Frequently asked questions
Do I need to credit the voice actors for synthetic NPCs?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. While attribution is good practice, the synthetic output is generated via our API. You do not need to credit specific voice actors for each NPC line, as the audio is a new synthetic file, not a direct rip of the original recording.
Can I use these voices in commercial games?
Yes. Our API generates synthetic audio files that you receive in the response. Since the input text is used only to produce the audio and not for training, and the voices are based on CC BY 4.0 and public-domain sources, you can integrate these audio files into your commercial game projects without additional licensing hurdles.
Are the voices watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded directly into the audio data returned by the API, allowing you to identify the content as AI-generated if needed, without affecting the audio quality or your ability to use it in your game.
What happens if my API request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests, so you can experiment with different voices or parameters without worrying about unexpected costs. This ensures that your API key balance reflects only successful audio generations, making it easy to track your actual usage and spending.
Do I need to download SDKs?
No. You can use the official OpenAI SDKs by changing the base_url to https://api.playmm9.com/v1, or use plain HTTP requests. We do not provide a proprietary SDK, so you can integrate the TTS API into your game engine using the tools and libraries you already have, keeping your workflow simple and familiar.
Can I control the speed of the NPC dialogue?
Yes. You can adjust the speech speed between 0.25 and 4.0 by setting the speed parameter in your API request. This allows you to fine-tune the pacing of NPC dialogue, making characters sound faster or slower to match the action or emotion of your game scene, ensuring the audio fits your narrative perfectly.
Are there any hidden fees for high volume?
No. The price is a flat $10 per 1 million characters, with no monthly plans, seats, or minimum spend. Failed requests are free, and your balance does not expire. You pay only for the characters you successfully generate, making it affordable for indie developers regardless of whether your game has a few NPCs or hundreds.
Is the audio generated in real-time?
Not strictly. Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real-time for long texts (about 25 characters per second), but short phrases may take a few seconds. We do not offer streaming or WebSocket endpoints for partial audio delivery.
Can I use multiple voices in one scene?
Yes. You can send multiple POST requests to the API, each with a different voice preset like aria, nova, or atlas. Since each request generates a separate audio file, you can assemble these files in your game engine to create diverse dialogue scenes with distinct character voices, enhancing the immersion of your game world.
Do you support SSML for emphasis?
No. We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control the output by selecting from eight voice presets and adjusting the speed parameter. If you need specific emphasis, you can adjust the text input or use the speed setting to convey tone, as we do not offer SSML tags for fine-grained control.
What is the character limit per request?
Each API request can handle up to 4096 characters of input text. For longer dialogues, you should split the text into parts of this size and join the resulting audio files. This limit ensures efficient processing, and since spaces and punctuation count as characters, you can plan your NPC dialogue accordingly to stay within the limit.
Can I clone my own voice with this API?
No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. You choose from eight preset voices (like aria, nova, or atlas) that are based on licensed recordings. This keeps the integration simple and affordable, as you do not need to manage custom voice models or training data for your NPCs.
Is there a free trial for developers?
Yes. Signing in with Google gives you $0.50 of credit (about 50,000 characters) valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test the API, generate sample NPC dialogue, and verify integration before committing to a top-up, ensuring the voices fit your game's style.
How do I top up my account?
Top up using USDT on the TRON network (TRC-20) only, with a minimum of $5. The balance is credited automatically within minutes after the transfer. We do not accept cards, PayPal, or subscriptions, so you can fund your account directly with crypto, keeping the process straightforward and avoiding the need for invoices or VAT handling.
First request
curl
curl https://api.playmm9.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Synthetic Voices for NPCs?
Traditional voice acting for indie games often means navigating union fees and complex licensing deals that eat into tight budgets. Synthetic voices remove these barriers, allowing you to generate unlimited NPC dialogue instantly without scheduling constraints or union negotiations.
Eliminate Actor Union Fees
Union rates can stall production, especially for games with extensive dialogue trees. By using synthetic speech, you pay a flat rate per character rather than hourly session fees or residual royalties, keeping your development costs predictable and low.
Instant Generation for Large Dialogues
Need 50,000 lines of quest text? Our API processes requests sequentially, handling large volumes without waiting for studio availability. You get audio files directly, ready for integration, ensuring your dialogue pipeline never bottlenecks during final polish.
No Licensing Royalties on Generated Audio
Once generated, the audio files are yours to use in your game without ongoing royalty checks or licensing renewals. The synthetic nature of the voices means no recurring costs tied to specific voice actors, simplifying your legal overhead.
Our 8 Preset Voices
Choosing the right voice is critical for immersion. Our eight presets are designed to cover the most common NPC archetypes in indie games, from warm narrators to deep lore keepers.
Warm Narrator Aria
Aria offers a warm, clear tone perfect for exposition or friendly guides. Her natural inflection keeps players engaged without feeling robotic.
Upbeat Nova for Quest Givers
Nova brings a bright, upbeat energy to dynamic interactions. Use her for high-energy dialogue or urgent mission updates.
