Frequently asked questions
Who runs FomoVoice?
FomoVoice is an independent storefront for a cloud text-to-speech API. We operate as a standalone service designed specifically for freelancers and ad agencies. Our team manages the infrastructure and billing directly, ensuring a transparent and straightforward experience for users producing radio spots and voiceovers without intermediary agencies.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base URL. However, we are a separate entity with our own pricing, voices, and infrastructure, completely independent of OpenAI.
Where are the voices from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These recordings form the foundation of our synthetic speech engine, providing natural-sounding voices like Aria, Nova, and Felix that are optimized for advertising workflows and radio spots.
Do you sell data?
No, we do not sell your data. Your input text is used only to produce the audio and is not used for training our models. Generated audio is returned in the response and not stored. We keep request metadata like time and characters solely for billing purposes.
How do I contact support?
Support is available by email only. We do not offer a phone number, live chat, or social media support channels. You can reach us through the contact page on our website. We aim to respond to your inquiries promptly to help you resolve any issues with your API usage.
Do you have a physical office?
We do not list a physical office address. As a cloud-based API service, our operations are managed remotely. We focus on delivering reliable text-to-speech generation via our API endpoint rather than maintaining a traditional brick-and-mortar location. All interactions, including support and billing, are handled digitally.
Are you a startup or established company?
We are an independent service provider operating a cloud text-to-speech API. We do not claim to be a startup or an established corporation. Our focus is on providing a transparent, no-nonsense API for freelancers and agencies to generate audio efficiently, with clear pricing and straightforward technical documentation.
Do you offer enterprise plans?
No, we do not offer enterprise plans, monthly subscriptions, or minimum spend requirements. We operate on a pay-as-you-go model with no seats or contracts. You simply top up your balance with USDT and use the API. There are no SLAs or uptime guarantees for any plan type.
Can I request a new voice?
We do not offer custom voice cloning or voice design for customers. You cannot upload your own voice or request a new preset. We provide eight fixed presets based on LibriVox recordings. If you need a specific voice not in our list, you will need to use one of the existing options.
How do you handle disputes?
We handle disputes primarily through email support. Since we do not offer phone support or live chat, all communication regarding billing or service issues is conducted via email. Please provide your account details and a description of the issue so we can investigate and resolve it efficiently.
Do you have a privacy policy?
Yes, we respect your privacy. Input text is used only for synthesis and not for training. Audio is returned and not stored. Request metadata is kept for billing. We do not sell data. For more details on how we handle your information, please refer to the privacy section on our site.
Are you GDPR compliant?
We do not have a GDPR certificate. We do not offer an on-premise install or data-center choice. We keep request metadata for billing and do not store generated audio. We process data transparently but do not make specific legal compliance claims.
Do you store user data?
We keep request metadata, including time, characters, and status, for billing purposes. Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and is not stored on our servers after delivery. We do not retain your audio files long-term.
Can I use the voices in my portfolio?
Yes, you can use the generated audio in your portfolio. Each file carries an inaudible watermark marking it as synthetic speech. Since the voices are based on licensed recordings, you can showcase them as examples of synthetic speech production. We do not claim ownership over your generated audio files.
Who We Are
FomoVoice is built for the realities of ad production. We help freelancers and agencies generate high-quality radio spots and voiceovers without hiring expensive talent. Our API delivers natural-sounding synthetic speech optimized for tight deadlines and specific advertising workflows.
As an independent storefront, we operate separately from the underlying engine providers. This means no brand affiliation, no misleading comparisons, and a direct line to the tool you need. We focus on what matters: delivering audio that fits your script.
Ad Freelancer Focused
We understand the pressure of client revisions and last-minute script changes. Our API allows you to iterate quickly, testing different voices like Aria or Felix until the tone matches the brand exactly. This saves hours of studio booking and actor availability coordination.
- Optimized for radio spots and voiceovers
- Ideal for rapid iteration and A/B testing
- Saves time on actor scheduling
Independent Storefront
We are not a subsidiary of OpenAI, ElevenLabs, or any other major tech brand. We are a dedicated TTS API provider. This independence ensures our pricing, features, and updates are driven by what freelancers actually need, not by corporate roadmap priorities.
- Not affiliated with major TTS brands
- Direct control over API behavior
- Transparent billing and data policies
No Hype, Just Facts
We don’t claim to be the "best" or "fastest." We provide a reliable cloud API with clear limits: 60 requests per minute, $0.01 per 1,000 characters, and a simple REST interface. If you need SSML or voice cloning, we don’t have it. If you need consistent, affordable audio, we do.
