Frequently asked questions
What is a museum audioguide?
A museum audioguide is an audio file delivering narration for exhibits. Our API generates these files via a simple POST request. You send text, receive an audio file, and play it on devices. It is a cloud TTS API designed for creating engaging audio content without coding, perfect for museum guides and travel videos.
Which voice is best for audioguides?
All eight voices support all 23 languages, so suitability depends on your specific exhibit tone. Choose Sage for calm, instructional narration or Luna for soft storytelling. Atlas works well for neutral updates, while Felix suits energetic promos. You can test each preset to find the best fit for your museum guide before integrating the API.
How do I split text for audioguides?
Split your script into parts of up to 4096 characters per request. Generate each part separately, then join the resulting audio files. This ensures reliable synthesis within the API limits. Longer texts are handled by concatenating these individual audio segments to create a complete audioguide track.
Can I use the API for multiple languages?
Yes, support 23 languages including English, Spanish, French, German, Chinese, and Japanese. Any voice can speak any supported language. Set the optional language parameter to ensure correct pronunciation, especially for non-English Latin-script text. Vietnamese, Thai, and Ukrainian are not supported.
How long does generation take?
Generation is roughly real-time, about 25 characters per second. Short phrases take a few seconds. Under load, requests may wait in a queue. Failed requests are free and refunded immediately. This speed is suitable for pre-recorded museum guides but not for live, real-time interaction.
Is the API suitable for live tours?
It is not ideal for live tours due to queueing delays and lack of streaming. Requests are processed sequentially, causing potential waits. For live use, pre-generate audio files and play them. The API returns static audio files, not real-time partial audio streams, making it best for pre-recorded content.
What format is best for mobile?
MP3 is the best format for mobile compatibility and small file sizes. You can also choose WAV, OPUS, FLAC, or PCM. MP3 ensures broad device support for museum audio players. Send your request with response_format set to mp3 for optimal balance of quality and size.
How do I control the voice speed?
Adjust the speed parameter between 0.25 and 4.0. Set it to 1.0 for normal pace, or lower it for clearer narration. This allows you to fine-tune the audioguide for elderly visitors or fast-paced exhibits. The API accepts this parameter in every speech request.
Can I use my own text?
Yes, you provide the input text up to 4096 characters. The API converts your specific script into speech. You retain full control over the content. Input text is used only to produce audio and is not used for training. Just send your text via the API endpoint.
How much does it cost per guide?
Cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count. A typical guide might cost a few cents. Failed requests are free. You pay only for what you generate, with no monthly plans or minimum spend required for your museum project.
Do I need a developer for this?
No, you can use the API without coding. The endpoint matches the OpenAI SDK shape, but you can also use plain HTTP or curl. Many no-code users integrate it easily. You can also generate keys and test via the dashboard without writing code.
What if the audio is too fast?
Reduce the speed parameter below 1.0. You can set it as low as 0.25 for very slow narration. This helps ensure clarity for all visitors. Adjust the speed value in your API request to match the desired pace of your museum audioguide.
How do I handle special characters?
Send your text directly in the input field. The API handles standard text input. There is no SSML support, so you cannot use custom pronunciation tags. For specific needs, you may need to spell out words phonetically in your text to ensure correct pronunciation by the voice.
Is the audio clear on low-end devices?
Yes, the generated audio files are standard formats like MP3 or WAV. These formats play clearly on almost all devices, including low-end mobile phones and museum audio players. The audio format is consistent regardless of the playback device.
Choose the Right Voice
Selecting the right voice is the first step in creating engaging museum audioguides. Our API offers eight distinct presets, each designed to match specific content tones. From warm narrators to deep documentary voices, you can tailor the audio experience to your exhibit’s atmosphere without needing complex sound engineering.
Aria for Warm Narration
Aria delivers a warm, clear narration style ideal for guiding visitors through historical narratives or artistic descriptions. Her voice feels inviting and professional, making complex stories accessible to tourists of all ages. Use Aria for main exhibit introductions where clarity and warmth are prioritized.
- Warm and clear tone
Atlas for Neutral News
Atlas provides a neutral voice suitable for informational content. His delivery is balanced and objective, perfect for factual displays, timeline overviews, or logistical instructions where emotional bias should be avoided. Atlas ensures the information remains the focus, offering a steady, reliable audio track for serious exhibits.
- Neutral, professional tone
Orion for Deep Documentary
Orion offers a deep, resonant voice reminiscent of high-quality documentaries. This preset adds gravitas and drama to historical events, archaeological findings, or cinematic tour segments. Use Orion when you want to evoke a sense of mystery or importance, enhancing the emotional impact of your content.
- Deep, documentary style
Prepare Your Text
Before sending text to the API, prepare your content to ensure smooth audio generation. Museum descriptions often exceed the single-request limit, so you must split long scripts into smaller chunks. This prevents errors and ensures every word is synthesized correctly.
