VoxQuest: Synthetic Voices for Game Developers

By VoxQuest editorial team · Updated 2026-11-19

VoxQuest is an independent storefront built for freelance game developers who need affordable, non-copyrighted NPC dialogue without the legal headaches of traditional voice acting. We simplify synthetic speech integration by offering clear presets, straightforward pricing, and transparent data usage.

You will find details on our LibriTTS-R licensing, data policies, and support structure. We also cover pricing, USDT top-ups, and API integration specifics so you can estimate costs and integrate quickly. Whether you are building a solo RPG or a multiplayer prototype, this guide ensures you know exactly what to expect from our TTS engine.

VoxQuest: Synthetic Voices for Game Developers

Frequently asked questions

Who runs this site?

This is an independent storefront for the VoxQuest text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or any other major brand. Our team focuses solely on providing a reliable, affordable TTS solution for freelance game developers, handling the infrastructure and billing directly without enterprise intermediaries.

Are the voices copyrighted?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. While the source material is open, every generated audio file carries an inaudible watermark marking it as synthetic speech, ensuring clear attribution and usage rights for your game projects.

Do you use my data for training?

No. Your input text is used exclusively to produce the audio file for your request. We do not use your text or generated audio for training our models. Only request metadata, such as time, character count, and status, is retained for billing purposes.

How do I contact support?

Support is available via email only. We do not offer live chat or phone support. You can reach our team through the contact page or by emailing us directly regarding your account, billing, or technical questions.

Do you have a phone number?

No, we do not have a phone number. All support communication happens via email. This keeps our operations lean and affordable for freelance developers. You can find our email address on the contact page to get help with your API key or billing issues.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint structure, so you can use OpenAI SDKs by simply changing the base URL. However, we are an independent service with our own pricing, voices, and infrastructure, completely separate from OpenAI.

Do you offer SLAs?

No, we do not offer Service Level Agreements or uptime guarantees. Our service is provided as-is without enterprise contracts.

Are you SOC 2 certified?

No, we do not have SOC 2, HIPAA, or GDPR certification. We are an independent storefront focused on affordability and simplicity for game developers. We do not maintain the extensive documentation or audits required for these certifications, keeping our overhead low to pass savings on to you.

Do you have a WordPress plugin?

No, we do not offer a WordPress plugin. We provide a standard REST API that works with any programming language or engine. You can integrate our voices directly into your game engine or web project using plain HTTP requests or the official OpenAI SDK with a custom base URL.

Do you offer voice cloning?

No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design a new one. We provide eight preset voices (like Aria, Nova, and Atlas) based on licensed recordings. These presets cover various tones, from warm narrators to deep documentary styles.

Can I upload my own voice?

No, you cannot upload your own voice for cloning. Our service uses eight fixed presets derived from LibriVox public-domain readings. If you need a specific voice, you must choose from our existing library of female and male presets, which are designed to cover common NPC dialogue needs.

Do you have a mobile app?

No, we do not have a mobile app. Our service is a cloud-based API accessed via HTTP requests. You can generate speech from any device with internet access using our API keys. This allows you to integrate TTS directly into your game engine or development workflow seamlessly.

Do you offer refunds?

Failed requests are refunded automatically. If synthesis fails, the charge is returned in full. Your balance does not expire, so you can use credits anytime.

Do you accept PayPal?

No, we do not accept PayPal or credit cards. We accept USDT on the TRON network (TRC-20) only for top-ups. The minimum top-up is $5, and credits are added automatically within minutes. This crypto-only approach helps us keep transaction fees low and pricing transparent for developers.

Do you have a VAT number?

No, we do not provide invoices with VAT. We are an independent storefront without enterprise billing structures. Payments are made via USDT on TRON. If you need proof of payment, we can provide transaction details via email support, but we do not issue formal VAT invoices.

Do you have an enterprise plan?

No, we do not offer enterprise plans, seats, or minimum spend requirements. Our pricing is simple: $10 per million characters. There are no monthly plans or contracts. This pay-as-you-go model is designed to be affordable for freelance game developers and small indie studios with variable usage needs.

Who We Are

Sound wave illustration for: Who We Are

VoxQuest is an independent storefront for a text-to-speech API, built by indie developers who understand the constraints of small teams. We provide a straightforward way to generate NPC dialogue without the overhead of traditional voice acting.

