Frequently asked questions
Is the text to speech converter really free?
Yes. Google sign-ups receive a $0.50 trial (7 days, ~50,000 characters). Email accounts start with zero credit. After usage, top up via USDT (TRC-20) on the TRON network. Failed requests are free. There are no monthly plans or subscriptions; you only pay for characters generated.
Which languages are supported for tourism audio?
MuseVoice supports 23 languages for tourism audio: 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. If you do not specify a language, the system guesses it based on the script.
Can I use the audio for commercial museum tours?
Yes. Our API delivers licensed, watermark-safe synthetic speech designed for heritage and travel experiences. Each generated file includes an inaudible watermark marking it as synthetic speech, ensuring clear provenance for your commercial museum tours or tourism apps without requiring additional voice actor hires.
Do the voices sound robotic or natural?
The voices are synthetic but clear, generated from licensed LibriTTS-R and LibriVox recordings. They are not robotic, though an inaudible watermark marks them as synthetic. You can choose from eight presets, such as Aria for warm narration or Sage for calm instruction, ensuring high-quality audio suitable for professional audioguides and tourism content.
How do I add multiple languages to one tour?
You can generate separate audio files for each language by specifying the language parameter in your API request. Since any voice can speak any supported language, you can use the same voice preset across different language versions. This allows you to create consistent, multilingual tour experiences by calling the API for each language version.
What happens if a voice doesn't sound right?
You can switch between the eight available voice presets to find a suitable fit for your content. Each voice has a distinct tone, from energetic to calm. Since you pay per character, you can test different voices with small text samples to ensure the tone matches your museum or tourism brand before generating full tours.
Is there a limit on audio length per request?
Yes, each API request accepts up to 4,096 characters of input text. For longer tour scripts, you should split the text into parts of this size and join the resulting audio files. This approach allows you to generate audio for extensive tour guides while maintaining control over the generation process and file management.
Do I need technical skills to use the API?
Basic technical skills are helpful but not mandatory. The API uses a standard JSON format similar to OpenAI, so many developers can integrate it quickly. We provide a ready curl example on the dashboard. For non-technical users, you can use the API key to generate audio via simple HTTP requests or third-party tools.
How are the voices licensed for public use?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This means the underlying recordings are freely available, but our synthesis engine adds value. Each generated file carries an inaudible watermark to identify it as synthetic speech, which helps maintain transparency for your audience and compliance with licensing terms.
Can I update my tour audio easily?
Yes, you can regenerate audio anytime by sending a new request with the updated text. Since you pay per character, you only pay for the changes. You can issue a new API key at any time, stopping the old one immediately. This allows you to keep your tour content fresh without managing large static files.
Is there a free trial for new users?
Yes, signing in with Google provides a $0.50 free trial valid for 7 days. This covers approximately 50,000 characters, enough to test the service. Accounts created with email and password do not receive this trial credit. You can use the trial to evaluate voice quality and integration before topping up with USDT.
How long does audio generation take?
Generation speed is roughly real-time for long texts, producing about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under heavy load, you might experience slight delays as your request waits in the queue. Typical usage remains fast and predictable for most tours.
What formats are best for mobile apps?
We support MP3, WAV, OPUS, FLAC, and PCM formats. For mobile apps, MP3 or OPUS are often best due to their small file sizes and wide compatibility. WAV and FLAC offer higher quality but larger files. PCM is uncompressed raw audio. Choose the format that balances quality with your app’s bandwidth and storage constraints.
Do I need to credit the voice actors?
Our voices are based on LibriTTS-R recordings (CC BY 4.0) from LibriVox. The generated audio carries an inaudible watermark marking it as synthetic speech. While the source recordings are CC BY 4.0, the output is a new synthetic file rather than a direct use of the original material. We recommend crediting MuseVoice for the TTS service.
First request
curl
curl https://api.playbdkk.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 tourism teams choose synthetic audio
Museums and tourism product teams need to keep content accurate and engaging across multiple languages without the overhead of traditional recording studios. Synthetic audio allows you to update exhibit descriptions or tour scripts quickly and consistently, ensuring your visitors always hear the latest information.
Cost-effective multilingual updates
Pricing is straightforward: $0.01 per 1,000 characters, with no monthly subscriptions or minimum spend. You only pay for the characters you generate, and failed requests are free. This model lets you expand your audio catalog across 23 languages without significant budget increases.
- Pay only for characters used
- No monthly subscriptions or seats
- Failed requests are free
Instant content localization
Update tour content in real time. Whether you need to add a new exhibit description in Japanese or translate a safety notice into Arabic, you can generate the audio immediately. Each voice supports all 23 languages, so you don’t need to manage separate voice talent for each region.
No studio booking delays
Short phrases generate in seconds, and longer texts process at roughly real-time speed. You aren’t waiting for studio availability or actor schedules. If your tour route changes, you can regenerate the audio guide within minutes and deploy it directly to your users.
