Frequently asked questions
Is the Arabic TTS free?
Arabic TTS is not free. It costs $0.01 per 1,000 characters. You receive a $0.50 free trial credit when signing in with Google, valid for 7 days. Email accounts start without trial credit. Failed requests are free. You can top up with USDT on TRON (TRC-20) starting at $5.
Which voices support Arabic?
All eight voices support Arabic. You can choose from female voices Aria, Nova, Luna, and Sage, or male voices Felix, Milo, Atlas, and Orion. Each voice has a distinct tone, from warm narration to deep documentary style. Any voice can speak any of the 23 supported languages, including Arabic.
How do I integrate the API?
Send a POST request to https://api.play33ok.com/v1/audio/speech with your text and voice selection. The endpoint uses the same JSON structure as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url. Include your API key in the Authorization header as a Bearer token.
What is the character limit?
Each request accepts up to 4096 characters of input text. For longer texts, split them into parts of 4096 characters or less and join the resulting audio files. Spaces and punctuation count toward the character limit. This limit applies to the input text field in every API call.
Do I need an API key?
Yes, you need an API key. Authentication uses the header Authorization: Bearer tts-... . You get one active key per account, issued on the /get-api-key/ page. You can issue a new key at any time; the old one stops immediately. Keys are required for all API requests.
How is pricing calculated?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spends. Balance does not expire. Top-ups via USDT are credited automatically.
Can I use the voices in games?
Yes, the voices are suitable for game audio. Generated files carry an inaudible watermark marking them as synthetic speech. Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. Input text is not used for training, and generated audio is not stored by the API.
Does it support SSML?
No, the API does not support SSML. It accepts plain text input up to 4,000 characters. There are no phoneme dictionaries or custom pronunciation lexicons. You cannot use emotion tags or SSML tags for pacing or emphasis. Adjust speed using the speed parameter between 0.25 and 4.0.
What audio formats are available?
Available formats are mp3, wav, opus, flac, and pcm. Specify the format using the response_format field in your request. All formats are generated from the same engine models (tts-1 or tts-1-hd). Choose the format that best fits your game engine’s audio pipeline requirements.
How fast is the generation?
Generation is roughly real-time on long texts, about 25 characters per second. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed applies to standard usage. Rate limits allow 60 requests per minute per key.
Can I clone a voice?
No, custom voice cloning is not offered. You cannot upload your own voice or design a custom voice. The API provides eight preset voices based on licensed recordings. There is no voice cloning feature, emotion tagging, or phoneme dictionary. Use the existing eight presets for your NPC dialogue.
Is there a free tier?
There is no ongoing free tier. You receive a $0.50 free trial credit (about 50,000 characters) valid for 7 days when signing in with Google. Email accounts start without trial credit. After the trial or balance depletion, you must top up with USDT on TRON to continue using the API.
How do I top up?
Top up using USDT on the TRON network (TRC-20). The minimum top-up is $5. Credits are credited automatically within minutes after the transfer. There are no cards, PayPal, subscriptions, or invoices. Balance does not expire. You can manage your account and view balance on the /get-api-key/ page.
Do you offer SLA?
No, there is no SLA or uptime guarantee. There is no enterprise contract, on-premise install, or data-center choice. Support is by email only. There is no phone number or live chat. No certifications like SOC 2, HIPAA, or GDPR are offered. Use the API with standard risk expectations.
First request
curl
curl https://api.play33ok.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.mp3Arabic TTS for NPCs
Generate localized NPC dialogue instantly using our Arabic-capable TTS API. Send text via a standard JSON POST request and receive an audio file ready for integration into your game engine. This workflow eliminates the need for external voice actors or complex audio pipelines, allowing you to iterate on dialogue scripts rapidly during development.
Localize dialogue instantly
Replace manual recording sessions with automated generation. Pass your dialogue strings to the API and receive synthesized speech in seconds. This approach scales effortlessly with your content volume, ensuring that every line of dialogue is produced consistently without scheduling constraints.
Support for Arabic script
The engine correctly processes Arabic script, handling right-to-left text and proper phonetic generation. You can explicitly set the language parameter to ensure accurate pronunciation, or rely on automatic detection based on the script used in your input text.
Consistent voice identity
Maintain character continuity across your game by assigning a specific voice preset to each NPC. Whether using the warm tone of Aria or the deep documentary style of Orion, the same voice file parameters are applied to every request, ensuring a uniform auditory identity for your characters.
