Frequently asked questions
What is the best voice for legal contracts?
Atlas offers a neutral, news-style voice ideal for legal content. Sage provides a calm, instructional tone suitable for documentation. You can choose any of the eight presets, as each supports all 23 languages. Select the voice that best matches your audience’s listening preference for dense text.
How long does it take to generate audio?
Generation takes roughly real-time, about 25 characters per second of audio. Short phrases may take a few seconds. Longer texts process sequentially, so requests may queue under load. Failed requests are free.
Can I use SSML for legal formatting?
No, our API does not support SSML. You cannot use markup for pauses or emphasis. Simply send plain text. The TTS engine handles natural pacing automatically. For precise control, adjust the speed parameter between 0.25 and 4.0 to suit your legal document’s rhythm.
Do I need to split long contracts manually?
Yes, you must split texts exceeding 4096 characters per request. Send multiple requests for each part, then join the resulting audio files. This ensures compliance with the API’s input limits. Your application logic should handle the splitting and concatenation process before or after synthesis.
How do I calculate the cost of a contract?
Cost is $0.01 per 1,000 characters, including spaces and punctuation. Count all characters in your contract text. Multiply by 0.00001 to get the price. Failed requests are free, so you only pay for successful audio generation. No minimum spend or monthly fees apply.
Is the audio quality suitable for legal use?
Audio is clear and generated from licensed recordings. Each file includes an inaudible watermark marking it as synthetic. Voices like Atlas or Sage provide neutral tones. It serves well for internal reviews and accessibility.
Can I store the generated audio files?
Yes, you receive the audio file directly in the response. We do not store the generated audio; it is returned to you immediately. You can store it in your own systems. Request metadata is kept for billing purposes only, not the audio content itself.
Do you support multiple languages in one contract?
Each request supports one language specified by the language field. If unset, the script guesses the language (Latin defaults to English). To mix languages, split the contract by language, generate separate audio files, and join them. Each voice can speak any of the 23 supported languages.
How do I handle errors during generation?
Failed requests are free, and the charge is returned in full. Check the response status for errors. If a request fails, retry it. Ensure your text is under 4096 characters. Rate limits apply (60 requests/minute), so handle retries with appropriate delays to avoid hitting the cap.
Is there a limit on the number of contracts?
There is no limit on the number of contracts or requests. You are limited by your rate limit of 60 requests per minute per key. You can process as many contracts as needed, provided you stay within the per-minute quota and have sufficient balance.
Can I clone a specific lawyer's voice?
No, we do not offer custom voice cloning. You cannot upload a voice sample to create a unique preset. You must choose from the eight available presets. Each voice is based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings.
Do you provide an SLA for production?
No, we do not provide an SLA or uptime guarantee. Requests are processed sequentially, so load may cause queues. There is no enterprise contract or on-premise install option. Support is by email only. Use the API at your own risk for critical production workflows.
How do I integrate with my existing app?
Send a POST request to https://api.playvt443.com/v1/audio/speech with your Bearer token. Use the OpenAI SDK by changing the base_url. Include model, input, voice, and response_format in the JSON body. The API accepts standard formats like mp3, wav, opus, flac, and pcm.
Is the API secure for sensitive documents?
Input text is used only to produce audio and is not used for training. We do not store the generated audio. Request metadata is kept for billing. However, we do not offer specific certifications like SOC 2 or HIPAA. Assess your own security requirements for sensitive legal data.
Prepare Your Legal Text
Legal contracts often contain complex formatting that can confuse synthesis engines. Ensure your source text is plain UTF-8 to guarantee consistent pronunciation and accurate character counting for billing purposes.
Clean text format
Strip out headers, footers, and page numbers before sending text to the API. Standardize punctuation so the engine can parse sentence boundaries correctly, ensuring the audio flows naturally without awkward pauses.
- Use plain UTF-8 encoding
- Remove page numbers and headers
- Standardize punctuation marks
Remove special symbols
Eliminate non-standard symbols like smart quotes, em dashes, or special bullets that may not be recognized. These characters can disrupt the voice model, leading to garbled audio or unexpected pauses in your legal document.
- Replace smart quotes with standard quotes
- Convert em dashes to commas or periods
- Remove special bullet points
Character limit check
Each API request accepts a maximum of 4096 characters, including spaces and punctuation. Verify your text length before submission to avoid truncation, which could cut off critical legal clauses mid-sentence.
