Frequently asked questions
Who runs this site?
GamerVoice is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or any other major brand. Each site in our network operates independently, providing direct access to the same underlying TTS engine and API infrastructure used by developers worldwide.
Are these real people's voices?
Yes, our eight voice presets are based on licensed recordings from real people, but the generated audio is synthetic speech. The voices originate from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. While the source is human, the generated audio files carry an inaudible watermark to clearly mark them as synthetic speech.
Do you clone voices?
No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design a new one. We provide eight distinct presets, such as Aria, Nova, and Felix, which you can use directly. There is no option to create a unique voice model for your brand.
Is my data used for training?
Input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, strictly for billing purposes. Your creative content remains yours.
Do you have an SLA?
No, we do not offer an SLA or uptime guarantee. We are an independent API without enterprise contracts or certifications like SOC 2 or HIPAA. Requests are processed sequentially, so under load, a request may wait in a queue. We focus on reliable, affordable access rather than guaranteed uptime.
How do I contact support?
Support is available by email only. We do not have a phone number, live chat, or on-call team. You can reach us via the contact page or by emailing us directly. We aim to respond to your inquiries as quickly as possible to help you integrate the API.
Are the voices licensed?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This provides a clear licensing basis for your NPC dialogue and content. We handle the licensing so you can focus on bringing your characters to life with clear, distinct, and high-quality synthetic voices.
Is this an official OpenAI site?
No, GamerVoice is not affiliated with OpenAI. We use a compatible endpoint structure, so the official OpenAI SDKs work by changing the base URL. However, we are an independent provider with our own pricing, voices, and infrastructure. We are not OpenAI, and our services are distinct from their offerings.
Do you offer refunds?
Failed requests are free, with the charge returned in full if synthesis fails. We do not offer general refunds for successful requests. Payments are made via USDT on the TRON network. Your balance does not expire, and you can top up anytime, ensuring you only pay for what you use.
Can I use the API commercially?
Yes, you can use the API commercially for games, NPCs, and content creation. There are no monthly plans, seats, or minimum spend requirements. You pay per character used, with a clear rate of $10 per million characters. This model is designed to be budget-friendly for indie developers and studios alike.
Who We Are
GamerVoice is an independent storefront for a text-to-speech API, not a subsidiary of a larger tech giant. We operate as a dedicated service layer, allowing game developers and content creators to integrate reliable NPC dialogue directly into their projects without unnecessary overhead. Our platform is built specifically for those who need consistent, budget-friendly audio generation for character voices.
Independent Storefront
Unlike major cloud providers, we focus solely on delivering high-quality speech synthesis without bundling it into complex ecosystems. This independence means our pricing and features remain transparent and aligned with the needs of indie developers and small studios. You get direct access to the API without navigating through layers of corporate infrastructure.
- Direct API access with no vendor lock-in
- Transparent pricing tailored for game development
- Independent infrastructure, not part of a larger tech conglomerate
Editorial Team
Our goal is to provide clear, usable audio that enhances storytelling without distracting from the gameplay experience.
- Developers and writers with game industry experience
- Regular testing of voice presets for NPC use cases
Developer Focused
We prioritize simplicity and reliability. Our API follows familiar patterns, making it easy to integrate with existing game engines. We support standard formats and provide clear documentation, so you can focus on building your game rather than debugging audio pipelines. Our tools are designed to be lightweight and efficient.
- Simple integration with standard game engines
- Clear documentation and examples
- Lightweight and efficient API design
Voice Licensing
GamerVoice’s voice models are built on licensed recordings from LibriTTS-R, a high-quality dataset derived from LibriVox. This foundation ensures that every character voice you select is based on licensed recordings.
All underlying audio data is licensed under CC BY 4.0, allowing flexible use in commercial game projects. We handle the attribution logic so you can focus on gameplay, not legal paperwork.
LibriTTS-R Source
The core engine uses audio from LibriTTS-R, a curated subset of LibriVox recordings. This dataset provides clear speech samples, ensuring consistent voice quality across all 8 presets and 23 languages.
- Based on real human recordings
- High-fidelity source material
- Optimized for neural synthesis
CC BY 4.0 License
The underlying voice data is licensed under Creative Commons Attribution 4.0. This means you can integrate these voices into your games, streams, or videos without worrying about complex royalty structures, provided you respect the attribution terms.
Public Domain Readings
Many source recordings come from public domain audiobooks. These readings are available for use, making them suitable for NPC dialogue.