Global Language Support
Game developers can localize NPC dialogue into 23 supported languages, including Arabic, Chinese, French, German, Japanese, Korean, Russian, Spanish, and more. Each voice can speak any of these languages, ensuring consistent character identity across your entire game world without needing separate voice actors for every region.
23 languages available
Our API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice preset can deliver natural-sounding speech in any of these languages, allowing you to maintain a unified audio style across different regional releases.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic language detection
If language is not set, it is guessed from the script (Latin text defaults to English), so for non-English Latin-script text set language. This simplifies integration, as you can pass raw text without managing language codes for every dialogue line.
Explicit language setting for Latin text
For non-English Latin-script text, we recommend explicitly setting the language parameter. Without it, the API defaults to English for Latin characters. Specifying the ISO code ensures accurate pronunciation and prosody for languages like French, German, or Portuguese, preventing the engine from defaulting to an English accent.
8 Engineered Voices
Eight distinct voice presets cover the full spectrum of NPC archetypes, from warm narrators to energetic promo announcers. Each voice is derived from licensed LibriTTS-R and LibriVox recordings, ensuring high-quality synthetic speech for game dialogue. Use consistent voices for character identity across different languages or switch tones to distinguish roles within your game world.
Every voice can speak any of the 23 languages. If language is not set, it is guessed from the script. The engine guesses the language from the script, but you can explicitly set the ISO code for Latin-script texts to ensure accurate pronunciation.
Female: Aria, Nova, Luna, Sage
Aria offers a warm, clear narrator tone ideal for exposition or calm interactions. Nova provides a bright, upbeat voice suitable for energetic characters or positive events. Luna delivers a soft, storytelling presence perfect for atmospheric dialogue. Sage brings a calm, instructional quality, excellent for tutorials or guidance NPCs.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male: Felix, Milo, Atlas, Orion
Felix is energetic and promo-focused, great for hype scenes or shopkeepers. Milo offers a friendly, conversational tone for approachable NPCs. Atlas provides a neutral, news-like voice for authoritative characters or broadcasts. Orion delivers a deep, documentary-style tone for serious or epic dialogue.
These male presets cover the remaining vocal range, ensuring you have options for every character type from the cheerful sidekick to the grim veteran.
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Voice types for narration and promo
The eight voices are engineered to cover common game audio needs. Use Aria or Luna for quest logs and story summaries. Employ Felix or Milo for interactive shop dialogue or quest updates. Atlas and Orion serve well for world-building elements like radio broadcasts or historical records.
Every generated file includes an inaudible watermark marking it as synthetic speech.
image]:
Developer-First API
The API endpoint mirrors the OpenAI speech structure, allowing you to reuse existing client libraries with a simple base_url change. This eliminates the need for custom wrappers or learning a proprietary protocol.
Requests are standard JSON bodies with minimal required fields. You send text, select a voice, and receive an audio file. This simplicity reduces integration time for freelance developers who need to localize NPC dialogue quickly without extensive engineering overhead.
OpenAI SDK compatible
Use the official OpenAI SDKs by pointing them to https://api.play33ok.com/v1. Pass your tts-... API key in the Authorization header. This compatibility means you can leverage familiar tools and error handling patterns already present in your codebase.
No custom client library is required. The request shape matches the standard speech endpoint, so migration or integration takes minutes rather than days.
- Compatible with official OpenAI SDKs
- Change
base_urltohttps://api.play33ok.com/v1 - Use standard
Authorization: Bearerheaders
Simple JSON request body
Send a POST request to /v1/audio/speech with a JSON body containing model, input, voice, and optional parameters like speed or language. The API handles the synthesis and returns the audio data directly in the response body.
Each request supports up to 4096 characters. For longer NPC dialogue, split the text into chunks, synthesize each part, and concatenate the audio files in your game engine or middleware.
- Model:
tts-1ortts-1-hd - Input text up to 4096 characters
- Optional
speed(0.25–4.0) andlanguage
Multiple audio formats (MP3, WAV, OPUS)
Choose mp3, wav, opus, flac, or pcm via the response_format field. MP3 and OPUS are ideal for reducing bandwidth in mobile or web-based games, while WAV provides uncompressed quality for local development.
Audio files are returned directly in the HTTP response.
- Supported formats: mp3, wav, opus, flac, pcm
- Optimize for bandwidth or quality
- Direct response body delivery
Pricing for Freelancers
Game dialogue generation scales with your project size. You pay only for what you process: $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free, so you only pay for successful synthesis.
