--- title: Voice Cloning API — Clone Any Voice via REST | ModelsLab description: Voice cloning API: clone a voice from a 4-second sample and speak any text in 48 languages with one POST to /api/v6/voice/text_to_audio. Plans from $21/month. url: https://modelslab.com/voice-cloning canonical: https://modelslab.com/voice-cloning type: website component: Seo/VoiceCloning generated_at: 2026-10-08T22:09:29.551621Z --- AudioGen Voice Cloning API — Clone Any Voice via REST --- Clone any voice from a 4-second sample and speak any text in 48 languages with one POST request. Accents and cadence carry over. Plans from $21/month. [Start Voice Cloning](https://modelslab.com/models/modelslab/voice-cloning) [Book a call](https://calendly.com/support-lael/30min?month=2024-11) Choosing a provider? See the [voice cloning API comparison](https://modelslab.com/voice-cloning-api-developer-guide) of sample length, API access and price per minute for ElevenLabs, Cartesia, Fish Audio and ModelsLab. Voice Cloning API quick start --- Clone a voice from a 4-second sample and synthesize speech with one POST request to /api/v6/voice/text\_to\_audio. Returns a hosted MP3/WAV URL. ### Python — synthesize speech from a cloned voice Python ``` 1import requests 2 3response = requests.post( 4 "https://modelslab.com/api/v6/voice/text_to_audio", 5 json={ 6 "key": "YOUR_API_KEY", 7 "prompt": "Hello, this is a cloned voice speaking naturally.", 8 "voice_id": "your-cloned-voice-id", 9 "language": "english", 10 "emotion": "neutral", 11 "speed": 1.0 12 } 13) 14 15print(response.json()["output"][0]) ``` ### JavaScript — voice cloning + multilingual TTS JavaScript ``` 1const response = await fetch('https://modelslab.com/api/v6/voice/text_to_audio', { 2 method: 'POST', 3 headers: { 'Content-Type': 'application/json' }, 4 body: JSON.stringify({ 5 key: 'YOUR_API_KEY', 6 prompt: 'Bonjour, voici une voix clonée parlant naturellement.', 7 voice_id: 'your-cloned-voice-id', 8 language: 'french', 9 emotion: 'happy', 10 speed: 1.0, 11 }), 12}); 13 14const data = await response.json(); 15console.log(data.output[0]); ``` ### cURL — quick test from 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_API_KEY", 5 "prompt": "Welcome to ModelsLab voice cloning API.", 6 "voice_id": "your-cloned-voice-id", 7 "language": "english", 8 "emotion": "neutral", 9 "speed": 1.0 10 }' ``` Trusted by ![Google logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/669b27bc-f881-4e16-569d-4ce02f1bc000/768) ![Salesforce logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/8f7d9952-1dee-4108-f1e5-96ff77108e00/768) ![Amazon logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/b4d3bc1b-8c2b-4d98-7c87-ed162ccbf400/768) ![IBM logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/41bf250b-c933-4d8a-6355-07cf4a2fda00/768) ![Adobe logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/9eb124dd-95c4-4889-c838-faa0f6317000/768) ![Sony logo](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/2d67a30b-a490-4b96-ce1d-28d8371da300/768) 500M+ API Requests Processed 400K+ Registered Users 5K+ Discord Community Members 300+ Available AI APIs 500 GPUs in Our Own Datacenter ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/09738200-f1fc-442c-9852-7d6a9cd56d34.png&quality=25) ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/851c5561-3239-4915-a66b-46d58d6c377c.png&quality=25) ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/70d56252-0444-431d-82b9-ad15c260263e.png&quality=25) ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/7b9995d6-68e1-48ba-bc0c-8e3a8f824faf.png&quality=25) ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/878fc33a-be9d-4fef-a8a5-f2f9931cd1d3.jpg&quality=25) ![Example of AI outpainting result](https://images.modelslab.sh/?image=https://assets.modelslab.ai/generations/6ecdc9a2-bbde-461d-b774-933f35410ea0.png&quality=25) Clone a voice from a sample of at least 4 seconds and use it on any text to speech request. [Try It Now](https://modelslab.com/models/modelslab/voice-cloning) Why Choose ModelsLab --- Key advantages that set us apart User-friendly interface Intelligent phonetic transcription Text-to-speech (TTS) developer-first API Prosody modeling Voice cloning from a 4-second sample Deep-learning voice models Paralinguistic features Multilingual voice clones