Frequently asked questions
What is a narrator voice generator?
It is a cloud API that converts text into audio files via a POST request. You send text, and receive synthesized speech using professional voices like Aria or Atlas. This tool allows tourism agencies to generate consistent narration for audioguides and video tours without hiring human voice talent for every project.
Can I use the same voice for multiple languages?
Yes. Every voice in our library can speak any of our 23 supported languages, including English, Spanish, French, German, and Japanese. You simply specify the ISO language code in the request. If omitted, the system guesses the language, defaulting to English for Latin script text.
Which voice is best for museum exhibits?
Atlas offers a neutral, news-style tone ideal for factual exhibit descriptions. Sage provides a calm, instructional voice suitable for guided tours. For a warmer, narrative approach to storytelling within exhibits, Aria is an excellent choice. All voices are based on licensed recordings and deliver consistent quality.
How accurate is the pronunciation in non-English languages?
Our voices support 23 languages, including Arabic, Chinese, Hindi, and Korean. Pronunciation is accurate as the voices are based on recordings in these languages. We recommend setting the language parameter explicitly for non-English Latin text to ensure correct interpretation, as the system defaults to English for Latin scripts otherwise.
Do I need to provide a script for each request?
Yes. Each API call requires an input field containing the text to be spoken, up to 4096 characters. You send the script directly in the JSON body. For longer scripts, you split them into parts, generate audio for each, and join the resulting audio files.
Can I change the speed of the narration?
Yes. You can adjust the speed parameter between 0.25 and 4.0. This allows you to slow down complex historical details or speed up simple signposts. The default speed is 1.0. Adjusting speed helps tailor the pacing of your audioguide to the specific context of your tour.
What audio formats are supported for tours?
We support mp3, wav, opus, flac, and pcm formats. MP3 is ideal for web-based tours due to its small file size. WAV offers high quality for local playback. FLAC provides lossless compression. Choose the format that best fits your distribution channel, whether it is a mobile app or website.
Is the generated speech watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify the content as AI-generated without affecting the listening experience. The watermark is embedded directly into the audio file upon generation and remains present in all supported output formats.
How do I handle long audioguide scripts?
Split your script into parts of up to 4096 characters per request. Generate audio for each part individually using the API. Then, join the resulting audio files to create a continuous narration. This ensures each request stays within limits while allowing you to produce long-form content efficiently.
Can I use the audio for commercial projects?
Yes. You pay per character used, with no restrictions on commercial usage. Generated audio is not stored by us, so you retain full control. There are no monthly plans or seat limits. You simply top up your balance via USDT (TRC-20) and generate as much content as needed.
Do you offer voice cloning for museum directors?
No. We do not offer custom voice cloning or uploading of your own voice. Our library consists of eight preset voices based on licensed recordings. These include options like Felix for energetic promos or Orion for deep documentaries, but you cannot create a custom clone of a specific person.
What happens if the API is slow during peak times?
Requests are processed one after another. Under load, a request may wait in a queue. Typical speed is roughly real-time on long texts, but short phrases take a few seconds. During high traffic, generation times may increase slightly as requests are sequenced through the processing pipeline.
Is there a limit to how many characters I can process?
Yes. Each API request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer scripts, you must split the text into multiple requests, generate audio for each segment, and then join the resulting audio files to create the final narration.
How do I contact support if I have an issue?
Support is available by email only. There is no phone number or live chat. You can reach us via the contact page or through your account dashboard. We do not offer an SLA or uptime guarantee, but we are available to assist with technical or billing questions.
First request
curl
curl https://api.play2288.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 Voisite for Tourism?
Tourism and museum projects demand narrative consistency across dozens of exhibits. Voisite provides a reliable text-to-speech API that ensures your audioguides and video tours maintain a uniform, professional voice identity without the logistical overhead of re-hiring talent for every new script.
Consistent Narrator Identity
Whether you are producing audio for a city walking tour or a museum exhibit, consistency builds trust with visitors. Our API allows you to lock a single voice preset across all your content, ensuring that your brand’s narrative voice remains recognizable from the entrance to the final display.
- Lock one voice for all exhibit scripts
- Uniform tone across multiple audio guide devices
- No re-recording needed for minor text updates
Multilingual Audioguides Made Easy
Expand your reach without managing international voice actors. Our API supports 23 languages, allowing you to generate accurate narration in English, Spanish, French, Chinese, Japanese, and others. Any voice preset can speak any supported language, simplifying the production of global tour content.
- Support for 23 languages including Hindi and Turkish
- Automatic language detection or explicit ISO code setting
- Consistent voice style across different language tracks
Cost-Effective Video Voiceovers
Scale your audio content from audioguides to video tours efficiently. At $0.01 per 1,000 characters, you can produce high-volume narration without monthly fees or minimum spends. Failed requests are free, ensuring you only pay for successful audio generation.
- Pay only for successful character counts
- No monthly subscription or seat limits
- Transparent billing via USDT (TRC-20)
Our Voice Presets for Narrators
Voisite offers eight distinct voice presets designed to match the specific tone of your museum exhibits or tourism content. Each voice is derived from licensed recordings, ensuring high-quality narration without the logistical overhead of hiring multiple voice actors for every project.