- Max 4096 characters per request
- Count all spaces and punctuation
- Check text length before API call
Choose the Right Voice
Selecting the correct voice ensures legal documents are consumed efficiently. Since legal teams often process dense text, clarity and neutrality prevent listener fatigue during long compliance reviews.
Neutral news tone
Atlas delivers a steady, neutral cadence ideal for reading contracts. Its consistent pacing helps teams digest dense clauses without distraction.
Calm instructional voice
Sage offers a clear, instructional tone perfect for explaining terms. It maintains a professional demeanor suitable for internal policy documentation.
Deep documentary style
Orion provides a deep, authoritative voice for formal disclosures. This style adds weight to critical legal notices or audit summaries.
Send Request to API
Sending your legal text to the API is a straightforward HTTP operation. You construct a JSON payload containing the text and voice settings, then submit it to the speech endpoint. The system processes the request and returns the audio file directly in the response.
This method integrates seamlessly with existing product workflows, allowing you to automate the conversion of dense contracts into listenable audio without complex middleware. The process is reliable and character-accurate, ensuring your billing reflects exactly what was processed.
Construct JSON body
Build a JSON object with the required fields: model, input, voice, and response_format. The input field holds your legal text, capped at 4096 characters. You can optionally set speed between 0.25 and 4.0, and specify a language ISO code if needed.
Choose tts-1 or tts-1-hd for the model, which share the same engine and pricing. Select a voice like atlas for neutral news tone or sage for calm instructional delivery.
model: "tts-1" or "tts-1-hd"input: your text (max 4096 chars)voice: e.g., "atlas", "sage"response_format: "mp3", "wav", or "flac"
Set authorization header
Include your API key in the Authorization header as a Bearer token. This authenticates your request and links the usage to your account balance. Ensure you use the correct key issued for your account.
The key format is tts-.... If you rotate your key, the old one stops immediately, so ensure your integration handles this transition smoothly to avoid service interruptions during deployments.
Authorization: Bearer tts-<your-key>
Submit POST request
Send a POST request to https://api.playvt443.com/v1/audio/speech with the JSON body and authorization header. Requests are processed one after another, so under load a request may wait in a queue.
Upon success, you receive the audio file directly in the response. Failed requests are free, so you can retry without penalty. This ensures you only pay for successfully generated audio, maintaining cost efficiency for your legal content library.
Handle Long Documents
Legal contracts often exceed the 4096-character limit per request. You must split the text into chunks that fit this constraint before sending them to the API.
Split into 4096 chars
Break your document into segments of up to 4096 characters each. Split the text into parts of up to 4096 characters and join the audio files.
Join audio files
After receiving audio files for each chunk, concatenate them into a single file. This ensures a continuous listening experience for your users.
Sequential processing
Requests are processed one after another. Under load, a request may wait in a queue, so plan your integration accordingly.
Select Audio Format
Choosing the right audio format ensures your legal documents play smoothly across devices while maintaining clarity for complex legal terminology. The API supports multiple formats, allowing you to optimize for either file size or fidelity based on your specific distribution needs.
MP3 for web players
MP3 is the ideal choice for embedding audio directly into web interfaces or mobile apps. Its compressed nature allows for smaller file sizes.
- Universal compatibility with all modern web browsers
- Smallest file size for efficient bandwidth usage
- Ideal for streaming in document viewer interfaces
WAV for high quality
WAV provides uncompressed audio. This format is best suited for archival purposes or when you need to ensure that no audio data is lost during playback, maintaining the integrity of the spoken legal text.
- Lossless audio quality
- No compression artifacts
- Higher file size than MP3
FLAC for archive
FLAC offers lossless compression, reducing file size while retaining full audio quality. It is perfect for long-term storage of generated legal audio files, ensuring that you save storage space without sacrificing the clarity required for precise legal review.
- Lossless compression
- Smaller than WAV, larger than MP3
- Ideal for long-term document archives
Verify Character Count
Accurate billing depends on counting every character in your legal text, including spaces and punctuation. The API charges $0.01 per 1,000 characters, so precise counting prevents unexpected costs or wasted credits.
Before sending a request, verify your text length. This ensures you have sufficient balance.
Count spaces and punctuation
Include every space, comma, and period in your character count. Legal contracts often contain dense formatting that adds up quickly.
Use standard string length functions in your code to get an accurate count before submitting to the API.
- Include spaces and punctuation
- Use standard string length functions
- Account for formatting characters
Estimate cost
Calculate the cost by dividing the total character count by 1,000 and multiplying by $0.01. This helps you budget for large contracts.
Failed requests are free, so you can test with small samples to verify your cost estimates before processing full documents.