Voice sampling and modulation Linguistic diversity in voice cloning with support for 48 languages Support by email, live chat and Discord Flexible and smooth integrations Large Global Community No Questions Asked 100% Refund Policy Rapidly Clone Voices and Make Them Human --- You can create natural-sounding voices and clone audio using the voice cloning API. Clone Your Voice in Any Language Select multiple deep-learning voice models from our growing library; clone from other samples by uploading your voice (or your clone’s) or share via URL. Clone in 48 languages, including Hindi, English and Spanish. Generate Text-to-Speech Customize voice clones with text-to-speech prompts. Edit and refine your narratives with the text-to-speech (TTS) AI voice cloning API. Transfer Styles and Enjoy Voice Feature Extraction Extract unique nuances, traits, accents, and emotions from samples. Transfer or infuse vocal attributes into cloned voices for deeper voice personalization. Clone From a Short Sample Upload a clean speech sample of at least 4 seconds, then use the cloned voice on any text to speech request in 48 languages. Full Data Security Complete data security safeguards your cloned voices against unauthorized access. End-to-end audio data encryption provides peace of mind. Only authorized users can access the voice cloning API. ![Clone Your Voice in Any Language](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/8741a716-a81d-419a-c14f-88155af00c00/768) How to Generate Voice Clones Step-by-Step? --- Creating cloned voices using the ModelsLab Voice Cloner is simple and easy. Just follow these four steps. STEP 01 STEP 01 ### Upload your Samples Record and upload audio files of your voice and the person's voice that you want to clone. STEP 02 STEP 02 ### Analyze and Synthesize Our deep learning algorithms will analyze your uploaded voice data and capture its unique traits. STEP 03 STEP 03 ### Edit and Refine You can edit and refine your cloned voices, change them to multiple languages, and adjust vocal attributes such as reverb, pitch, volume, playback speed, and more. STEP 04 STEP 04 ### Generate and Export Download your generated voice clone in any audio file format. Render and export as MP3, WAV, OGG, and others. [Generate Voice Clones ](https://modelslab.com/models/modelslab/voice-cloning) Explore Voice Cloning Features --- ### Clone Your Voice in Any Language Select multiple deep-learning voice models from our growing library; clone from other samples by uploading your voice (or your clone’s) or share via URL. Clone in 48 languages, including Hindi, English and Spanish. ### Generate Text-to-Speech Customize voice clones with text-to-speech prompts. Edit and refine your narratives with the text-to-speech (TTS) AI voice cloning API. ### Transfer Styles and Enjoy Voice Feature Extraction Extract unique nuances, traits, accents, and emotions from samples. Transfer or infuse vocal attributes into cloned voices for deeper voice personalization. ### Clone From a Short Sample Upload a clean speech sample of at least 4 seconds, then use the cloned voice on any text to speech request in 48 languages. ### Full Data Security Complete data security safeguards your cloned voices against unauthorized access. End-to-end audio data encryption provides peace of mind. Only authorized users can access the voice cloning API. [Start Voice Cloning](https://modelslab.com/models/modelslab/voice-cloning) Our Popular Use Cases Here is where you can use our AI Voice Cloning API. PodcastsAds, HR, and e-learningGamingSocial MediaVirtual AssistantsVoice Preservation and Restoration Clone voices for your audio podcasts and create unique character voices. ![Podcasts](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/0fbacb1a-6e34-4254-0a9d-5e75178cf200/768) ### Voice cloning by language Language pages with cloning examples for each language. [ English](https://modelslab.com/voice-cloning/english) [ Hindi](https://modelslab.com/voice-cloning/hindi) [ Spanish](https://modelslab.com/voice-cloning/spanish) [ French](https://modelslab.com/voice-cloning/french) [ German](https://modelslab.com/voice-cloning/german) [ Italian](https://modelslab.com/voice-cloning/italian) [ Portuguese](https://modelslab.com/voice-cloning/portuguese) [ Brazilian