Data Privacy
We prioritize your data integrity by ensuring that input text is used strictly for the purpose of generating audio. Your scripts are not repurposed or used to train our underlying models, keeping your creative assets exclusively yours.
Generated audio files are delivered directly in the response and are not stored on our servers after delivery. This ephemeral handling ensures that your NPC dialogue remains transient unless you choose to save it yourself.
Billing Metadata
To ensure accurate invoicing, we retain minimal request metadata including the timestamp, character count, and status. This data is used solely for billing purposes and is not linked to the content of your generated speech.
- Input text is not used for training
- Audio is not stored post-delivery
- Metadata retained only for billing
Support and Contact
We keep things simple so you can focus on building your game. All communication happens through a single, reliable channel. You won’t need to navigate complex support tiers or wait on hold during a voice call.
Our team responds to emails directly. We aim to be helpful without the overhead of live agents. This keeps our costs low and your API prices fair.
Email Only
Send your questions or issues to our support email. We handle every message personally. You’ll get a clear, specific answer without automated routing delays.
No Live Chat
We do not offer real-time chat widgets on this site. This avoids the noise of simultaneous conversations and ensures your issue gets full attention when we reply.
No Phone Support
There is no phone number to call. If you prefer asynchronous communication, email is the best way to reach us. We provide detailed context in writing, which is often more useful for debugging API issues.

Technical Limits
GamerVoice is an independent API storefront designed for game developers and content creators. We prioritize clear pricing and straightforward technical access over enterprise fluff. Our model is built for scale and simplicity, allowing you to integrate high-quality NPC dialogue without complex negotiations or hidden fees.
No SLA
We do not offer a Service Level Agreement. Our infrastructure is optimized for cost-effective, reliable generation rather than guaranteed latency or priority queuing. This keeps our pricing transparent and accessible for indie studios and solo developers.
No Uptime Guarantee
There is no contractual uptime percentage. While we strive for consistent operation, network fluctuations or maintenance windows may occasionally affect availability. We recommend implementing retry logic in your game engine to handle brief interruptions gracefully.
No Enterprise Contract
We do not provide custom enterprise contracts, dedicated support lines, or volume discounts. All users operate under the same standard terms with a single API key. This ensures a uniform experience and prevents administrative overhead for smaller teams.
Product Facts
GamerVoice provides a straightforward cloud API for game developers needing reliable NPC dialogue. The service operates as an independent storefront, offering a clean integration path for content creators who require consistent voice synthesis without complex infrastructure management.
Our architecture prioritizes simplicity and predictability. By adhering to standard request shapes, we ensure that your existing development workflows remain uninterrupted while delivering high-quality audio outputs tailored for interactive media environments.
API Endpoint
Send text to POST https://api.lawpan.info/v1/audio/speech with a JSON body. The request shape matches the OpenAI speech endpoint, allowing you to use the official OpenAI SDKs by simply changing the base_url to https://api.lawpan.info/v1.
Other endpoints include GET /v1/voices for listing available voices and GET /v1/models for model details. Authentication uses Authorization: Bearer tts-... with one active key per account.
- Endpoint: POST https://api.lawpan.info/v1/audio/speech
- Auth: Bearer tts-... key
- SDK compatible: Yes (via base_url change)
Rate Limits
The API allows 60 requests per minute per key. New accounts start with a limit of 10 requests per minute until the first top-up is processed. Requests are processed sequentially, so high load may introduce queue delays.
- Standard limit: 60 requests/minute
- Initial limit: 10 requests/minute
- Processing: Sequential
Supported Formats
You can choose from mp3, wav, opus, flac, and pcm for the response_format field. The model parameter accepts either "tts-1" or "tts-1-hd", which use the same engine and price. Text input is limited to 4096 characters per request.
- Formats: mp3, wav, opus, flac, pcm
- Models: tts-1, tts-1-hd
- Max input: 4096 characters
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Use her for characters who serve as guides or historians in your game.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Creative Commons Attribution 4.0
- LibriVox public-domain audiobooks
- curl documentation
- LibriTTS-R corpus (OpenSLR 141)
- TRON developer hub: TRC-20
- FFmpeg documentation
- IETF RFC 7845: Ogg Opus
- openai-node on GitHub
- LibriTTS-R paper (arXiv 2305.18802)
- OpenAI API reference: create speech
- MDN: Web Speech API
