Unlimited Open Source Models

Get Plan
Skip to main content
Imagen

Cheapest Text to Speech API for Developers

Speech generation and voice cloning from $12/month. Unlimited open-weight speech at $127/month — billed per API call, not per character, so long scripts don't inflate the bill.

Get Started — $12/MonthAPI Documentation

Why ModelsLab Is the Cheapest Text to Speech API

Per-Call Pricing, Not Per-Character

Most text-to-speech APIs bill per character. That model is fine for short UI prompts and punishing for anything long — an audiobook chapter, a training module, a dubbed video — because the bill scales with every word you generate, including the takes you throw away.

ModelsLab bills per API call instead. The Basic plan is $12/month for 600 calls, Standard is $27/month for 3,000 calls, and one call is one generation request regardless of script length. If you regenerate a paragraph five times to get the delivery right, you spend five calls, not five times the character count.

Cheap Does Not Mean a Thin Voice Catalogue

The low tier is not a stripped-down trial. Every plan reaches the same speech stack:

  • Voice cloning from a short reference sample
  • Text-to-speech across 44 languages
  • Voice-to-voice conversion for changing an existing recording
  • Multi-speaker synthesis and per-speaker settings
  • Speech-to-text transcription on the same key
  • 13 open-weight speech endpoints self-hosted on ModelsLab GPUs
  • Optional third-party voices (ElevenLabs, Google, Inworld) per call
  • One REST endpoint and one API key across all of it

What Each Plan Costs

Speech plans are billed per API call. One call is one generation request, whatever the length of the script.

PlanPrice / MonthAPI CallsRate Limit
Basic$126005 req/s
Standard$273,00010 req/s
Unlimited Premium (best value)$127Unlimited open-weight15 req/s

ModelsLab audio plan pricing, verified against the plans table in August 2026. Unlimited covers the 13 open-weight speech endpoints ModelsLab self-hosts, including voice cloning. Third-party voices (ElevenLabs, Google, Inworld, Sonauto) are billed per call from wallet balance on top of any plan.

Generate Speech in One Request

One endpoint for text-to-speech and voice cloning.

Text to speech (Python)

Python
1import requests
2

3response = requests.post(
4    "https://modelslab.com/api/v7/voice/text-to-speech",
5    headers={
6        "Authorization": "Bearer YOUR_MODELSLAB_API_KEY",
7        "Content-Type": "application/json",
8    },
9    json={
10        "model_id": "text-to-speech",
11        "voice_id": "madison",
12        "prompt": "Your order has shipped and arrives on Thursday.",
13    },
14)
15

16# One API call, whatever the script length
17print(response.json())

Change the voice of an existing recording (Python)

Python
1import requests
2

3response = requests.post(
4    "https://modelslab.com/api/v7/voice/speech-to-speech",
5    headers={
6        "Authorization": "Bearer YOUR_MODELSLAB_API_KEY",
7        "Content-Type": "application/json",
8    },
9    json={
10        "model_id": "voice-changer",
11        "voice_id": "madison",
12        "init_audio": "https://example.com/original-recording.wav",
13    },
14)
15

16# Keeps the timing and delivery of the source, swaps the voice
17print(response.json())

Batch a script with JavaScript

JavaScript
1const lines = [
2  'Chapter one. The house on the hill.',
3  'It had been empty for as long as anyone could remember.',
4];
5

6// One call per line — 2 calls against your plan, not 90 characters billed.
7const audio = await Promise.all(
8  lines.map(async (prompt) => {
9    const res = await fetch('https://modelslab.com/api/v7/voice/text-to-speech', {
10      method: 'POST',
11      headers: {
12        'Content-Type': 'application/json',
13        Authorization: 'Bearer YOUR_MODELSLAB_API_KEY',
14      },
15      body: JSON.stringify({
16        model_id: 'text-to-speech',
17        voice_id: 'madison',
18        prompt,
19      }),
20    });
21    return res.json();
22  }),
23);
24

25console.log(`${audio.length} clips generated`);

Ship Speech in 3 Steps

From signup to production audio.

STEP 01
STEP 01

Step 1: Sign Up

Create a ModelsLab account, subscribe to the $12/month Basic audio plan, and copy your API key from the dashboard. Every audio plan reaches the same voices.

STEP 02
STEP 02

Step 2: Generate Speech

POST your text and a voice_id to the text-to-audio endpoint, or pass a reference sample to clone a voice. One request is one API call against your plan, whatever the script length.

STEP 03
STEP 03

Step 3: Move to Unlimited at $127/mo

Past roughly 3,000 calls a month the $127/month unlimited plan costs less than the metered tiers. It covers unlimited generation on the open-weight speech models ModelsLab self-hosts.

Get API Key

Related speech guides

Best Text to Speech API 2026

Full comparison beyond price — voice quality, latency, and language coverage.

Cheapest AI Image API

The same cost breakdown for image generation at $0.0047 per image.

Voice Cloning API

Clone a voice from a short sample and generate speech in 44 languages.

How the Unlimited Plan Works

ModelsLab self-hosts 13 open-weight speech endpoints on its own GPUs, which is what makes flat pricing possible: once the infrastructure is running, the marginal cost of another generation is close to zero. The $127/month plan removes per-call limits on those models.

Third-party voices are the exception and are priced honestly rather than folded into "unlimited". ElevenLabs, Google, Inworld and Sonauto voices are billed per call from wallet balance on top of your plan, because ModelsLab pays those providers per call too.