Accurate formatting improves both the API’s character counting and the final listener experience. By structuring your text clearly, you avoid unexpected pauses or truncated sentences when the audio is generated.
Split Long Descriptions
The API accepts a maximum of 4096 characters per request. If your museum guide script is longer, split it into parts of up to 4096 characters each. You can then join the resulting audio files to create a continuous guide.
This split-and-join workflow is essential for large exhibits. It ensures that even extensive historical narratives fit within the technical constraints without losing quality or context.
- Split text at logical breaks (paragraphs, not mid-sentence).
- Keep each chunk under 4096 characters.
- Join audio files sequentially after generation.
Check Character Limits
Each request counts spaces and punctuation as characters. A 4096-character limit means roughly 100-150 words per request, depending on length. Exceeding this limit will cause the request to fail.
Plan your script density carefully. Short, concise descriptions fit easily into one request, while longer historical details may require careful segmentation to stay within the limit.
- Count characters including spaces and punctuation.
- Target ~100-150 words per request.
- Test with a sample chunk first.
Format for Clarity
Use simple punctuation to guide the voice engine. Avoid complex symbols or markdown that might confuse the TTS model. Clear sentences with standard commas and periods help the AI pause naturally.
Remove unnecessary line breaks or special characters. Clean, plain text ensures the voice sounds natural and professional, which is critical for engaging museum visitors without distracting audio artifacts.
- Use standard punctuation (.,;?).
- Avoid markdown or HTML tags.
- Keep sentences short and clear.

Select the Language
Selecting the correct language ensures your museum audioguide sounds natural to the intended audience. While the API attempts to guess the language from Latin script text (defaulting to English), explicit configuration is often necessary for non-English content.
Use ISO Codes
Always provide the language field in your request using standard ISO codes (e.g., de for German, fr for French). This overrides automatic detection and guarantees the voice model applies the correct phonetic rules for that specific language.
- Supported languages include 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 speak any of these 23 languages.
Auto-Detection Limits
If you omit the language parameter, the system guesses based on the text script. For non-English Latin-script text, this default guess is English, which may result in an accent if not specified correctly.
Multi-Language Support
You can generate audio for any supported language without switching models. Since all voices can speak all supported languages, you can maintain a consistent vocal identity across different language versions of your museum tour.
Generate the Audio
Generating the audio file is a straightforward process: you send your prepared text to the API endpoint and receive an audio file in return. The API accepts JSON bodies with fields like model, input, voice, and response_format.
For museum guides, you can send texts up to 4096 characters per request. Longer descriptions should be split into parts, and the resulting audio files can be joined for a continuous tour experience.
Send POST Request
To generate voice over, send a POST request to https://api.playabc77.com/v1/audio/speech. Include your Authorization: Bearer key and specify the model (tts-1 or tts-1-hd), input text, voice preset, and desired response_format (mp3, wav, opus, flac, or pcm).
- Endpoint: POST https://api.playabc77.com/v1/audio/speech
- Auth: Authorization: Bearer tts-...
- Body: JSON with model, input, voice, format
Receive Audio File
The API returns the generated audio file directly in the response body. You can save this file locally or play it in your museum app or website. The file format matches your response_format selection, such as MP3 for web compatibility or WAV for high quality.
Handle Response
Check the HTTP status code to confirm success (200 OK) or identify errors. Failed requests are free, so if synthesis fails, the charge is returned in full. Use the response data to update your tour guide's audio queue or display error messages to users.
- Status 200: Success, audio file included
- Status 4xx/5xx: Error, check message
- Failed requests are free
Optimize for Tourists
Tourists often listen while walking, so clear audio is essential. Adjusting the speed ensures the narration matches the listener’s pace, preventing them from getting lost in fast-paced descriptions or bored by slow delivery.
Choosing the right format and testing on actual devices guarantees a smooth experience for visitors using their own smartphones.
Adjust Speed Settings
You can adjust the speech rate between 0.25 and 4.0. For museum audioguides, a slight increase might help keep up with moving crowds, while a slower speed aids comprehension for non-native speakers.
- Standard speed (1.0) works well for most static exhibits.
- Increase speed to 1.2–1.5 for fast-moving tours.
- Reduce speed for complex historical details.
Choose MP3 Format
MP3 is the most compatible format for web players and mobile devices. It offers a good balance between file size and audio quality, ensuring quick loading times for tourists with varying data connections.
- MP3: Best for web embedding and mobile apps.
- WAV/FLAC: Higher quality, but larger files.
- OPUS: Efficient compression.
Test on Devices
Always test your generated audio on smartphones and tablets. Check clarity on small speakers and ensure the volume is audible in noisy museum environments without distortion.
- Test on iOS and Android devices.
