Frequently asked questions
What is an AI voice reader?
It is a cloud text-to-speech API that accepts text input and returns an audio file. You send a POST request to the endpoint with your text, and the system synthesizes the speech using licensed voices. It is designed to turn dense legal text into clear, listenable audio for product teams.
Which voice is best for reading legal documents?
Q: Which voice is suitable for reading legal documents? A: We offer eight presets, including atlas (neutral, news) and sage (calm, instructional), which suit legal content well. Every voice can speak any supported language. You can test all options via the /v1/voices endpoint to find the tone that best fits your specific compliance or documentation needs.
How much does it cost to convert legal text to audio?
Pricing 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 charges returned in full. There are no monthly plans, seats, or minimum spend requirements, allowing you to pay only for what you use.
Do you support SSML for legal formatting?
No, we do not support SSML. The API accepts plain text input up to 4096 characters. If you need specific formatting, you should split your text into parts and join the resulting audio files. We do not offer phoneme dictionaries or custom pronunciation lexicons for precise legal term control.
Can I use my own voice for legal narration?
No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design a new one. The API uses eight fixed presets based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark marking it as synthetic speech.
How many characters can I send in one request?
You can send up to 4096 characters per request. For longer legal documents, you should split the text into parts of this size and join the resulting audio files. This ensures efficient processing and allows you to manage character counts accurately for billing purposes.
Is the audio stored after generation?
No, generated audio is returned in the response and not stored by our system. Input text is used only to produce the audio and is not used for training. We keep request metadata, such as time, characters, and status, strictly for billing and usage tracking purposes.
Do you offer an SLA for legal apps?
No, we do not offer an SLA or uptime guarantee. There is no enterprise contract or on-premise install option. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time, but short phrases may take a few seconds.
How do I get a API key?
Sign up on our /get-api-key/ page using Google or an email and password. Accounts are per site. Once registered, you receive one active key. You can issue a new key at any time, which stops the old one immediately. The dashboard shows your key, balance, and usage.
What languages are supported?
We support 23 languages, including English, German, French, Spanish, and Japanese. Any voice can speak any of these languages. If you do not set the language, it is guessed from the script. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.
Is there a limit on requests per minute?
Yes, the limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. This ensures fair usage while processing requests sequentially. Longer texts are split into parts, so multiple requests may be needed for a single document.
Do you support streaming audio?
No, we do not support streaming, WebSocket, or real-time partial audio. You send a POST request with your text and receive the complete audio file in the response. This synchronous approach ensures reliable delivery of the synthesized speech for your legal documentation workflows.
Can I clone a lawyer's voice?
No, we do not offer custom voice cloning. You cannot upload a voice sample to create a unique preset. The API uses eight fixed voices based on licensed recordings. Each file carries an inaudible watermark indicating it is synthetic speech, distinct from human recordings.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum amount is $5. Credits are added automatically within minutes after your transfer. We do not accept cards, PayPal, or subscriptions. Your balance does not expire, and you can manage it via your account dashboard.
First request
curl
curl https://api.playvt443.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 Legal Text into Audio
ClarityVoice transforms dense legal text into clear, listenable audio via a simple API call. Send your compliance documents or contracts, and receive synthesized speech that maintains readability without manual formatting. This tool is designed for product teams who need to convert static text into accessible audio formats quickly.
Compliance-ready conversion
Input up to 4,096 characters per request. The API returns audio files ready for playback in your applications. Failed requests incur no charge, ensuring accurate billing for your compliance audits.
- Handle up to 4,096 characters per request
- Receive audio files instantly
- Zero cost on failed synthesis
Clear narration voices
Choose from eight preset voices, including neutral and instructional tones like Atlas and Sage. These voices are based on licensed recordings, ensuring a professional standard for legal content without celebrity impersonation.
- Eight distinct voice presets
- Licensed source recordings
- Professional, neutral tones available
Instant API access
Use the standard OpenAI-compatible endpoint to integrate immediately. Send a POST request with your text and voice selection, and receive the audio file directly. No custom SDKs or complex setup required.
