Frequently asked questions
What is AI powered text to speech for tourism?
It is a cloud API that converts written text into audio files. You send a script via JSON, and receive synthesized speech. This allows tourism creators to generate natural-sounding audio guides from existing scripts without recording studios, streamlining the production of museum and tour content.
How many languages does the API support?
The 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 can speak any of these languages, ensuring versatile content for diverse tourist audiences.
Can I use the API for commercial museum projects?
Yes, the API is designed for commercial use. There are no monthly plans, seats, or minimum spend requirements. You simply pay for the characters you generate. Generated audio is not stored by the service, and input text is used only for production, making it suitable for commercial tour scripts.
What is the character limit per request?
Each API request accepts up to 4096 characters of text. For longer scripts, you can split the text into parts of this size and join the resulting audio files. This allows you to generate complete audioguides regardless of the total script length.
How much does it cost to generate an audio guide?
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 charges returned in full. There are no subscriptions or minimum spend requirements, so you only pay for what you generate.
Do I need to code to use the API?
No coding experience is required. You can paste your text into the dashboard on /get-api-key/ and download the audio files directly. The API also works with standard tools, but the web interface allows non-technical users to generate audio guides easily without writing code.
Are the voices human or synthetic?
The voices are synthetic, based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. However, they are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech, distinguishing it from human recordings.
Can I change the speed of the audio?
Yes, you can adjust the playback speed between 0.25 and 4.0. This allows you to speed up or slow down the narration to fit your specific tour pacing needs. The speed parameter is part of the standard request body sent to the API.
What audio formats are available?
You can choose from mp3, wav, opus, flac, and pcm formats. Select the format that best suits your distribution method, whether it is web delivery, mobile apps, or offline museum devices. The format is specified in the request body alongside the text and voice.
Is my tour script data used for training?
No, your input text is used only to produce the audio and is not used for training the model. Generated audio is returned in the response and not stored by the service. Only request metadata like time and character count is kept for billing purposes.
How do I top up my account?
Top up using USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes after the transfer. There are no credit cards, PayPal, or subscriptions. Your balance does not expire, so you can top up as needed.
Do you offer refunds for failed requests?
Yes, failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successfully generated audio files. You can monitor the status of your requests in the dashboard to confirm whether a charge was applied.
What is the difference between tts-1 and tts-1-hd?
Both models use the same engine and have the same price. The only difference is the model identifier in the request. You can choose either 'tts-1' or 'tts-1-hd' without any change in cost or character limits, allowing flexibility in your API configuration.
Can I generate audio for a 10,000 character script?
Yes, you can generate audio for a 10,000 character script by splitting it into parts of up to 4096 characters. You then join the resulting audio files. This workflow allows you to create complete audioguides from longer texts without exceeding the per-request character limit.
First request
curl
curl https://api.playmcww.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.mp3Turn Tour Scripts into Audio Guides
Convert your written tour scripts into professional audio guides instantly. Our platform allows museum curators and tourism creators to generate natural-sounding narration without complex technical setups. Simply paste your text, select a voice, and download the audio file for immediate use in your exhibits.
Simple online generation for quick previews
Test your scripts quickly by pasting text directly into our interface. Receive an audio file after a short wait, allowing you to review pacing and tone before committing to full production. This method is ideal for short exhibit descriptions or quick audio samples.
- Paste text and download audio instantly
- Ideal for short exhibit descriptions
- Account required for basic previews
API integration for mobile apps and websites
For larger projects, integrate our API directly into your mobile apps or museum websites. Send a JSON request with your script and receive an audio file. The endpoint structure matches the OpenAI speech API, making it easy for developers to plug in without rewriting code.
No coding needed for basic audio creation
You do not need to be a developer to use our core features. The web interface handles the technical details, allowing you to focus on your content. Generate audio guides for your tours using just a mouse and keyboard, perfect for non-technical tourism teams.
Choose the Right Voice for Your Tour
Select a voice that matches the atmosphere of your space. Our eight presets are designed to enhance the visitor experience, from warm narrators for history tours to friendly voices for interactive exhibits.
Warm narrators for history tours
Use Aria or Luna to deliver historical narratives with clarity and warmth. These voices provide a natural storytelling rhythm that keeps visitors engaged without sounding artificial.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling tone
Friendly voices for interactive exhibits
For interactive displays or children’s areas, choose Felix or Milo. Their energetic and conversational tones make instructions feel welcoming and approachable for all ages.
- Felix: Energetic, promo style
- Milo: Friendly, conversational
Calm tones for relaxation zones
Create a peaceful atmosphere in meditation or rest areas with Sage or Orion. Their calm, instructional, or deep documentary styles help visitors unwind.
- Sage: Calm, instructional
- Orion: Deep, documentary
Support for Major Tourist Languages
The API supports 23 languages, ensuring your audio guides reach diverse visitors. You can explicitly set the language code or let the system detect it from the text script. This flexibility prevents mispronunciation and ensures natural delivery for international tourists.
English, Spanish, and French narration
These are the most common languages for global tourism. Our voices handle these natively, providing clear and accurate pronunciation for standard tourist scripts.
Asian languages including Japanese and Korean
Support for Japanese and Korean allows you to create localized guides for major Asian destinations. The system accurately processes these scripts without requiring special setup.
European languages like German and Italian
Beyond English, Spanish, and French, we support German, Italian, and 19 other European languages. This covers the vast majority of tourist destinations across Europe and the Americas.