Portuguese](https://modelslab.com/voice-cloning/brazilian-portuguese) [ Polish](https://modelslab.com/voice-cloning/polish) [ Turkish](https://modelslab.com/voice-cloning/turkish) [ Russian](https://modelslab.com/voice-cloning/russian) [ Dutch](https://modelslab.com/voice-cloning/dutch) [ Czech](https://modelslab.com/voice-cloning/czech) [ Arabic](https://modelslab.com/voice-cloning/arabic) [ Chinese](https://modelslab.com/voice-cloning/chinese) [ Japanese](https://modelslab.com/voice-cloning/japanese) [ Hungarian](https://modelslab.com/voice-cloning/hungarian) [ Korean](https://modelslab.com/voice-cloning/korean) [ Ukrainian](https://modelslab.com/voice-cloning/ukrainian) [ Romanian](https://modelslab.com/voice-cloning/romanian) [ Serbian](https://modelslab.com/voice-cloning/serbian) [ Swedish](https://modelslab.com/voice-cloning/swedish) [ Thai](https://modelslab.com/voice-cloning/thai) [ Welsh](https://modelslab.com/voice-cloning/welsh) [ Afrikaans](https://modelslab.com/voice-cloning/afrikaans) [ Belarusian](https://modelslab.com/voice-cloning/belarusian) [ Bulgarian](https://modelslab.com/voice-cloning/bulgarian) [ Danish](https://modelslab.com/voice-cloning/danish) [ Finnish](https://modelslab.com/voice-cloning/finnish) [ Greek](https://modelslab.com/voice-cloning/greek) [ Hebrew](https://modelslab.com/voice-cloning/hebrew) [ Indonesian](https://modelslab.com/voice-cloning/indonesian) [ Persian](https://modelslab.com/voice-cloning/persian) [ Nepali](https://modelslab.com/voice-cloning/nepali) [ Vietnamese](https://modelslab.com/voice-cloning/vietnamese) [ Urdu](https://modelslab.com/voice-cloning/urdu) [ Telugu](https://modelslab.com/voice-cloning/telugu) [ Tamil](https://modelslab.com/voice-cloning/tamil) [ Kannada](https://modelslab.com/voice-cloning/kannada) [ Malayalam](https://modelslab.com/voice-cloning/malayalam) [ Punjabi](https://modelslab.com/voice-cloning/punjabi) [ Gujarati](https://modelslab.com/voice-cloning/gujarati) [ Marathi](https://modelslab.com/voice-cloning/marathi) [ Bangla](https://modelslab.com/voice-cloning/bangla) Your Data is Secure: GDPR Compliant AI Services --- ![ModelsLab GDPR Compliance Certification Badge](https://imagedelivery.net/PP4qZJxMlvGLHJQBm3ErNg/28133112-07fe-4c1c-44eb-36948d51ae00/768) Pricing That's Perfect --- Choose plan as per your needs, cancel anytime. 100% refund policy on monthly & yearly plans — cancel anytime MonthlyYearly 2 Months Free [Contact Sales](https://calendly.com/support-lael/30min?month=2024-11) Best Value ### Open Source Unlimited Mission-Critical $149 /month Get API Key100% 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 Get API Key100% 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 Get API Key100% 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 TestimonialsTrusted by Enterprise Teams Worldwide --- Enterprise Success Stories Previous slideNext slide “ ModelsLab's Voice Cloning API has revolutionized how we approach character development in our games. It's like having a studio full of voice actors at our fingertips! ![Alex Rivera](https://assets.modelslab.ai/testimonials/01JPWP92FN0B22SS21SVTR85X0.webp) #### Alex Rivera Game Developer at TVC “ The ease of creating lifelike voiceovers for our e-learning courses has dramatically increased engagement. A real breakthrough for educational content! ![Priya Singh](https://assets.modelslab.ai/testimonials/01JPWPPF58W1TGMEJJZPZTW5AG.webp) #### Priya Singh Instructional Designer at TVC1 “ The LLM Chat API has dramatically helped me in how I approach chat integration. It's like giving an AI voice to my application, making it truly engaging. Thanks, ModelsLab! ![John H.](https://assets.modelslab.ai/testimonials/01JPWSBS6871RQ0NQ769C9C9P9.webp) #### John H. Developer Enthusiast at Mr “ Voice Cloning from ModelsLab gave our marketing campaigns a unique edge with custom, realistic voiceovers. It's incredibly easy to use and effective. ![Michael Chen](https://assets.modelslab.ai/testimonials/01JPWS3GYGTTX7H4K05M5DCR0E.webp) #### Michael Chen Digital Marketing Manager at TVC2 Related Speech APIs --- - [Speech to Text API](/speech-to-text)Transcription with word-level timestamps. - [Whisper API](/whisper-api)Whisper large-v3 on our own GPUs. - [Text to Speech API](/text-to-speech)48 languages, billed per second of audio. - [Cheapest