- OpenAI SDK compatible
- Standard JSON format
- Immediate integration capability
Voices for Legal Contexts
ClarityVoice offers distinct voice presets tailored for different legal communication styles. Whether you are broadcasting regulatory updates or explaining complex compliance procedures, selecting the right tone ensures your audience remains engaged and informed.
Neutral news tone
Atlas delivers a steady, authoritative delivery ideal for reading out lengthy terms of service or legal notices. Its neutral cadence ensures that dense contractual language is processed clearly without introducing emotional bias.
- Consistent pacing for high-volume text
- No emotional inflection for objective reading
- Ideal for standard legal disclosures
Calm instructional voice
Sage provides a gentle, instructional tone perfect for guiding users through onboarding flows or compliance checklists. The clear enunciation helps break down complex procedural steps into digestible audio segments.
- Clear articulation for complex instructions
- Softer delivery for user guidance
- Reduces cognitive load for readers
Deep documentary style
Orion brings a deep, resonant quality suitable for detailed case studies or historical legal reviews. This voice adds a layer of gravitas to long-form content without sounding monotonous.
- Rich timbre for long-form content
- Engaging narrative structure
- Suitable for case law reviews
Support for 23 Languages
ClarityVoice supports 23 languages, covering the majority of global legal documentation needs. From Arabic to Chinese, we cover the essential markets for international compliance teams.
The API handles language detection automatically based on the text script, ensuring accurate synthesis without extra configuration for standard inputs.
Global legal texts
Our engine supports 23 specific languages, including English, German, French, Spanish, Japanese, Korean, and Chinese. This range covers most major legal jurisdictions, allowing product teams to process contracts and compliance docs in their native tongues without switching providers.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-language detection
If you do not specify a language, the API guesses it from the script. Latin script defaults to English, which works for most English legal texts. Non-English Latin text should always set the language code to avoid mispronunciation.
Explicit language codes
For precise control, pass the ISO language code in the request. This ensures consistent pronunciation for mixed-language clauses or specific regional variants. Note that Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Developer-Friendly Integration
Integrate ClarityVoice into your legal tech stack using familiar tools. Our API mirrors the OpenAI speech endpoint structure, allowing you to swap in your API key and base URL without rewriting your integration logic. This compatibility means your existing codebases can start generating audio immediately.
OpenAI SDK compatible
Use the official OpenAI SDKs by simply updating the base_url to https://api.playvt443.com/v1. Your authentication header remains Authorization: Bearer tts-..., ensuring a seamless drop-in replacement for current text-to-speech implementations.
Simple curl requests
Test the endpoint directly from your terminal. A single POST request with JSON body sends your legal text and receives the audio file, making it easy to validate responses during development without setting up a full frontend.
- POST https://api.playvt443.com/v1/audio/speech
- Authorization: Bearer tts-...
Standard JSON format
Requests follow a standard JSON structure with fields like model, input, voice, and response_format. This predictable shape reduces parsing errors and simplifies debugging when processing dense compliance documents or lengthy case files.
Precise Character Billing
Legal billing requires exactness. ClarityVoice charges $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total, ensuring predictable costs for dense compliance documentation. Failed requests are free, so you only pay for successfully generated audio.
Usage is transparent in your dashboard. You can track characters consumed, balance remaining, and request status in real time. This visibility helps product teams budget accurately without guessing how long complex legal texts will take to synthesize.
Pay per 1,000 characters
The rate is fixed at $0.01 per 1,000 characters. This linear model scales directly with your document volume. Whether processing a short clause or a full contract, the cost remains proportional to the character count, including spaces and punctuation.
- $0.01 per 1,000 characters
- Spaces and punctuation count as characters
- Linear scaling for any document length
Transparent usage
Your dashboard displays current balance, trial credit, and character usage. You can see exactly how much text has been processed and how much remains. This data helps you monitor API consumption without needing external tools.
No hidden fees
There are no monthly plans, seats, or minimum spend requirements. You top up with USDT (TRC-20) and spend only what you use. Failed requests are refunded in full, ensuring you never pay for errors.

Audio Formats for Any Player
ClarityVoice supports multiple audio formats to suit different playback environments and quality requirements. Choose the format that fits your application’s needs, from lightweight web playback to high-fidelity archival storage.