High-Quality Audio Formats
Select the audio format that matches your deployment environment. Our API supports MP3, WAV, FLAC, and OPUS, giving you control over file size, quality, and compatibility for museum installations or mobile applications.
MP3 for web streaming and apps
MP3 is the standard for web delivery and mobile apps. It offers a good balance between file size and audio quality, ensuring fast loading times for your audio guide players without compromising clarity.
WAV for high-fidelity museum speakers
Choose WAV for uncompressed, high-fidelity audio. This format is ideal for local playback on museum speakers or kiosks where maximum audio clarity is required and bandwidth constraints are minimal.
FLAC for archival preservation
FLAC provides lossless compression, preserving every detail of the synthesized voice. Use this format for long-term archival of your tour content, ensuring future-proof storage without data loss.
Fast and Reliable Generation
Long tour scripts generate at roughly real-time speed, averaging about 25 characters per second. While short phrases take a few seconds, longer texts process sequentially, so requests may queue under high load. This ensures consistent audio quality without compromising the integrity of your museum or tourism content.
Real-time speed for long scripts
Generation speed matches spoken pace, producing approximately one second of audio for every 25 characters of input. This predictable rate helps you estimate processing times for large-scale audiobook projects or extensive museum exhibits without unexpected delays.
Consistent quality across all texts
Every request uses the same high-fidelity engine, ensuring uniform tone and clarity whether you are generating a 50-word exhibit label or a 4000-character historical narrative. The engine handles varying text lengths without degrading voice quality or introducing artifacts.
Manual handling of long tour segments
Since the API limits input to 4096 characters per request, longer tour scripts must be split into parts by the user. You split the text, send each segment, and join the resulting audio files manually. This approach ensures precise control over chapter breaks and segment boundaries.

Transparent Pricing for Tourism Budgets
Audio guide production costs scale directly with content length. We charge $0.01 per 1,000 characters, ensuring you only pay for what you generate. Failed requests are refunded in full, so you never pay for errors.
Pay only for characters used
Every character, including spaces and punctuation, counts toward your usage. This linear pricing model makes budgeting for large museum collections predictable and simple.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Spaces and punctuation count
No monthly fees or subscriptions
There are no recurring subscriptions, seats, or minimum spend requirements. You can top up your balance whenever needed without locking into a contract.
Free trial to test your first audio guide
Sign in with Google to receive $0.50 in trial credit, enough for approximately 50,000 characters. This allows you to generate and test your first audio guide immediately.
Easy API for Developers
Connect your museum’s digital assets to our TTS engine using standard tools. Our API uses the same request shape as the OpenAI speech endpoint, allowing you to leverage existing OpenAI SDKs by simply changing the base URL to https://api.playmcww.com/v1.
OpenAI SDK compatible endpoint
Use the official OpenAI SDKs with zero code changes. Set your base_url to https://api.playmcww.com/v1 and use your site-specific key. This ensures you get the same JSON response structure and error handling you are already familiar with, reducing integration time for your development team.
Simple JSON request structure
Send a POST request to /v1/audio/speech with your script. The body requires only the model (e.g., tts-1-hd), input text, and voice preset. You can also specify response_format (mp3, wav, opus, flac, pcm) and speed (0.25–4.0) to match your tour’s pacing.
- Supports 8 voice presets optimized for narration
- Handles up to 4096 characters per request
- Returns audio files directly in the response
Clear documentation for integration
Visit our /docs/ page for complete reference materials. We provide ready-to-use curl examples and code snippets for common languages. Authentication is handled via a Bearer token in the header, ensuring secure access to your generated audio guides.
Data Privacy for Your Content
We process your museum scripts solely to generate the requested audio file. Your text is not retained after synthesis, ensuring that your curated tour narratives remain private and secure.
Text used only for audio generation
Input text is used exclusively for producing the audio and is not used for training. We do not reuse your scripts for model improvement or other purposes.
No training on your scripts
Your content remains yours. We do not use your input data to train or improve our TTS models, preserving the uniqueness of your tour content.
No storage of generated audio files
Generated audio is returned in the response and not stored. Once you download your file, it is not kept on our servers, giving you full control over your audio assets.
Start Creating Audio Guides Today
Create your first museum audio guide in minutes. Sign up with your Google account to receive $0.50 in free trial credit, valid for 7 days. This allows you to generate approximately 50,000 characters of narration without entering payment details.
Once registered, you will instantly access your unique API key on the /get-api-key/ dashboard. You can immediately paste your tour scripts and download audio files directly from the interface, requiring no coding experience for basic use.
Sign up with Google for instant access
Visit the /get-api-key/ page and click "Sign in with Google." This method provides immediate access to your account along with a $0.50 trial credit. Accounts created via email and password start without this trial credit.
- Instant account creation
- Automatic $0.50 trial credit (7 days)
- No credit card required
Get your API key in seconds
Your dashboard displays your active API key immediately after login. You can use this key to authenticate requests or simply view your balance and usage statistics. If needed, you can issue a new key at any time, which invalidates the previous one instantly.
- Key displayed on dashboard
- Instant key rotation available
- Real-time balance tracking
Generate your first tour audio now
Paste your script into the online generator or use the provided cURL example. The system processes text up to 4096 characters per request. For longer tours, you must split the text into parts of up to 4096 characters and join the resulting audio files. You receive the audio file directly in your chosen format.
- Paste text and download audio
- Support for MP3, WAV, Opus, FLAC
- Automatic handling of long texts
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This feedback loop ensures your final audio guide meets visitor expectations without unnecessary rework.
23 languages
Any voice speaks any of these languages.
