream_to_file("speech.mp3")
JavaScript
const res = await fetch('https://api.tryspeakeasy.io/v1/audio/speech', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${'{'}apiKey{'}'}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'tts-1',
    input: 'Hello, welcome to SpeakEasy!',
    voice: 'alloy',
  }),
});
const audioBlob = await res.blob();

Built for developers

Drop-in Compatible

Works with OpenAI and ElevenLabs SDKs. Switch providers by changing one URL.

Real-time Streaming

Stream audio chunks as they're generated for instant playback in voice apps and chatbots.

Word Timestamps

Get precise timing for each word. Perfect for syncing speech with text animations.

Multiple Voices

35+ voices across 9 languages with different personalities. Choose the perfect tone for your app.

Multiple Formats

Output in MP3, Opus, AAC, FLAC, or WAV. Optimize for quality or file size.

90% Cheaper

Save up to 90% compared to ElevenLabs with comparable voice quality.

Text-to-Speech Pricing

~3.3 million characters included with your $10/month plan.

Additional usage at $0.25 per additional hour (~67K characters per hour).

View full pricing →

Learn more

SpeakEasy vs OpenAITTS API GuideAPI Documentation

Frequently asked questions

What voices are available?
We offer 35+ voices across 9 languages, including English (US and UK), Japanese, Chinese, Spanish, French, Hindi, Italian, and Portuguese. All voices are compatible with OpenAI's voice names.
What output formats are supported?
We support MP3, Opus, AAC, FLAC, and WAV output formats. MP3 is the default.
Is streaming supported?
Yes! Enable streaming to receive audio chunks in real-time as they're generated. Perfect for real-time voice applications.
How many characters can I convert per request?
Each request supports up to 4,096 characters. For longer content, split it into multiple requests.
Do you provide word-level timestamps?
Yes. Request word-level timestamps to sync generated speech with text for subtitle generation or karaoke-style highlighting.
How does this compare to OpenAI and ElevenLabs?
Our API is compatible with both OpenAI and ElevenLabs formats, so switching is a one-line change. We offer up to 90% savings compared to ElevenLabs with comparable quality.

$1. 50 hours. Both STT and TTS.

Your current speech API provider is charging you too much. Switch in one line of code.

Start for $1 →Read the Docs
SPEAKY