Sage: The Calm Instructor
Sage delivers a calm, instructional tone ideal for educational tours. His steady pace helps visitors absorb complex historical details without distraction, making him perfect for detailed exhibit descriptions or directional guidance.
- Tone: Calm and instructional
Aria: The Warm Storyteller
Aria provides a warm, clear narrator voice that brings history to life. Her engaging delivery is perfect for narrative-driven tours where emotional connection enhances the visitor experience, such as personal stories from the past.
- Tone: Warm and clear
Atlas: The Neutral News Anchor
Atlas offers a neutral, authoritative voice suitable for factual presentations. His consistent delivery ensures clarity and professionalism, making him an excellent choice for news-style updates or formal exhibition introductions where neutrality is key.
- Tone: Neutral and authoritative
Supported Languages for Global Tours
Voisite supports 23 languages, allowing tourism agencies to produce consistent audio guides across diverse visitor demographics. Whether your audience speaks English, Spanish, or Arabic, our single API endpoint handles the narration, ensuring a unified brand voice for your museum or tour.
English and European Languages
We cover the core European markets with high-fidelity narration. Supported languages include English, French, German, Italian, Spanish, Portuguese, Dutch, Swedish, Norwegian, Danish, Finnish, Polish, Russian, Greek, and Turkish.
- English, French, German, Italian, Spanish, Portuguese
- Dutch, Swedish, Norwegian, Danish, Finnish
- Polish, Russian, Greek, Turkish
Asian Languages: Chinese, Japanese, Korean
Accommodate East Asian tourists with precise phonetic rendering. Our API supports Mandarin Chinese, Japanese, and Korean, ensuring that complex characters and tonal nuances are handled correctly without requiring separate voice talent for each market.
- Chinese (Mandarin)
- Japanese
- Korean
Emerging Markets: Hindi, Turkish, Swahili
Expand your reach into growing tourism sectors. We support Hindi, Swahili, and Arabic, allowing museums in global hubs to offer inclusive audio experiences. Note that languages like Vietnamese, Indonesian, and Thai are not yet supported.
- Hindi
- Swahili
- Arabic
- Hebrew
Technical Simplicity for Agencies
Agencies can integrate Voisite into their existing workflows using familiar tools. Our API mirrors the standard OpenAI speech endpoint structure, meaning you can use official OpenAI SDKs by simply adjusting the base URL to https://api.play2288.com/v1. This compatibility reduces development time for engineering teams already comfortable with standard TTS implementations.
We deliver audio in formats like MP3, WAV, OPUS, FLAC, and PCM. The JSON-based request structure accepts text input and returns audio files directly, eliminating the need for complex middleware or custom parsing logic in your deployment pipeline.
OpenAI SDK Compatible
You can leverage existing OpenAI SDKs by pointing them to our API base URL. This ensures consistent behavior for authentication and request handling without requiring you to build a custom client from scratch.
- Use standard OpenAI SDKs with modified base_url
Standard Audio Formats (MP3, WAV, OPUS)
Choose from MP3, WAV, OPUS, FLAC, or PCM based on your storage and bandwidth needs. MP3 offers efficient compression for web delivery, while WAV provides lossless quality for high-end audio guide hardware.
Simple JSON API Integration
Send a POST request with your text and voice selection in a standard JSON body. The API returns the audio file directly, allowing for straightforward integration into your content management or tour booking systems.
- Standard JSON request body
Pricing for High-Volume Narration
Voisite charges $0.01 per 1,000 characters, making it ideal for scaling museum audio guides without fixed overhead. Spaces and punctuation count toward the total, so you can accurately estimate costs based on your script length. Failed requests are free, ensuring you only pay for successful audio generation.
Pay Per Character
Our pricing model aligns directly with content volume. At $10 per million characters, long-form audioguide scripts remain cost-effective. You can split texts into 4,096-character chunks to manage generation time while keeping billing simple.
- Rate: $0.01 per 1,000 characters
No Monthly Fees
There are no subscriptions, seats, or minimum spends. You only pay for what you use. This structure allows tourism agencies to test new tour routes or languages without committing to a recurring budget. Balance never expires, so unused credits remain available for future projects.
Transparent USDT Payments
We accept USDT on the TRON network (TRC-20) for top-ups. Transfers are credited automatically within minutes, with a minimum deposit of $5. There are no invoices, VAT, or hidden processing fees. Support is available via email for any billing questions.
- Network: TRON (TRC-20)

Use Cases for Museums and Tourism
Voisite transforms static exhibits into engaging auditory experiences. By converting your museum scripts into high-quality audio files, you eliminate the logistical cost of hiring voice talent for every new tour or language version. This ensures a consistent narrator identity across all your content, from introductory films to detailed exhibit descriptions.
