Unlimited Open Source Models

Get Plan
Skip to main content
AudioGen

Text to Speech API

Turn text into speech with one POST to /api/v6/voice/text_to_audio. 48 languages and voice cloning on the same endpoint, $0.001 per second of audio.

  • $0.001 per second of audio
  • 48 languages
  • Unlimited on the $149 plan

Hear Our AI Voices in Action

Experience the quality of our AI text to speech generator. Listen to a variety of voice samples below.

Explore Our Voice Library

ASMR Girl Voice (US English)

0:000:00

Authoritative News Anchor (Female)

0:000:00

Professional Male Voice (Spanish)

0:000:00

Calm Narration (Male)

0:000:00

Energetic Ad Read (Female)

0:000:00

Hindi News anchor(Male)

0:000:00

Japanese Anime (Female)

0:000:00

Multilingual Demo (Spanish Female)

0:000:00

Standard Female Voice (US English)

0:000:00

Standard Male Voice (UK English)

0:000:00

More voice styles, languages, and customization options available in our full text to speech playground.

TTS API pricing: $0.001 per second

You pay for the audio you get back: $0.001 per second of generated speech, with a $0.0047 minimum per request. The number of characters you send does not change the price.

The $21 Basic allowance covers about 5.8 hours of speech a month. On the $149 Open Source Unlimited plan, speech from our self-hosted models has no per-second charge.

PlanPrice per monthSelf-hosted speechParallel generations
Basic$21$0.001 per second, about 5.8 hours5
Standard$47$0.001 per second10
Open Source Unlimited$149No per-second charge15

48 languages

Pass one of these values in the required language field. Every plan covers all of them.

  • Arabic
  • Assamese
  • Bengali
  • Brazilian Portuguese
  • Chinese
  • Czech
  • Danish
  • Dutch
  • English
  • Finnish
  • French
  • German
  • Greek
  • Gujarati
  • Hebrew
  • Hindi
  • Hungarian
  • Indonesian
  • Italian
  • Japanese
  • Kannada
  • Korean
  • Maithili
  • Malay
  • Malayalam
  • Marathi
  • Min Nan Chinese
  • Nepali
  • Odia
  • Persian
  • Polish
  • Punjabi
  • Russian
  • Sindhi
  • Sinhala
  • Slovak
  • Spanish
  • Swahili
  • Swedish
  • Tamil
  • Telugu
  • Thai
  • Turkish
  • Ukrainian
  • Urdu
  • Vietnamese
  • Welsh
  • Yue Chinese

Voice cloning from a short sample

Pass a voice sample of at least 4 seconds as init_audio and the same request speaks your text in that voice. Cloned speech costs the same $0.001 per second.

To reuse a voice, save it with voice_upload and pass its voice_id. Extra saved-voice uploads cost $1 per 10 from your wallet. More detail is on the Voice Cloning API page.

Text to speech API quick start

POST /api/v6/voice/text_to_audio with prompt, language and voice_id. Python, JavaScript and cURL.

Python: speak text with a saved voice

Python
1import requests
2
3response = requests.post(
4 "https://modelslab.com/api/v6/voice/text_to_audio",
5 json={
6 "key": "YOUR_MODELSLAB_API_KEY",
7 "prompt": "Your order has shipped and arrives on Thursday.",
8 "language": "english",
9 "voice_id": "YOUR_VOICE_ID",
10 },
11)
12
13print(response.json())

JavaScript: clone a voice from a sample

JavaScript
1const response = await fetch(
2 'https://modelslab.com/api/v6/voice/text_to_audio',
3 {
4 method: 'POST',
5 headers: { 'Content-Type': 'application/json' },
6 body: JSON.stringify({
7 key: 'YOUR_MODELSLAB_API_KEY',
8 prompt: 'Bonjour, et bienvenue.',
9 language: 'french',
10 // A sample of at least 4 seconds of the voice to clone.
11 init_audio: 'https://example.com/voice-sample.wav',
12 }),
13 },
14);
15
16console.log(await response.json());

cURL: quick test from the terminal

bash
1curl -X POST 'https://modelslab.com/api/v6/voice/text_to_audio' \
2 -H 'Content-Type: application/json' \
3 -d '{
4 "key": "YOUR_MODELSLAB_API_KEY",
5 "prompt": "Welcome to the text to speech API.",
6 "language": "english",
7 "voice_id": "YOUR_VOICE_ID"
8 }'

Partner voices

ElevenLabs and Inworld voices are available on the same API key. They are partner models: on Basic and Standard they use the plan allowance first, then your wallet, and the $149 unlimited plan does not cover them.

Text to speech by language

Language pages with voice samples and request examples for each language.

Pricing That's Perfect

Choose plan as per your needs, cancel anytime.

100% refund policy on monthly & yearly plans — cancel anytime
Contact Sales
Best Value

Open Source Unlimited

Mission-Critical

$149/month

🛡️ 100% refund policy · cancel anytime

Unlimited Open Source Models
100% refund policy
24x7 Support
15 parallel generations ⚡
Access to all APIs
Unlimited generations on all open-source models
For mission critical workloads
Add Team Members
Priority GPU Clusters
Most Popular

Standard

Production

$47/month

🛡️ 100% refund policy · cancel anytime

Moderate Traffic
100% refund policy
Priority Developer Support
10 concurrent API requests ⚡
For Production workloads
API access to all models
Prototype

Basic

Prototype

$21/month

🛡️ 100% refund policy · cancel anytime

Moderate Traffic
100% refund policy
Developer Support via Discord/Email
5 concurrent API requests ⚡
API access to all models
Shared GPU

Start generating speech

Plans start at $21 a month. Speech is $0.001 per second, or unlimited on the $149 plan.

Get API key

Get Expert Support in Seconds

We're Here to Help.

Want to know more? You can email us anytime at support@modelslab.com

View Docs

POST https://modelslab.com/api/v6/voice/text_to_audio with `prompt` set to the text, `language` set to its language and `voice_id` set to a voice from /api/v6/voice/voice_list. Add `init_audio` to speak in a cloned voice instead. The response carries a hosted MP3 or WAV URL.

No. Self-hosted speech is billed by the length of the audio it produces: $0.001 per second, with a $0.0047 minimum per request, paid from the usage included in your plan. The number of characters you send does not change the price, and the $149/month Open Source Unlimited plan has no limit on the self-hosted speech models.

Plans start at $21/month (Basic) and $47/month (Standard). Self-hosted speech is paid from that included usage at $0.001 per second of generated audio, so $21 covers about 5.8 hours. Open Source Unlimited ($149/month) has no limit on the open-weight speech models ModelsLab self-hosts. Partner voices such as ElevenLabs and Inworld use the plan's included usage first on Basic and Standard, then your wallet; on the $149 plan they bill from your wallet.

The text to speech API covers 48 languages; set `language` on each request. Voices come from the voice list endpoint and from your own cloned voices, and both work on the same text to speech request.

ModelsLab is a paid service. Plans start at $21/month. Creating an account is free, but generating speech requires an active plan.

The API returns a complete file per request. For interactive products, generate short segments and play them as they return; each segment is one request, billed by the seconds of audio it returns.