We do not offer WAV, MP3, or FLAC exclusively; all are available via the standard API response. Select the format that aligns with your player’s capabilities and your team’s quality standards.
MP3 compatibility
MP3 is the most widely supported format for web players and mobile apps. It offers a good balance between file size and audio quality, making it ideal for general-purpose legal document playback.
WAV for quality
WAV provides uncompressed audio, ensuring no loss in fidelity. This format is suitable for archival purposes or when high-quality playback is required for detailed legal review.
FLAC lossless
FLAC offers lossless compression, preserving the original audio data while reducing file size. It is perfect for teams that need high-quality audio without the larger file size of WAV.
Built for Product Teams
ClarityVoice is designed for product teams who need to embed audio directly into their applications without managing infrastructure. Our API integrates seamlessly with existing legal tech stacks, allowing you to convert dense contract text into clear audio files on demand.
The system handles variable workloads efficiently, processing requests sequentially with predictable latency. You can scale usage up or down based on your team's review cycles without over-provisioning resources or paying for idle capacity.
Billing is strictly usage-based, charged per 1,000 characters. There are no monthly subscriptions, seat limits, or minimum spend requirements. You only pay for the characters you actually convert, making it easy to forecast costs for specific document batches.
Easy integration
The API follows a standard JSON structure compatible with the OpenAI SDK. Product teams can switch to our base URL and use familiar libraries to send text and receive audio files instantly.
We provide simple curl examples and clear documentation for common legal text workflows, reducing the time from prototype to production.
- OpenAI SDK compatible
- Standard JSON format
- Simple curl requests
Scalable volume
The API handles requests sequentially, processing them in order. For long documents, split the text into parts of up to 4,096 characters and join the resulting audio files.
Rate limits are set at 60 requests per minute per key, which is sufficient for most batch processing needs without requiring complex queue management.
No monthly plans
There are no monthly plans, seats, or minimum spends. Accounts start with a $0.50 trial credit if you sign in with Google.
Top-ups via USDT (TRC-20) are processed automatically. Balance does not expire, so you can pause usage between projects without losing access.
Legal Data Privacy
Legal teams need assurance that sensitive contract text isn’t repurposed. Our API processes input strictly to generate audio; the raw text is not used for model training, ensuring your proprietary clauses remain confidential during synthesis.
No training on input
Unlike some consumer-grade TTS services, ClarityVoice does not ingest your submitted text to improve its base models. Your legal documents, terms of service, and compliance notes are processed in real-time and discarded after generation, keeping your intellectual property secure.
- Input text is used solely for audio synthesis.
- Not used for training or model improvement.
No stored audio
Generated audio files are returned directly in the API response and are not persistently stored on our servers for long-term retention. Once you download the file, the temporary copy is removed, minimizing the attack surface for your legal audio assets.
- Audio is returned in the response.
- No long-term storage of generated files.
Metadata only
We retain minimal request metadata—specifically the timestamp, character count, and status—for accurate billing and rate limit tracking. This data does not contain the content of your legal text, ensuring that your usage patterns are transparent without exposing your document content.
- Time, characters, and status are kept.
- Used strictly for billing and limits.
Try It With Free Credit
Start testing immediately with $0.50 of trial credit, valid for 7 days after signing in with Google. This gives you 50,000 characters to verify quality before committing. Accounts created with email only start without this trial credit.
Use the credit to convert dense legal clauses into clear audio. Verify that the narration tone matches your compliance requirements and that the character billing is accurate from the first request.
Get $0.50 trial
Receive $0.50 of credit upon signing in with Google. This amount covers approximately 50,000 characters, allowing you to test the API without immediate payment.
The trial is valid for 7 days. If you need more volume, you can top up with USDT on the TRON network.
Sign in with Google
Access the /get-api-key/ page and sign in with your Google account. Your API key and trial balance are available instantly.
This method ensures quick setup. Note that email-based accounts do not receive the trial credit.
Test with legal text
Send a JSON request with a sample legal clause to https://api.playvt443.com/v1/audio/speech. Choose a voice like 'atlas' for a neutral, news-like tone or 'sage' for calm instruction.
Receive the audio file in your preferred format (mp3, wav, or flac). Check the output for clarity and accurate character billing.
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.