- Check audio clarity in noisy environments.
- Verify playback speed matches listener expectations.
Integrate with Your Site
Integrating Audioguide Voice into your museum or travel website is straightforward. You can embed audio players directly using standard HTML5 tags or link to the generated files via our API endpoint. For developers, the API follows the same request shape as OpenAI, making integration simple.
Embed Audio Players
Use standard HTML5 <audio> elements to play your generated MP3 files. Since the API returns direct audio files, you can host them on your server or a CDN. This ensures smooth playback for tourists browsing your site without needing custom JavaScript players.
- Use HTML5
<audio>tags for compatibility - Host files on your preferred CDN
- Ensure MP3 format for broad device support
Link to API Endpoint
Send text to POST https://api.playabc77.com/v1/audio/speech with your JSON body. The endpoint returns the audio file directly in the response. You can then store or stream this file to your users. Remember to include your Authorization: Bearer tts-... key in the header.
- Base URL:
https://api.playabc77.com/v1 - Endpoint:
POST /v1/audio/speech - Include Bearer token in headers
Use OpenAI SDK
The API is compatible with the official OpenAI SDKs. Simply change the base_url to https://api.playabc77.com/v1 and use your site's key. This allows you to use familiar code structures for generating speech. It supports both tts-1 and tts-1-hd models seamlessly.
- Change
base_urlto our API - Use standard OpenAI SDK methods
- Supports
tts-1andtts-1-hdmodels
Manage Costs
Audio guides can consume surprising amounts of credit, especially for detailed historical tours. Understanding your text length helps prevent unexpected charges and keeps your project budget predictable.
Estimate Character Count
Every space, punctuation mark, and letter counts toward your 4096-character limit per request. At $0.01 per 1,000 characters, a 500-word guide uses roughly $0.25. Track your usage to stay within limits.
- Count all spaces and punctuation as characters.
- Split long texts into 4096-character chunks.
- Failed requests refund the full amount.
Use Free Trial First
Sign in with Google to receive $0.50 in trial credit, valid for 7 days. This covers about 50,000 characters, enough to test multiple voices and formats before committing to a top-up.
- Google sign-in grants $0.50 trial credit.
- Email/password accounts start without trial credit.
- Trial credit expires after 7 days.
Top Up with USDT
Add funds via USDT on the TRON network (TRC-20). Minimum top-up is $5, and balances are credited automatically within minutes. There are no monthly plans or subscription fees.
- Accepts USDT (TRC-20) only.
- Minimum top-up is $5.
- No invoices or VAT included.

Quality Assurance
Before deploying audioguide content, listen closely to the generated audio to ensure the narration flows naturally for museum visitors. Check that the voice tone matches the exhibit’s atmosphere, whether it is a warm historical tour or a neutral informational guide.
Every audio file includes an inaudible watermark confirming it is synthetic speech, which helps identify AI-generated content without affecting the listening experience. This ensures transparency while maintaining a professional audio quality.
Listen for Clarity
Play the generated MP3 or WAV file on typical tourist devices like smartphones or tablet speakers. Ensure the audio is crisp and free of artifacts, especially at normal speed settings.
Verify that the pacing feels natural for listening while walking. If the speech sounds too fast or robotic, adjust the speed parameter between 0.25 and 4.0 to find the optimal balance.
- Test audio on common mobile devices
- Adjust speed for natural walking pace
- Check for audio artifacts in MP3/WAV
Check Watermarks
While the watermark is inaudible, it serves as a marker that the content is AI-generated synthetic speech. This is standard for all outputs from the API.
No visual watermarks appear in the audio files, keeping the experience immersive for museum visitors who are unaware of the technology behind the voice.
Verify Language Accuracy
Confirm that the generated speech matches the intended language. If the language field is not set, the system guesses based on the script, which may default to English for Latin text.
For non-English Latin-script text, explicitly set the language parameter to avoid incorrect pronunciation. Test with native speakers to ensure accuracy for languages like German, Spanish, or Japanese.
- Explicitly set language codes
- Test with native speakers
- Avoid default English guessing
Common Pitfalls
Museum audioguides often fail when language detection assumes English for Latin-script texts like French or German. Always explicitly set the language ISO code to ensure correct pronunciation and avoid awkward accents that break immersion for visitors.
Rate limits and text size are common hurdles. Sending too many requests at once triggers a 60-per-minute cap, while large single inputs may exceed the 4,096-character limit, causing synthesis errors or truncated audio.
Ignoring Language Tags
The API guesses the language from the script if you omit the language field. For non-English Latin text, this default assumption often results in an English voice pronouncing foreign words incorrectly. Always specify the ISO code to guarantee accurate delivery.
Exceeding Rate Limits
New accounts start with a low limit of 10 requests per minute. Hitting this cap pauses your generation queue. Monitor your usage dashboard to adjust batch sizes accordingly, ensuring smooth production for large museum collections.