- $0.01 per 1,000 characters
- Divide count by 1,000
- Multiply by $0.01
Check balance
Ensure your account has sufficient balance before processing long documents. You can check your current balance and characters left on the dashboard.
If your balance is low, top up using USDT on the TRON network to avoid interruptions during bulk processing.
- Check dashboard for balance
- Top up via USDT (TRC-20)
- Monitor characters left
Test with Free Trial
Start by creating your account on the /get-api-key/ page using your Google identity. This method instantly grants you a $0.50 trial credit, valid for seven days. Unlike email-only accounts, this path ensures immediate access to your first characters without delay.
With the credit active, you can generate approximately 50,000 characters of audio. This allows you to test the full workflow—from text submission to audio download—before committing to a top-up. It is the fastest way to verify the API fits your legal document pipeline.
Sign in with Google
Navigate to the /get-api-key/ page and select the Google sign-in option. This creates an independent account for playvt443.com and immediately activates your trial credit. You receive your unique API key instantly, ready to use in your first request.
- Instant key generation
- No credit card required
- 7-day validity period
Get $0.50 credit
Your trial balance starts at $0.50, which covers about 50,000 characters. Since spaces and punctuation count as characters, you have ample room to test long contracts. The balance does not expire, so you can pause testing and return later within the week.
Run sample request
Use the provided curl example on your dashboard to send a POST request to the /v1/audio/speech endpoint. Set the model to 'tts-1' and choose a voice like 'atlas' for a neutral news tone. The API returns an audio file directly, allowing you to verify quality and speed immediately.

Integrate into App
Integrating ClarityVoice into your legal product workflow is straightforward because the API mirrors the standard OpenAI speech endpoint. This allows your existing engineering teams to adopt the service without learning a new proprietary system. You simply point your existing code to our infrastructure.
By reusing the proven OpenAI SDKs, you ensure stability and ease of maintenance. This approach lets your team focus on parsing complex legal clauses rather than managing custom HTTP client logic or retry mechanisms for each new legal document type your application supports.
Use OpenAI SDK
Leverage the official OpenAI Python or JavaScript SDKs, which are already familiar to most product teams. This eliminates the need for a dedicated in-house SDK while providing robust error handling and type safety out of the box. You retain the reliability of a widely tested library.
This strategy reduces integration time significantly. Your developers can start converting dense contracts into audio files within hours, using libraries they already trust and understand from other parts of your application stack.
- - Official OpenAI SDKs work seamlessly
- - No proprietary client library needed
- - Familiar error handling patterns
Configure base URL
Update your SDK configuration to point to the ClarityVoice endpoint: https://api.playvt443.com/v1. This single change directs all synthesis requests to our infrastructure while keeping your codebase clean. Ensure you inject your unique API key into the authorization header for secure access.
This base URL structure matches the standard pattern, making it easy to swap between environments or test locally. You can store this configuration in your environment variables.
Handle responses
The API returns the audio file directly in the response body. Your application should capture this binary data and save it or stream it to the user. If the request fails, the SDK will raise an error, allowing you to log the issue without losing your API credit.
Since requests are processed sequentially, you may encounter queue delays during high load. Implement basic retry logic for transient errors, but note that failed synthesis requests are refunded automatically, so you do not need to manage complex billing reconciliation for errors.
Monitor Usage
Monitoring usage is straightforward through the dashboard, where you can view real-time character consumption and balance updates. Since billing is precise to the character, including spaces and punctuation, tracking your exact usage helps avoid unexpected pauses during bulk document processing.
The system keeps request metadata for accurate billing, so you can audit exactly how many characters were processed per document. This transparency ensures that your legal team knows precisely what they are paying for without hidden fees or ambiguous charges.
Check dashboard
The /get-api-key/ page displays your current balance, remaining trial credit, and character count. This central view updates automatically, allowing you to see exactly how much of your $10 per million character allowance has been consumed.
You can also see the status of your API key and verify that it is active. If you issue a new key, the old one stops immediately, ensuring you are always monitoring the correct credential.
- Real-time balance updates
- Active key status
- Character consumption history
Track character count
Since costs are calculated per character, including spaces, accurate counting is essential. The API counts every character in your input text, so even minor formatting changes can impact the final bill. Use the provided curl examples to test exact character counts before full deployment.
Longer contracts may split into multiple requests. Each split part counts separately, so ensure your total character count reflects all parts of the document. This prevents overestimating your available balance.