Which Plan Fits Your Volume

Under 600 generations a month, Basic at $12 is the cheapest way to run speech in production. Between 600 and 3,000, Standard at $27 works out cheaper than topping up. Above roughly 3,000 calls a month, unlimited at $127 is strictly cheaper than either metered tier and removes the need to forecast volume at all.

Voice cloning costs the same as plain text-to-speech — there is no separate cloning tier or per-voice fee. A reference sample needs at least 4 seconds of clean speech; longer samples are trimmed to about 10 seconds.

What You Get at $12/Month

Key advantages that set us apart

Plans from $12/month — the cheapest entry point we sell
Billed per API call, not per character
Unlimited open-weight speech at $127/month
Voice cloning included at no extra cost
44 languages on the same endpoint
Voice-to-voice conversion as well as text-to-speech
Speech-to-text transcription on the same API key
13 open-weight speech endpoints, self-hosted
Third-party voices priced per call, never hidden in a plan
One API key across image, video, speech and LLM

Our Popular Use Cases

What teams build with low-cost speech generation:

Per-call billing is the whole point here. Generate chapter after chapter without a character meter running, and re-record individual paragraphs for the cost of one call each.

Audiobooks and Long-Form Narration

Cheapest Text to Speech API FAQ

ModelsLab starts at $12/month for 600 API calls, which is the cheapest plan we sell in any category. Standard is $27/month for 3,000 calls, and unlimited generation on our self-hosted open-weight speech models is $127/month. Billing is per API call rather than per character, so long scripts do not increase the cost of a request.

No. ModelsLab bills per API call. One generation request is one call regardless of how long the text is, which makes long-form narration and repeated takes much cheaper than character-metered pricing.

Voice cloning is included on every audio plan at the same cost as plain text-to-speech. There is no per-voice fee and no separate cloning tier. Your reference sample needs at least 4 seconds of clean speech.

It covers unlimited generation on the 13 open-weight speech endpoints ModelsLab self-hosts, including voice cloning, text-to-speech and voice conversion. Third-party voices such as ElevenLabs, Google, Inworld and Sonauto are billed per call from wallet balance on top of the plan, because those providers charge us per call.

ModelsLab is a paid service. Audio plans start at $12/month for 600 API calls. Creating an account is free, but generating speech requires an active plan.

44, including Hindi, Bangla, Urdu, Tamil, Telugu, Malayalam, Punjabi, Marathi, Gujarati, Kannada, Persian, Arabic and Spanish, alongside English. The same endpoint and the same plan cover all of them.

Yes. Start on Basic at $12/month and move up when your volume justifies it. Above roughly 3,000 calls a month the $127/month unlimited plan is cheaper than the metered tiers. You can move back down if volume drops — there is no lock-in.

Your Data is Secure: GDPR Compliant AI Services

ModelsLab GDPR Compliance Certification Badge

GDPR Compliant

Pricing That's Perfect

Choose plan as per your needs, cancel anytime.

Coming Soon

We are making some changes to our pricing, please check back later.

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

ModelsLab audio plans start at $12/month for 600 API calls, which is the cheapest plan we sell in any category. Standard is $27/month for 3,000 calls, and unlimited generation on the open-weight speech models ModelsLab self-hosts is $127/month. Billing is per API call rather than per character, so a long script does not make a request cost more.

No. ModelsLab bills per API call. One generation request is one call regardless of the length of the text, which makes long-form narration and repeated takes considerably cheaper than character-metered pricing.

Voice cloning is included on every audio plan at the same cost as plain text-to-speech. There is no per-voice fee and no separate cloning tier. A reference sample needs at least 4 seconds of clean speech, and longer samples are trimmed to about 10 seconds.

Unlimited generation on the 13 open-weight speech endpoints ModelsLab self-hosts, including voice cloning, text-to-speech and voice conversion. Third-party voices such as ElevenLabs, Google, Inworld and Sonauto are billed per call from wallet balance on top of the plan, because those providers charge us per call.

ModelsLab is a paid service. Audio plans start at $12/month for 600 API calls. Creating an account is free, but generating speech requires an active plan.

The voice API covers 44 languages, including Hindi, Bangla, Urdu, Tamil, Telugu, Malayalam, Punjabi, Marathi, Gujarati, Kannada, Persian, Arabic and Spanish alongside English. The same endpoint and plan cover all of them.

Yes. Start on Basic at $12/month and move up as volume grows. Above roughly 3,000 calls a month the $127/month unlimited plan costs less than the metered tiers, and you can move back down if volume falls. There is no lock-in.

Explore Our Other Solutions

Unlock your creative potential and scale your business with ModelsLab's comprehensive suite of AI-powered solutions.

Imagen

AI Image Generation & Tools

Generate, edit, upscale, and transform images with state-of-the-art AI models.

Explore Imagen
Video Fusion

AI Video Generation & Tools

Create, edit, and enhance videos with AI-powered generation and transformation tools.

Explore Video Fusion
Chat

Engage Seamlessly with LLM

Access powerful language models for chatbots, content generation, and AI assistants.

Explore Chat
3D Verse

Create Stunning 3D Models

Transform images and text into 3D models with advanced AI-powered generation.

Explore 3D Verse
Plugins

Explore Plugins for Pro

Our plugins are designed to work with the most popular content creation software.

Explore PluginsLearn More
API

Build Apps with
ML
API

Use our API to build apps, generate AI art, create videos, and produce audio with ease.

API DocumentationPlayground