text to speech API](/cheapest-text-to-speech-api)TTS cost per minute of audio, compared. - [Cheapest AI API](/cheapest-ai-api)Image, video and speech prices side by side. - [Unlimited AI API](/unlimited)Every self-hosted open-source model for $149/mo. Get Expert Support in Seconds We're Here to Help. --- Want to know more? You can email us anytime at Chat with support[View Docs](https://docs.modelslab.com) A clean speech sample of at least 4 seconds. A short, noise-free clip works better than a long recording with music or crosstalk. POST https://modelslab.com/api/v6/voice/text_to_audio with `init_audio` set to the URL of the reference sample, `prompt` set to the text to speak and `language` set to the language of that text. The response carries a hosted audio URL, or an id to fetch when the request is queued. No. Voice cloning is included on every plan at the same rate as plain text to speech: $0.001 per second of generated audio. There is no separate cloning tier; extra saved-voice uploads cost $1 per 10 from the wallet. Plans start at $21/month. The voice API covers 48 languages, including Hindi, Bangla, Urdu, Tamil, Telugu, Arabic, Spanish and English. The same endpoint, plan and cloned voice work across all of them. ModelsLab is a paid service. Plans start at $21/month, and Open Source Unlimited, with no limit on self-hosted open-weight models, is $149/month. Creating an account is free, but generating audio requires an active plan. Yes, for voices you have the rights to clone. You own the audio the API generates. Cloning a real person requires their consent, and ModelsLab's terms prohibit impersonation. 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](https://modelslab.com/imagen) [Video Fusion ### AI Video Generation & Tools Create, edit, and enhance videos with AI-powered generation and transformation tools. Explore Video Fusion](https://modelslab.com/video-generation) [Chat ### Engage Seamlessly with LLM Access powerful language models for chatbots, content generation, and AI assistants. Explore Chat](https://modelslab.com/chatbot-api) [3D Verse ### Create Stunning 3D Models Transform images and text into 3D models with advanced AI-powered generation. Explore 3D Verse](https://modelslab.com/text-to-3d) Plugins Explore Plugins for Pro --- Our plugins are designed to work with the most popular content creation software. [Explore Plugins](https://modelslab.com/pro#plugins) [Learn More](https://modelslab.com/pro) API Build Apps with ModelsLab ML API --- Use our API to build apps, generate AI art, create videos, and produce audio with ease. [API Documentation](https://docs.modelslab.com) [Playground](https://modelslab.com/models) ## Frequently Asked Questions ### How much reference audio does the voice cloning API need? A clean speech sample of at least 4 seconds. A short, noise-free clip works better than a long recording with music or crosstalk. ### Which endpoint clones a voice? POST https://modelslab.com/api/v6/voice/text_to_audio with `init_audio` set to the URL of the reference sample, `prompt` set to the text to speak and `language` set to the language of that text. The response carries a hosted audio URL, or an id to fetch when the request is queued. ### Is voice cloning billed separately from text to speech? No. Voice cloning is included on every plan at the same rate as plain text to speech: $0.001 per second of generated audio. There is no separate cloning tier; extra saved-voice uploads cost $1 per 10 from the wallet. Plans start at $21/month. ### How many languages does the voice cloning API support? The voice API covers 48 languages, including Hindi, Bangla, Urdu, Tamil, Telugu, Arabic, Spanish and English. The same endpoint, plan and cloned voice work across all of them. ### Is there a free voice cloning API? ModelsLab is a paid service. Plans start at $21/month, and Open Source Unlimited, with no limit on self-hosted open-weight models, is $149/month. Creating an account is free, but generating audio requires an active plan. ### Can I use cloned voices commercially? Yes, for voices you have the rights to clone. You own the audio the API generates. Cloning a real person requires their consent, and ModelsLab's terms prohibit impersonation. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-10-09*