Editorial Team

Editorial Team

Our small team consists of indie developers and audio enthusiasts who test every voice preset in actual game engines. We verify that the 8 available voices sound natural in context, ensuring reliable results for your projects.

Mission for Indie Devs

Mission for Indie Devs

We aim to simplify the integration of synthetic speech into your project by offering clear presets, straightforward pricing, and transparent data usage. Our goal is to help you focus on game design, not on managing complex audio pipelines.

Independent Storefront

We are not affiliated with OpenAI or other major brands. We operate as a direct gateway to the TTS API, giving you full control over your API key and usage without middlemen or hidden fees.

Voice Licensing

Sound wave illustration for: Voice Licensing

We built VoxQuest on a foundation of transparent licensing to give freelance game developers clear rights for their NPC dialogue. Our voices are derived from established, openly licensed datasets, ensuring that your generated audio is safe for commercial use without hidden legal fees or complex attribution requirements.

LibriTTS-R License

The synthetic voices are based on licensed recordings from LibriTTS-R, which operates under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This open license structure provides a reliable legal framework for deriving new audio assets while maintaining clear attribution standards for the underlying data.

  • CC BY 4.0 licensed source data
  • Clear commercial usage rights
  • Standard attribution requirements

LibriVox Sources

Our voice presets also draw from LibriVox public-domain audiobook readings. Since these source recordings are in the public domain, they carry no remaining copyright restrictions. This dual-source approach ensures that your NPC dialogue is built on material that is freely available and legally unencumbered.

  • Public-domain audiobook readings
  • No copyright restrictions on source audio
  • High-quality natural speech patterns

Commercial Rights

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This combination allows you to integrate synthetic speech into your games without worrying about traditional voice acting royalties or complex licensing negotiations.

  • Ready for commercial game projects
  • No per-unit royalties
  • Simple legal footing

Data Policy

Sound wave illustration for: Data Policy

We use your input text solely to generate the requested audio file. It is not used for training our models or improving the engine. This ensures your dialogue lines remain private and are not consumed to build future voice datasets.

No Training on Input

Your text is processed strictly for synthesis. We do not retain your raw input for machine learning purposes, keeping your game’s narrative data distinct from our training corpus.

No Storage of Audio

Generated audio files are returned in the response and not stored. Once you receive the file, we do not keep a copy on our infrastructure, ensuring your NPC voices are yours alone.

Metadata for Billing

We keep request metadata—time, character count, and status—only for billing accuracy. This allows us to verify charges and process refunds for failed requests without storing the actual audio content.

Technical Limits

Sound wave illustration for: Technical Limits

VoxQuest delivers a straightforward, file-based TTS API. We prioritize simplicity and predictable costs over complex, real-time features. This keeps the integration lightweight for freelance game developers who just need reliable NPC dialogue audio files without managing streaming infrastructure or complex markup languages.

No Streaming

We return complete audio files (mp3, wav, opus, flac, pcm) in the response body. There is no WebSocket or partial audio stream, so you cannot hear words as they are generated. This is ideal for pre-baking dialogue into your game engine rather than real-time playback.

  • Complete file delivery in response

No SSML

Our API accepts plain text input with no support for SSML tags. You cannot control pitch, rate, or pauses via XML markup. Voice characteristics are determined solely by the selected preset (e.g., 'sage' for calm, 'felix' for energetic). For nuanced timing, split your text into multiple requests.

No Custom Cloning

We use 8 fixed presets derived from licensed LibriTTS-R recordings. We do not offer voice cloning or custom voice uploads. You cannot train a model on your own voice or a specific character's voice. All generated audio carries an inaudible synthetic watermark to mark it as AI-generated speech.

  • 8 fixed presets only

Support

Sound wave illustration for: Support

VoxQuest is built for developers who value time over talk. We keep our support structure simple and transparent, ensuring you can reach us when you need help without the hassle of complex call centers or waiting on hold. Our team focuses on resolving technical and billing questions efficiently via email, the most reliable channel for detailed asynchronous communication.

We believe in clear, documented answers rather than endless back-and-forth conversations. By sticking to email, we ensure every query is logged, searchable, and handled with care. This approach allows us to maintain high quality in our responses while keeping our operational costs low, passing those savings on to you in the form of affordable TTS pricing.