- Best for: Energetic side quests, upbeat announcers
Deep Documentary Orion for Lore
Orion provides a deep, documentary-style voice ideal for historical records or ancient lore. His neutral delivery adds weight to serious narrative moments.
- Best for: Ancient texts, serious NPCs, history logs
Supported Languages
VoxQuest supports 23 languages, allowing you to localize NPC dialogue without hiring multiple voice actors. English, Spanish, and German are among the supported languages, ensuring clear communication for major markets. Our engine handles diverse scripts with precision, letting you focus on narrative rather than language barriers.
We also support Japanese and Korean, expanding your reach into key gaming communities. Whether you are creating a fantasy RPG or a sci-fi shooter, you can easily adapt dialogue to fit your game's setting without compromising audio quality or consistency across different voice presets.
English, Spanish, and German
English, Spanish, and German are among the supported languages. These core languages ensure high-quality synthetic voices for your primary player base. Use any of our 8 voice presets to match character personalities, from the warm narrator Aria to the energetic promo style of Felix.
- Native-like pronunciation across all 8 voices
- No extra cost for localization
Japanese and Korean Support
Japanese and Korean support allows you to expand your indie game’s audience globally. Our engine accurately handles complex character sets and intonation patterns, ensuring NPCs sound natural in these languages. This feature is essential for developers targeting Asian markets without needing native voice talent.
- Accurate character rendering
- Natural intonation patterns
23 Total Languages Available
We offer 23 languages in total, including Arabic, Chinese, French, Hindi, Italian, and more. Any voice can speak any of these languages, giving you flexibility in character design. If the language is not set, the system guesses based on script, but we recommend specifying it for best results.
Note: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not yet supported.
- Arabic, Danish, Dutch, Finnish, Greek, Hebrew, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, Turkish
- Any voice works with any language
How It Works
Generate NPC dialogue by sending a simple HTTP request. Our API processes your text and returns a high-quality audio file, ready to drop into your game engine.
Integrate seamlessly using standard tools. The endpoint matches the OpenAI speech API structure, allowing you to use the official OpenAI SDKs or basic curl commands for quick prototyping.
Send Text, Receive Audio
Submit up to 4096 characters of dialogue text via a POST request. The engine synthesizes the speech and returns the audio file in your chosen format, such as MP3 or WAV.
- Supports 8 distinct voice presets for varied NPC personalities.
- Handles languages from English to Japanese with automatic detection or explicit setting.
Simple JSON API Endpoint
Use the endpoint POST https://api.playmm9.com/v1/audio/speech. The request body is a standard JSON object containing your API key, the text input, and voice parameters.
Authentication is handled via a Bearer token in the Authorization header. One active key per account ensures straightforward access control for your development workflow.
OpenAI SDK Compatible
Reuse your existing OpenAI SDK code by simply changing the base_url to https://api.playmm9.com/v1. This allows for rapid integration without rewriting your client logic.
Use the same request shape for models like tts-1 or tts-1-hd, making migration or comparison between providers effortless.
- Compatible with official OpenAI SDKs.
- No custom client library required.
Pricing for Freelancers
VoxQuest charges $10 per million characters, meaning every 1,000 characters costs just $0.01. Failed requests are free, so you only pay for successfully generated audio. Spaces and punctuation count toward the total, ensuring transparent billing for every line of NPC dialogue.
Pay Per Character
Generate dialogue efficiently without worrying about volume caps. With a limit of 4,096 characters per request, you can split longer conversations and join the audio files seamlessly. This model fits perfectly for indie projects with unpredictable dialogue needs.
- $0.01 per 1,000 characters
- Failed requests are free
- No hidden per-minute fees
No Monthly Subscriptions
Keep your overhead low by paying only for what you use. There are no monthly plans, no seats, and no minimum spend. Your balance never expires, so you can pause development and resume later without losing credit.
Free Trial Available
Start immediately with a free trial. Signing in with Google gives you $0.50 in credit, enough for about 50,000 characters valid for 7 days. Accounts created with email and password start without this trial credit.
- $0.50 free credit
- 7-day validity period
- Instant access with Google sign-in

Technical Specs
Our API supports multiple audio formats to fit your game engine’s needs. You can request MP3, WAV, OPUS, FLAC, or PCM. This flexibility ensures seamless integration whether you are building for mobile or PC.
The TTS engine processes requests sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, generating about 25 characters of text per second of audio for long dialogues. Short phrases take a few seconds to synthesize.
MP3, WAV, OPUS Formats
Choose the format that best suits your storage and playback constraints. We support MP3, WAV, OPUS, FLAC, and PCM. Each generated file carries an inaudible watermark marking it as synthetic speech, helping you identify assets later.
All formats are generated via a single API call. You do not need separate endpoints or conversion steps for different file types.
- MP3 for compressed web delivery
- WAV for high-quality local storage
- OPUS for efficient storage
- FLAC for lossless archives
- PCM for raw audio processing
Speed Control 0.25x to 4.0x
Adjust speech speed between 0.25x and 4.0x to match character personality or scene pacing. Slow down dialogue for dramatic effect or speed up for rapid-fire NPC interactions. This control applies to all 8 preset voices.