Large Single Requests
Each request supports up to 4,096 characters. Sending a full museum exhibit description in one go may fail or truncate. Split long texts into smaller segments and join the resulting audio files for seamless playback.
Advanced Features
Beyond basic generation, Audioguide Voice offers precise control over audio characteristics and delivery formats to suit diverse museum contexts. These advanced options allow you to fine-tune the listening experience without requiring external processing tools.
You can adjust playback speed, select from multiple audio formats, and manage multiple requests efficiently. These features ensure your audioguide content is optimized for both clarity and compatibility across various devices.
Speed Adjustment
You can set the speech speed between 0.25 and 4.0. This allows you to slow down complex historical descriptions for better comprehension or speed up brief directional hints.
The API accepts a speed parameter in your request. Values below 1.0 slow the voice, while values above 1.0 accelerate it, maintaining the original voice character.
- Range: 0.25 to 4.0
- Adjusts playback rate only, not pitch
- Useful for non-native speakers or elderly visitors
Multiple Formats
Choose between mp3, wav, opus, flac, or pcm formats. MP3 is ideal for web embedding due to its small file size, while WAV and FLAC offer lossless quality for high-end audio systems.
The response_format field in your POST request determines the output file type. Select the format that best matches your museum’s existing infrastructure or distribution method.
- MP3: Small size, universal support
- WAV/FLAC: Lossless quality for premium devices
- OPUS: Efficient for streaming
Batch Processing
Send multiple texts in sequence to generate several audio files. Since requests are processed one after another, long texts are split into 4096-character parts and joined automatically.
Use the input field with up to 4096 characters per request. For longer content, split your text into chunks and combine the resulting audio files using standard tools.
Rate limits apply: 60 requests per minute per key. Plan your batch sizes accordingly to avoid delays, especially during peak usage.
- Max 4096 characters per request
- Manual splitting for long texts
- Rate limit: 60 requests/minute
Support and Contact
We support you primarily through email. For any questions about your Audioguide Voice account, billing, or API usage, please reach out to our team. We do not offer phone lines or live chat, so email is your most reliable channel for assistance.
While we don't provide real-time status pages or SLAs, our documentation covers most common integration scenarios. You can also verify your API key status directly from your dashboard to ensure your requests are authorized.
Email Support
For all inquiries, send an email to our support team. We aim to respond promptly to help you resolve any issues with your museum audio content generation.
Documentation Links
Refer to our comprehensive docs for API endpoint details, voice lists, and pricing models. The documentation is updated regularly to reflect current capabilities and limits.
You can also find ready-to-use cURL examples and SDK configurations directly in the docs to speed up your integration process.
- API Reference
- Voice Presets
- Pricing Model
API Status
We do not maintain a public uptime dashboard. You can verify your account's active status and key validity via the dashboard.
If requests fail, check your balance and rate limits (60 req/min) to ensure your account is in good standing.

Next Steps
Getting started with Audioguide Voice is straightforward. Create your account on the /get-api-key/ page to receive your unique API key and $0.50 trial credit. This allows you to test the service immediately without a credit card.
Generate your first audio clip by sending a POST request to the speech endpoint. Use the OpenAI SDK for ease of integration or plain HTTP for simplicity. Your audio file is returned instantly, ready for your museum guide.
As you scale, monitor your character usage and top up with USDT on the TRON network when needed. The system handles rate limits automatically, ensuring your tourist content remains available during peak hours without interruption.
Create Your Account
Sign up via Google or email on the get-api-key page. You will receive a single active API key and $0.50 in trial credit valid for seven days.
No minimum spend or monthly plans are required. Your balance does not expire, allowing you to start small and grow as your museum exhibits expand.
- Use Google or email for quick setup
- Receive $0.50 trial credit automatically
- No credit card required for initial access
Generate Your First Clip
Send a POST request to the speech endpoint with your text, chosen voice, and language code. The API returns an audio file in your preferred format, such as MP3 or WAV.
Test the output on various devices to ensure clarity. The generated audio includes an inaudible watermark to identify it as synthetic speech.
- Use the /v1/audio/speech endpoint
- Choose from 8 realistic voices
- Receive audio in MP3, WAV, OPUS, FLAC, or PCM
Scale Your Content
Top up your account with USDT on the TRON network for larger projects. Credits are added automatically within minutes, allowing continuous generation without downtime.
Monitor your usage through the dashboard to stay within your budget. With $10 per million characters, you can affordably produce extensive guide content for multiple exhibits.
- Top up with USDT (TRC-20)
- Minimum $5 top-up amount
- Balance never expires
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your audioguide turns every museum visit into a memorable, easy-to-create experience for all visitors.
23 languages
Any voice speaks any of these languages.