$10 per million characters
Your character count includes every space and punctuation mark. At this rate, a 4,000-character NPC line costs roughly $0.04. Longer quests require splitting text, but each segment is billed individually.
No monthly subscriptions
There are no seats, minimums, or recurring fees. Balance does not expire. You top up when needed and use funds until they run out.
Free trial credit included
Sign up with Google to receive $0.50 in trial credit, valid for 7 days. This covers about 50,000 characters, enough to test voices and latency before committing to USDT top-ups.

Technical Limits
The API enforces a strict 4096-character limit per request. For longer NPC dialogue scripts, split the text into chunks and join the resulting audio files sequentially.
4096 characters per request
Each API call processes a maximum of 4096 characters. This includes spaces and punctuation. Longer dialogue lines must be split into smaller parts. The client code handles splitting and joins the audio files.
- Limit: 4096 characters per request
- Includes spaces and punctuation
- Split long texts manually or via code
60 requests per minute
Each API key is limited to 60 requests per minute. New accounts start with 10 requests per minute until the first top-up. Requests are processed sequentially. Under load, a request may wait in a queue.
- Standard limit: 60 requests/minute
- New account limit: 10 requests/minute
- Sequential processing may cause queueing
Real-time generation speed
Generation speed is roughly real-time, approximately 25 characters of text per second of audio. Short phrases take a few seconds to process. Long texts generate at near real-time speed.
- Speed: ~25 characters per second
- Short phrases: few seconds
- Long texts: near real-time
Data Privacy
When you send text to our API, we process it solely to generate the requested audio file. Your source strings are not harvested or used to train our speech models, ensuring your unique NPC dialogue remains proprietary.
Input not used for training
The text you submit is processed in real-time to produce the audio output. Once the synthesis is complete, the input data is not stored for model improvement, keeping your game’s dialogue distinct from our general dataset.
Audio returned in response
The generated audio file is returned directly in the HTTP response. We do not archive your specific audio files on our servers after delivery, meaning you retain full control over the generated assets without dependency on our storage.
No long-term storage
We retain only the metadata required for billing and usage tracking, such as request timestamps and character counts. The actual audio content and input text are not kept long-term, minimizing data exposure for your game's audio pipeline.
Integration
Integration is designed for speed and simplicity. Get your API key immediately after signing in, then use standard HTTP clients or the OpenAI SDK to start generating dialogue. The workflow requires minimal code changes to your existing audio pipeline.
Payments are straightforward via USDT on the TRON network (TRC-20). Credits are added automatically within minutes, ensuring your NPC generation never stalls due to billing delays.
USDT TRC-20 payments
Top up with USDT on the TRON network. The minimum deposit is $5, and credits appear in your balance automatically within minutes. There are no monthly subscriptions or VAT invoices to manage.
None
- TRC-20 only
- Minimum $5 top-up
- Automatic credit within minutes
- No credit cards or PayPal
Instant key generation
Sign up on /get-api-key/ using Google or email. Your API key is generated instantly and ready to use. You can issue a new key at any time, invalidating the old one immediately.
None
- Google or email signup
- Instant key creation
- Immediate revocation of old keys
cURL and SDK examples
The endpoint follows the OpenAI speech API shape. Use the official OpenAI SDKs by changing the base_url to https://api.play33ok.com/v1. A ready-to-use cURL example is provided on your dashboard.
None
- OpenAI SDK compatible
- Change
base_urlonly - Standard JSON request body
- Dashboard cURL example
Support
Support is handled exclusively via email. There is no phone line or live chat to wait on. You receive a direct response from the engineering team without intermediate layers.
Email support only
Send your queries to [email protected]. We prioritize technical issues related to API integration, billing discrepancies, or voice selection. Response times vary based on queue volume, but we aim for clear, actionable answers.
No live chat
We do not offer real-time chat widgets. This keeps our overhead low, allowing us to focus resources on API reliability and server capacity for your dialogue generation needs.
Documentation included
Comprehensive docs are available at /docs/. They include cURL examples, SDK configurations for OpenAI-compatible clients, and details on all 23 supported languages and 8 voice presets. This reduces the need for basic support tickets.
- Full API reference
- cURL and SDK examples
- Voice and language details
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.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- MDN: Web Speech API
- Node.js documentation
- FFmpeg documentation
- Creative Commons Attribution 4.0
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- W3C WAI: making audio and video accessible
- IETF RFC 7845: Ogg Opus
- ISO 639 language codes
- LibriTTS-R paper (arXiv 2305.18802)