The speed parameter is included in your JSON request body. It allows fine-tuning without re-generating the audio file if you decide to change the pace later.
4096 Character Limit per Request
Each API call accepts up to 4,096 characters of input text. Spaces and punctuation count toward this limit. For longer dialogues, split the text into parts, generate each part, and join the resulting audio files.
This limit ensures consistent quality and manageable processing times. If you exceed the character count, the API will return an error, allowing you to adjust your segmentation strategy.
Data & Privacy
When you send dialogue for your NPCs, that text is used solely to generate the audio file and is never used to train our models. Once the audio is returned, it is not stored on our servers, ensuring your unique dialogue trees remain private.
No Training on Your Text
Your input characters are processed strictly for synthesis. We do not repurpose your NPC lines or voice directions to improve the TTS engine, keeping your creative IP distinct from our general training data.
Inaudible Watermarking
Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify AI-generated NPC dialogue in your final game build without affecting the audio quality or player immersion.
Metadata Kept for Billing
We retain request metadata—specifically the timestamp, character count, and status—for billing purposes. This allows us to accurately charge you $0.01 per 1,000 characters and verify failed requests for full refunds.
Get Started
Getting started with VoxQuest takes less than five minutes. Create your account using Google to instantly receive $0.50 in trial credit, valid for seven days. This allows you to generate approximately 50,000 characters of NPC dialogue before committing to a top-up.
Once signed in, you gain access to your unique API key and usage dashboard. You can immediately start testing voices like Aria or Orion without any initial financial risk.
Sign Up with Google
Visit the /get-api-key/ page and click "Sign in with Google." This method automatically activates your free trial credit. If you prefer, you can also register with an email and password, though this method does not include the initial trial balance.
Get Your API Key
After authentication, your dashboard displays your active API key starting with tts-. This single key controls all requests. You can generate a new key at any time, which immediately invalidates the previous one for security.
- One active key per account
- New keys invalidate old ones instantly
- Auth header:
Authorization: Bearer tts-...
Copy the cURL Example
Use the provided cURL snippet to make your first request. Send a POST to https://api.playmm9.com/v1/audio/speech with your text and selected voice. The API returns the audio file directly, ready for integration into your game engine.
- Endpoint: POST /v1/audio/speech
- Supports standard JSON body
- Works with OpenAI SDKs
Community & Open Source
VoxQuest is built for developers who value open standards. Our API mirrors the widely adopted OpenAI request shape, meaning you can swap the base URL in your existing scripts without rewriting your entire integration logic. This compatibility ensures that your game’s audio pipeline remains flexible and future-proof, whether you are prototyping in Unity or building a custom backend in Python.
There are no hidden tiers, surprise overage fees, or complex enterprise contracts. You pay exactly $0.01 per 1,000 characters, and failed requests are refunded instantly. This predictability helps indie developers budget their audio costs accurately per project, avoiding the financial risk often associated with voice-over pipelines.
GitHub Integration Friendly
Integrate directly into your repository workflows. Since we support standard JSON payloads, you can store your voice presets and speed configurations alongside your game code. This makes version control for your audio assets seamless, allowing you to track changes in NPC dialogue just like you track changes in your C# or C++ scripts.
Our straightforward endpoint structure means you don’t need a dedicated middleware. You can call the API directly from your game client or server during development, then switch to a backend proxy in production if needed. This flexibility supports both rapid prototyping and scalable deployment.
- Compatible with standard OpenAI SDKs
- Simple JSON request structure
- Easy to version control
Transparent Pricing Models
Costs are directly proportional to usage. With a clear $10 per million characters rate, you can calculate exact audio costs before generation. The free trial provides $0.50 in credit, allowing you to test voice quality and integration without financial commitment.
No monthly subscriptions mean you only pay when you need audio. This model is ideal for indie developers with fluctuating production schedules, ensuring you never pay for unused capacity or dormant accounts.
- $0.01 per 1,000 characters
- No monthly subscriptions
- Instant refunds on failure
Developer-First Support
We prioritize clear documentation and direct communication. Our support team consists of developers who understand the nuances of game audio integration. You can reach us via email for technical questions, pricing clarifications, or integration tips.
We avoid marketing fluff in favor of practical solutions. If you encounter a rate limit or a format issue, we provide specific guidance on how to adjust your request parameters, such as splitting text chunks or adjusting speed settings to optimize generation time.
- Email support only
- Developer-focused responses
- No live chat wait times
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.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- IETF RFC 7845: Ogg Opus
- W3C WAI: making audio and video accessible
- LibriVox public-domain audiobooks
- ISO 639 language codes
- TRON developer hub: TRC-20
- FFmpeg documentation
- LibriTTS-R corpus (OpenSLR 141)
- Creative Commons Attribution 4.0
- Node.js documentation
- OpenAI API reference: create speech