Email Only

All support requests are handled via email. This ensures your query is documented and can be addressed thoroughly by our team. You can send your questions to [email protected].

For complex technical issues, such as API integration problems or billing discrepancies, we may take a bit longer to provide a detailed solution.

  • Send queries to [email protected]
  • Response time: within 24 hours
  • Detailed, documented responses

No Live Chat

We do not offer live chat. This decision reduces overhead and allows our support team to focus on providing thoughtful, accurate answers rather than rushing through quick chats. It also means you won't have to wait in a queue for a human to become available.

If you prefer immediate assistance, you can check our documentation at /docs/ for common integration issues and API usage examples. For anything not covered there, email is the best way to get a precise answer.

No Phone Number

We don't have a phone number. Voice calls can be disruptive and hard to schedule, especially for a remote-first team. Email allows you to include screenshots, logs, and code snippets directly in your message, which helps us solve your problem faster.

If you have a billing question or need to discuss a custom integration, email is still the preferred channel. We’re here to help, just not by phone.

Support

Contact Us

Sound wave illustration for: Contact Us

We are a small, independent team built for freelance game developers. Our support channel is straightforward: email only. We do not have a phone number, live chat widget, or ticketing system to clutter your workflow. If you have a specific question about your NPC dialogue integration or API key, this is the place to send it.

Email Address

Send all inquiries to [email protected]. This is the single point of contact for our entire team. We do not route messages through different departments, so you will get a direct answer from someone who understands the API and the game dev context.

Response Time

We aim to respond to all emails within one business day. Since we are a lean team handling our own infrastructure and billing, volume can occasionally cause slight delays, but we prioritize clear, specific questions about your project's audio needs.

Feedback

We build this API specifically for indie developers who need reliable NPC voices without legal headaches. Your feedback on which voices work best for RPGs or sci-fi projects helps us prioritize new presets and improve voice clarity. If you notice a glitch in the synthesis, tell us exactly which voice and text triggered it.

Pricing and Payment

Sound wave illustration for: Pricing and Payment

VoxQuest charges $10 per million characters, or $0.01 per 1,000 characters. Failed requests are free, ensuring you only pay for successful synthesis. Balances never expire, and there are no monthly plans or minimum spend requirements.

Per-Character Rates

Every character, including spaces and punctuation, counts toward your usage. This predictable model helps indie developers budget NPC dialogue costs accurately without hidden fees or volume discounts.

USDT Top-Up

Top up your account using USDT on the TRON network (TRC-20). The minimum deposit is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or issue VAT invoices.

  • Network: TRON (TRC-20)
  • Minimum: $5
  • Speed: Automatic, within minutes

Free Trial Credit

Sign in with Google to receive $0.50 in free credit, enough for approximately 50,000 characters. This trial is valid for 7 days. Accounts created with email and password start with zero balance.

API Integration

Sound wave illustration for: API Integration

VoxQuest’s API mimics the OpenAI speech endpoint structure, allowing you to reuse existing integration code. By updating the base URL to https://api.playmm9.com/v1 and using your API key, you can generate NPC dialogue with standard libraries.

OpenAI SDK Compatible

The endpoint POST /v1/audio/speech accepts the same JSON body as the OpenAI speech API. This means you can use the official OpenAI SDKs for Python, Node.js, or other languages without rewriting your request logic.

  • Use standard OpenAI SDKs with modified base_url
  • Supports JSON body format
  • Compatible with popular programming languages

Request Format

Send text up to 4096 characters per request. You can specify the model ("tts-1" or "tts-1-hd"), voice preset, response format (mp3, wav, opus, flac, pcm), and speed (0.25–4.0). The language field is optional but recommended for non-English Latin text.

Rate Limits

New keys start with a limit of 10 requests per minute. After your first top-up, the limit increases to 60 requests per minute. Requests are processed sequentially, so under load, synthesis may wait in a queue.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This preset is excellent for tutorial systems, helping new users understand controls or rules with a friendly, approachable demeanor.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. OpenAI API reference: create speech
  3. Tether (USDT)
  4. ISO 639 language codes
  5. openai-node on GitHub
  6. Python documentation
  7. openai-python on GitHub
  8. LibriTTS-R corpus (OpenSLR 141)
  9. TRON developer hub: TRC-20
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. curl documentation
  12. Creative Commons Attribution 4.0

More on this site