Audio Guide Scripts
Generate multilingual audioguides efficiently using our 23 supported languages. Whether you need English, German, or Japanese narration, the same text can be converted into distinct voice presets like Sage or Aria. Each request handles up to 4096 characters, allowing you to batch long tour routes into single audio files or split them for precise user control.
- Support for 23 languages including Spanish, French, and Chinese.
- Consistent voice identity across entire tour routes.
- No minimum spend for small museum collections.
Exhibition Video Narration
Produce professional voiceovers for promotional videos and exhibition trailers without studio booking delays. Use voices like Atlas for neutral news-style updates or Luna for soft storytelling. The API returns standard formats like MP3 or WAV, ready for immediate integration into your video editing pipeline or web players.
- Output formats: MP3, WAV, OPUS, FLAC, PCM.
- Speed adjustable from 0.25x to 4.0x for pacing control.
- No SSML or phoneme dictionaries needed for basic scripts.
Interactive Kiosk Content
Deploy dynamic audio for interactive kiosks where text length varies. Since failed requests are free, you can test different voice presets like Felix or Orion without risk. Each generated file includes an inaudible synthetic watermark, ensuring authenticity while keeping your input data private and unused for training.
- Generation takes roughly real-time for long texts; short phrases take a few seconds.
- Pay only for successful synthesis (60 req/min limit).
- Input text is not used for model training.
Quality and Authenticity
Voisite’s synthetic voices are grounded in real, licensed source material, ensuring a natural and authentic listening experience for your museum visitors and tour participants. Voices are based on licensed recordings: LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings.
Licensed Voice Recordings
Our eight voice presets—such as Sage, Aria, and Atlas—are derived from licensed recordings, including LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This foundation ensures consistent, professional-grade narration that sounds human without requiring expensive voice talent hires for every new exhibit.
Synthetic Watermarking
Every audio file generated by Voisite contains an inaudible watermark that marks the content as synthetic speech. This subtle digital signature helps identify the audio as AI-generated while maintaining high perceptual quality for end-users.
No Training on Your Data
When you send text for synthesis, we use it solely to produce the audio file. Your input text is not used to train or improve our voice models. Once the audio is returned in the response, it is not stored, ensuring your exhibition scripts remain private and secure.
Getting Started with Voisite
Start by creating an account on our /get-api-key/ page. You can sign in with Google or use your email and password. Once registered, your API key is displayed immediately, along with your current balance and a ready-to-use cURL example for quick testing.
New Google sign-ups receive a $0.50 free trial, valid for 7 days. This provides about 50,000 characters to test voice quality and integration without any commitment. Accounts created with email and password start without this trial credit.
Sign Up and Get Your Key
Visit the /get-api-key/ page to register. Choose Google authentication or standard email/password signup. Your unique API key appears instantly in your dashboard, ready for immediate use in your tourism applications.
- Immediate key generation
- Google or email signup
- Dashboard with key, balance, trial, characters left, usage and a ready curl example
Try the Free Trial
Google sign-ups start with $0.50 credit, covering roughly 50,000 characters. This allows you to test voice presets and audio formats before purchasing. The trial expires after 7 days if unused.
View the Documentation
Check the /docs/ page for detailed integration guides. Learn how to adjust speed, select voices, and choose audio formats like MP3 or WAV. The API follows the OpenAI speech endpoint structure, making it easy for developers to adapt existing code.
Frequently Asked Questions
Voisite simplifies audio production for tourism agencies by removing the logistical friction of studio bookings. You receive consistent, high-quality narration files ready for integration into your tours, audioguides, or marketing videos without hiring voice talent for every new script.
Our API is designed for scale, allowing you to generate hours of content quickly. Whether you are producing a single museum exhibit or a global tour series, Voisite ensures your brand voice remains uniform across all languages and formats.
Common Technical Questions
Voisite uses a standard JSON API compatible with the OpenAI SDK. You simply change the base URL to https://api.play2288.com/v1 and use your API key. There is no need for a custom SDK or complex setup.
We support MP3, WAV, OPUS, FLAC, and PCM formats. Text is limited to 4096 characters per request; for longer scripts, split the text and join the resulting audio files. Speech speed ranges from 0.25x to 4.0x.
- Rate limit: 60 requests/minute (10/min initially)
- Max input: 4096 characters per request
- No streaming or SSML support
Voice Selection Tips
For museum guides, 'sage' offers a calm, instructional tone ideal for historical facts, while 'aria' provides a warm, clear narration for storytelling. 'atlas' is suitable for neutral, news-style updates in kiosks.
All voices support all 23 languages. If using Latin script for non-English languages, always set the 'language' field to ensure accurate pronunciation.
- sage: Calm, instructional (museum guides)
- aria: Warm, clear storyteller
- atlas: Neutral, news-style
Billing and Support
Pricing is $0.01 per 1,000 characters. Failed requests are free. Payments are accepted via USDT (TRC-20) only; no credit cards or subscriptions. Minimum top-up is $5.
Support is via email only. We do not offer phone support, SLAs, or live chat. Your input text is not used for training models.
- Cost: $0.01 / 1,000 chars
- Payment: USDT (TRC-20) only
- Support: Email only
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.