8 Licensed Voices for Every Tone
MuseVoice provides eight licensed voices, all derived from LibriTTS-R recordings, ensuring high-quality synthetic speech for your heritage content. Each voice is designed for specific tones, allowing you to match the audio exactly to your exhibit or tour context.
All voices support 23 languages, enabling consistent character across multilingual guides without hiring multiple actors. Every generated file includes an inaudible watermark to clearly mark synthetic speech.
Warm narrators for history
Aria delivers a warm, clear narration perfect for exhibit descriptions. Her tone brings historical narratives to life with clarity.
Luna offers a soft, storytelling quality ideal for longer historical narratives. She guides visitors through deep dives with a gentle, engaging presence.
- Aria: warm, clear narrator
- Luna: soft, storytelling
Energetic voices for promotions
Felix brings an energetic tone perfect for promotional materials and quick updates. His voice captures attention in time-limited offers.
Milo provides a friendly, conversational tone for general information. He feels like a helpful companion rather than a formal guide.
- Felix: energetic, promo
- Milo: friendly, conversational
Calm guides for museums
Sage offers a calm, instructional tone, ideal for complex museum layouts or detailed instructions. Nova provides a bright, upbeat presence for welcoming areas.
Atlas remains neutral and news-like for factual updates, while Orion delivers a deep, documentary style for immersive experiences.
- Sage: calm, instructional
- Nova: bright, upbeat
- Atlas: neutral, news
- Orion: deep, documentary

Support for 23 Languages
MuseVoice supports 23 specific languages, enabling tourism teams to reach diverse audiences without hiring local voice actors for every market. Our API accepts an optional ISO language code to ensure accurate pronunciation, especially for non-English Latin text, preventing the system from defaulting to English.
Whether you are creating content for global city tours or specialized heritage sites, you can select the appropriate language setting for each request. This ensures consistent delivery across your entire portfolio of audio guides.
Arabic and Hindi for global tours
Support for Arabic and Hindi allows you to serve major international tourist demographics effectively. The API handles these scripts accurately when the language parameter is specified, ensuring clear deliverables for visitors from the Middle East and South Asia.
European languages for heritage sites
We cover all major European markets, including German, French, Spanish, Italian, and Dutch. This range supports heritage sites that cater to both domestic visitors and the broader European travel circuit, ensuring professional-grade audio for historical narratives.
Asian languages for travel guides
For the Asian market, we support Chinese, Japanese, Korean, and Malay. Note that we specifically support 'Chinese' rather than distinguishing specific dialects, ensuring broad compatibility for travel guides targeting Mandarin speakers and other regional audiences.
How the API Works
Our API processes text inputs and returns audio files via a standard POST request. You send your script, and we return the synthesized speech in your chosen format, ready for integration into your museum tours or travel guides.
The interface mirrors the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply updating the base URL to https://api.playbdkk.com/v1. This compatibility ensures a smooth transition for existing teams without requiring complex custom integrations.
Send text, receive audio
Send a POST request to /v1/audio/speech with your text (up to 4096 characters) and selected voice. The API returns the generated audio file directly in the response. If synthesis fails, you are not charged.
For longer tour scripts, split your text into chunks under the character limit and join the resulting audio files. Processing is sequential, so queue times may apply during high load.
- Supports MP3, WAV, OPUS, FLAC, and PCM formats
- Speed adjustable from 0.25x to 4.0x
- Automatic language detection or explicit ISO code setting
OpenAI SDK compatible
Use your preferred OpenAI SDK client by changing the base URL to https://api.playbdkk.com/v1 and providing your MuseVoice API key. This ensures consistent request shapes and familiar authentication patterns.
Authenticity is maintained via Bearer tokens. One active key per account simplifies management across different tour applications or museum zones.
Simple JSON integration
The request body uses standard JSON fields: model, input, voice, response_format, and optional language. This structure works seamlessly with most HTTP libraries and SDKs.
Include your API key in the Authorization header as 'Bearer tts-...'. The system handles the rest, returning raw audio or base64 encoded data depending on your preference.
Free Trial and Pricing
Start generating multilingual audioguide content immediately with a $0.50 free trial credit, valid for seven days when you sign in with Google. This allows your team to test voice quality and integration without upfront commitment.
$0.50 free trial credit
Sign up with Google to receive $0.50 in credit, covering approximately 50,000 characters. This trial is valid for seven days. If you create an account using only email and password, you start without this trial credit.
- Valid for 7 days
- Approx. 50,000 characters
- Instant access with Google sign-in
Pay only for characters used
The standard rate is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, with the charge returned in full if synthesis fails.