- No superlatives or vague claims
- Clear rate limits and pricing
- Honest feature list
Voice Licensing
Our voice models are built on licensed recordings from the LibriTTS-R dataset. We do not use celebrity voices or unlicensed samples, ensuring a clear legal foundation for your commercial projects.
LibriTTS-R Source
The core of our eight voice presets comes from the LibriTTS-R dataset. This provides a diverse range of natural speech patterns optimized for clarity and consistency across different advertising contexts.
CC BY 4.0 License
LibriTTS-R is released under the Creative Commons Attribution 4.0 International License. This allows us to build commercial-grade TTS engines while maintaining transparency about our data sources and usage rights.
LibriVox Recordings
The underlying audio data originates from LibriVox, featuring public-domain audiobook readings. This ensures that the base recordings are free of copyright restrictions, allowing us to focus on engineering rather than licensing fees.
Data Policy
We respect your creative assets. The text you submit for synthesis is used exclusively to generate the audio file for that specific request. Your input is not ingested into our training datasets, ensuring your unique scripts remain yours.
No Training on Input
Your input text is processed solely to produce the audio response. It is not used to train or improve our models, keeping your copy confidential and distinct from our training data.
No Audio Storage
Generated audio files are returned directly in the response and are not stored on our servers after delivery. Once you have the file, it exists only on your end.
Metadata for Billing
We retain request metadata—such as timestamp, character count, and status—strictly for billing and usage verification. This ensures accurate charges and helps us maintain service reliability without storing your creative content.
Technical Infrastructure
FomoVoice operates as a cloud-based text-to-speech API, designed for reliability and ease of integration. By sending text via standard HTTP requests, you receive audio files without managing complex infrastructure or hardware.
The API is fully compatible with OpenAI’s SDKs. You can use existing tools by simply changing the base_url to https://api.playfomo7.com/v1 and using your API key. This ensures a familiar workflow for developers accustomed to modern TTS services.
Cloud API
Our infrastructure is entirely cloud-based, handling synthesis with typical speed of roughly real time on long texts, though short phrases take a few seconds and requests may wait in a queue under load. Text is processed, converted to audio, and returned as a file without requiring local processing power on your end.
OpenAI Compatible
The endpoint structure mirrors OpenAI’s speech API. This means you can use the official OpenAI SDKs with minimal configuration changes, specifically by updating the base URL.
- Supports standard request shapes
- Uses
tts-1andtts-1-hdmodel identifiers - Compatible with existing OpenAI client libraries
Simple REST
We use simple REST endpoints for all interactions. Audio generation, voice listing, and model information are accessible via straightforward HTTP methods, making integration quick for freelancers and agencies alike.

Support and Contact
We keep things simple so you can focus on your campaigns. Our support is straightforward and accessible, designed for freelancers who need clear answers without navigating complex call trees or waiting on hold.
Email Only
All inquiries go to our support email. We prioritize clarity and provide detailed responses to help you integrate the API smoothly into your ad workflows.
No Live Chat
We do not offer live chat. This allows us to maintain thorough, documented responses that you can reference later without losing context during a quick chat window.
No Phone Number
There is no phone number to call. Email remains our single channel for support, ensuring every query is logged and addressed with the same level of care.
Why We Exist
FomoVoice exists because hiring voice talent for small projects is often disproportionate to the budget. We built an independent API that gives freelancers immediate access to professional-grade synthetic speech, removing the friction of casting and scheduling.
We focus on delivering clear, ad-ready audio at a fraction of traditional rates, ensuring that every character counts toward your final budget without hidden fees or complex contracts.
Empowering Freelancers
Freelancers and small agencies often lack the leverage to negotiate bulk voice acting rates. Our API puts the power directly in your hands, allowing you to generate radio spots and voiceovers on demand. You control the casting among eight distinct voice presets, from warm narrators to energetic promo styles, without waiting for availability.
Affordable Audio
At $0.01 per 1,000 characters, you only pay for what you use. There are no monthly subscriptions, no minimum spends, and no seat limits. Failed requests are free, and your balance never expires. This model allows you to experiment with multiple takes or voices without financial risk, keeping your overhead predictable and low.
Simplified Workflow
Integrate TTS directly into your production pipeline using standard REST requests. The API accepts simple text inputs and returns audio files after processing, which typically takes a few seconds for short phrases or roughly real time for long texts, compatible with existing tools. You can adjust speed and language in real-time, ensuring the final output matches your creative vision without needing specialized audio engineering software or extensive post-production time.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