- Exact character counting
- Space and punctuation inclusion
- Split request accounting
Manage balance
Top-ups are made via USDT on the TRON network, with a minimum of $5. Once transferred, the balance is credited automatically within minutes. There are no monthly plans or subscriptions, so you only pay for what you use.
If you need more credit, simply send USDT to the provided address. The balance does not expire, so you can top up when convenient. Failed requests are free, so you won’t be charged for errors.
- USDT TRC-20 top-ups
- Automatic credit within minutes
- No expiration on balance
Handle Errors
Legal synthesis isn't always instantaneous. If a request fails, you receive no charge, but you must handle the response gracefully to maintain your application's reliability.
Proactive error handling prevents wasted time and ensures your legal documents are delivered without unexpected interruptions during critical review periods.
Retry on failure
Failed requests are free, so you can safely retry without incurring double costs. Implement exponential backoff to handle transient network issues or brief server overloads.
Since requests are processed sequentially under load, a simple retry loop ensures your document eventually synthesizes without manual intervention.
- Retry on 5xx server errors
- Use exponential backoff for network issues
- No charge for failed attempts
Check rate limits
Your API key allows 60 requests per minute after the first top-up. If you exceed this, you will receive a 429 status code.
Before processing large contracts, verify your current rate limit status to avoid queuing delays that could impact user experience.
- Limit: 60 requests/minute
- Status: 429 Too Many Requests
- Initial limit: 10 requests/minute
Verify input text
Ensure your text does not exceed 4096 characters per request. Long contracts must be split programmatically before submission.
Check that the input field contains valid UTF-8 and that the voice and model parameters match the supported presets.
- Max 4096 characters per request
- Valid UTF-8 encoding required
- Check voice/model availability
Ensure Data Privacy
Legal teams need assurance that sensitive contract details remain private. Our TTS API processes your input text solely to generate the requested audio file. We do not use your specific contract language or case details to train or improve our underlying models, ensuring your proprietary terms stay confidential.
Once the audio is generated and returned in the response, it is not stored on our servers. This means your legal documents are transient, used only for the immediate conversion task, and then discarded from active storage.
No text training
Your input text is used exclusively for the synthesis process. Unlike some competitors, we do not ingest your data into our training datasets. Your legal phrasing and unique clauses remain yours, preserving attorney-client privilege and internal confidentiality standards without hidden data mining.
- Input text is not used for model training
- Proprietary legal phrasing remains confidential
No audio storage
Generated audio files are returned directly in the API response and are not retained on our infrastructure. This minimizes the attack surface for your legal assets. You control where the audio is stored, whether in your own secure cloud buckets or local servers.
- Audio is returned in the response
- No long-term audio storage on our servers
Metadata only
We retain only the essential metadata required for billing and troubleshooting. This includes the timestamp, character count, and request status. No content from your contracts or the resulting audio is kept beyond what is necessary for accurate billing and service reliability.
- Timestamps, character counts, and status codes only
- No content retention beyond billing needs
Launch to Users
Launching ClarityVoice for legal content requires deploying your API key and monitoring real-time performance to ensure seamless audio generation. By tracking character usage and response times, product teams can maintain compliance-ready documentation without unexpected interruptions. The dashboard provides clear visibility into balance and usage, ensuring accurate billing down to the character.
Supporting end-users hinges on reliable delivery and clear error handling. Since the API processes requests sequentially, monitoring queue status helps manage expectations for long contracts. Support is by email only.
Deploy API key
Securely integrate your ClarityVoice API key into your application’s backend configuration. Ensure the key is protected from exposure in client-side code, as each account holds one active key at a time. Rotate the key via the /get-api-key/ dashboard if needed, noting that the old key stops immediately upon issuing a new one.
- Store keys in environment variables
- Rotate keys via dashboard
- Protect keys from client exposure
Monitor performance
Track character consumption and request latency through the dashboard. Since requests are processed sequentially, long documents may experience slight delays during high load. Use the usage metrics to anticipate volume spikes and adjust your processing pipeline accordingly, ensuring consistent delivery of audio files to your users.
- Track character consumption
- Monitor request latency
- Anticipate volume spikes
Support users
Provide clear guidance on character limits and voice selection. Since support is email-only, ensure your documentation links directly to /contact/ for efficient issue resolution. Educate users on the 4096-character limit and the need to split longer contracts, minimizing support tickets related to input size or formatting errors.
- Guide on character limits
- Link to email support
- Educate on splitting text
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This ensures each segment is processed correctly without truncation or errors.
23 languages
Any voice speaks any of these languages.