No monthly subscriptions
There are no monthly plans, seats, or minimum spends. Balance does not expire. Top-ups are accepted via USDT on the TRON network (TRC-20), with a minimum of $5. Credits are added automatically within minutes of transfer.
- No monthly subscriptions
- No minimum spend
- Balance never expires

Audio Quality and Format
Generate high-quality audio files tailored to your tour’s distribution needs. The API supports MP3, WAV, OPUS, FLAC, and PCM formats, allowing you to balance file size and fidelity for web players, mobile apps, or offline devices.
MP3, WAV, OPUS, FLAC options
Choose the format that best fits your infrastructure. MP3 offers compact size for streaming, while WAV and FLAC provide lossless quality for archival. OPUS and PCM are available for specialized use cases.
- MP3 for efficient web delivery
- WAV and FLAC for lossless fidelity
- OPUS and PCM for specialized needs
Inaudible synthetic watermark
Every generated file includes an inaudible watermark marking it as synthetic speech. This provides clear attribution without affecting the listening experience, ensuring transparency for your museum or tourism audience.
Consistent voice across tours
Maintain a unified brand voice across all your locations. Select one of eight licensed presets, such as Aria for warm history or Felix for energetic promos, and apply it consistently to all generated content.
Use Cases in Tourism
Museums and tourism teams use our API to generate professional, multilingual audioguides and audio content without hiring voice actors. Our synthetic speech in 23 languages is designed for the specific constraints of heritage and travel experiences, ensuring consistent voice quality across tours.
Museum exhibit descriptions
Generate clear, calm narrations for static displays. Use "sage" for instructional content or "aria" for warm historical context. Each request processes sequentially, allowing you to batch descriptions for entire halls while maintaining consistent audio quality.
- Support for 23 languages including Arabic, Hindi, and European heritage languages
- Up to 4096 characters per request for detailed exhibit texts
- Inaudible watermark marks synthetic speech for easy identification
Audio walking tours
Create engaging routes with "nova" for upbeat energy or "atlas" for neutral news-style updates. Split longer texts into parts under 4096 characters and join the audio files seamlessly. Requests are processed one after another, so under load a request may wait in a queue.
- Speed adjustable from 0.25 to 4.0 for different walking paces
- Formats like MP3 and OPUS optimize file size for mobile apps
- No need to book studio time for route updates
Hotel room information guides
Provide multilingual instructions for amenities using "milo" for a friendly, conversational tone. Generate short, clear clips for Wi-Fi, dining, or checkout details. The API delivers licensed, watermark-safe synthetic speech, ensuring professional quality without recurring actor fees.
- Instant localization into 23 languages for international guests
- Pay only for characters used, starting at $0.01 per 1,000 characters
- No monthly subscriptions or minimum spend required
Data Privacy and Licensing
MuseVoice prioritizes transparency in how your content is handled. Your input text is used exclusively for the immediate production of the audio file and is not repurposed for training other models. This ensures that your specific tour scripts and exhibit descriptions remain private to your generation workflow.
Text not used for training
When you send text to our API, it is processed solely to generate the requested audio file. Once the audio is created and returned, that specific text input is not retained for model improvement or used to train future versions of our voices. This keeps your proprietary content distinct from our general dataset.
LibriTTS-R licensed voices
Our eight voice presets are built upon the LibriTTS-R dataset, which is licensed under CC BY 4.0. These voices originate from public-domain audiobook readings available on LibriVox. By using these licensed recordings as the foundation, we provide you with high-quality, legally clear synthetic speech suitable for commercial museum and tourism applications.
No data storage after generation
The generated audio file is returned directly in the API response and is not stored on our servers after delivery. However, please note that request metadata—including timestamp, character count, and status—is retained for a limited period specifically for billing and usage verification purposes.

Get Started Today
Create your account on playbdkk.com using your Google credentials to access the MuseVoice dashboard instantly. This quick setup grants you immediate access to the API key management interface, allowing tourism teams to start integrating synthetic audio into their product workflows without administrative delays.
Your account is created specifically for this site, ensuring secure and isolated management of your usage metrics and billing data.
Sign up with Google
Click the sign-in button on the /get-api-key/ page and authorize with your existing Google account. This method is the fastest way to create a profile and is eligible for the free trial credit.
- Instant account creation
- Eligible for $0.50 trial credit
- Secure Google authentication
Get your API key instantly
Upon sign-in, your unique tts-... API key is displayed immediately on the dashboard. You can copy this key directly into your OpenAI SDK configuration by setting the base URL to https://api.playbdkk.com/v1.
- One active key per account
- Regenerate key anytime
- Works with standard HTTP clients
Try the free demo
Use your initial $0.50 trial credit to generate your first audio files. This allows you to test voice selection, language support, and format options without any upfront payment or credit card requirement.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Our audioguide transforms museum visits into immersive storytelling experiences for visitors.
23 languages
Any voice speaks any of these languages.
