Frequently asked questions
What is text reader online for legal documents?
LexiSpeak is a cloud text-to-speech API for legal teams. Send text via POST request to receive synthesized speech for case files and contracts. It supports 23 languages and uses licensed voices based on public-domain readings. The generated audio is returned in the response and not stored, ensuring reliable formatting for internal review and accessibility.
How does TTS handle legal terminology?
Our engine uses eight preset voices like Sage or Atlas. It does not offer custom pronunciation lexicons or phoneme dictionaries. For accurate legal terminology, ensure your input text is clear and contextually precise. The system handles standard pronunciation well, but specific jargon relies on the clarity of your submitted text to generate correct audio output.
Which voice is best for reading contracts?
Sage offers a calm, instructional tone ideal for detailed contract review, while Atlas provides a neutral, news-style delivery suitable for standard legal text. You can adjust the speed between 0.25 and 4.0 to match your team’s preferred listening pace for complex legal clauses.
Can I use TTS for client recordings?
Yes, you can generate audio files for client use. Every generated file carries an inaudible watermark that marks it as synthetic speech. The input text is not used for training, and generated audio is not stored on our servers. You retain control over the output format, choosing from mp3, wav, opus, flac, or pcm for your needs.
What is the character limit per request?
Each API request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer legal documents, you must split the text into parts of up to 4096 characters and join the resulting audio files. This ensures consistent processing and avoids timeouts during synthesis.
Do you support SSML for legal pacing?
No, LexiSpeak does not support SSML. You cannot use SSML tags for custom pacing, pauses, or emphasis within legal documents.
Is the audio format compatible with players?
A: Yes, you can choose from mp3, wav, opus, flac, or pcm formats. These are standard formats compatible with most media players and legal review software.
How fast is the generation speed?
Generation is roughly real-time, producing about 25 characters of text per second of audio. Short phrases take a few seconds, while longer texts process sequentially. Under load, requests may wait in a queue. The speed is consistent, allowing you to estimate processing times based on the character count of your legal documents.
Can multiple team members use one key?
Yes, one active API key can be used by multiple team members. Each account has one active key, which can be revoked and replaced at any time. The rate limit is 60 requests per minute per key, so large teams may need to coordinate usage or manage multiple keys if high volume is required.
Do you offer voice cloning for partners?
No, LexiSpeak does not offer custom voice cloning. You cannot upload your own voice or design custom voices. The service relies on eight preset voices derived from licensed recordings. If you need a specific partner’s voice, you must select the closest preset, such as Milo for conversational tones.
What happens if the API request fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You can retry the request or split the text into smaller parts. This ensures you only pay for successfully generated audio. Check the response status to identify the issue and adjust your input or speed settings if necessary.
Are there volume discounts for large firms?
No, there are no volume discounts or monthly plans. The price is fixed at $10 per 1 million characters. There are no minimum spends or tiered pricing. Large firms pay the same rate per character as smaller teams, with no additional fees for seats or usage volume, keeping costs predictable.
Which languages are supported for legal texts?
We support 23 languages, including English, Spanish, German, French, and Arabic. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script. For non-English Latin-script text, set the language parameter explicitly to ensure accurate pronunciation for your legal documents.
Do I need an internet connection to listen?
Yes, you need an internet connection to generate the audio via the API. Once downloaded, the audio file can be played offline. The API requires a connection to send text and receive the audio file. Playback of the generated file does not require internet access, but generation does.
First request
curl
curl https://api.playokpk.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.mp3Streamline Document Review
Legal teams face dense case files that demand careful reading. LexiSpeak processes contracts by splitting text into 4096-character chunks and joining the audio files. This allows you to review entire agreements without staring at a screen.
Batch Process Contracts
Split longer documents into parts of up to 4096 characters and join the resulting audio. Process multiple sections sequentially to build a complete narrated file for your review folder.
- Split text into 4096-character chunks
- Join audio files for full documents
- Process sections sequentially
Listen While You Work
Listen to case details while reviewing other materials or commuting. The API returns standard audio formats like MP3 or WAV, compatible with any legal review software or device.
Reduce Review Time
Generation runs at roughly real-time speed, processing about 25 characters per second. Queue requests sequentially under load to maintain consistent playback for lengthy contract reviews.
Voice Clarity for Legal Text
Legal documents demand precise pronunciation and consistent pacing. Our voices are engineered for clarity, ensuring that complex legal terminology is rendered accurately without the distractions of emotional inflection or artificial warmth.
Neutral News Voice
Atlas provides a neutral, news-style delivery ideal for reading case files and contracts. Its steady tone removes subjective emphasis, allowing your team to focus on the legal content rather than the narrator's personality.
- Neutral tone for unbiased reading
- Ideal for long-form contract review
- Reduces listener fatigue during extended sessions
Clear Narration
Voices like Aria and Luna offer warm, clear narration suitable for storytelling or detailed contract explanations. This clarity helps legal teams maintain focus during internal reviews or accessibility readings without distraction.
- Warm clarity for complex texts
- Suitable for detailed explanations
- Reduces cognitive load for listeners
Adjustable Speed
Adjust playback speed from 0.25x to 4.0x to match your reading pace. Speed up through standard clauses or slow down for dense legal arguments, ensuring every word is audible and understandable.
- Speed range: 0.25x to 4.0x
- Adapts to individual reading preferences
- Optimize review efficiency

Supported Languages
LexiSpeak supports 23 languages, allowing legal teams to process international contracts and case files without needing separate tools for each region. Any voice can speak any of these languages.
English & Spanish
English and Spanish are fully supported with all eight voice presets available. You can explicitly set the language code to ensure consistent pronunciation, especially when mixed scripts appear in bilingual documents.
- All 8 voices support English
- All 8 voices support Spanish
- Explicit language code recommended for mixed scripts
German & French
German and French texts are processed. Any voice can speak these languages.
- All 8 voices support German
- All 8 voices support French
- Consistent pronunciation across all voice types
23 Languages Total
Beyond English, Spanish, German, and French, we support 19 additional languages including Arabic, Chinese, Japanese, Hindi, and Portuguese. This wide range allows global legal teams to centralize their TTS workflow. If the language parameter is omitted, Latin-script text defaults to English, so set the code for other languages to avoid mispronunciation.
- Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, Turkish
- Latin script defaults to English if language is not set
- Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported
Technical Integration
Our API endpoint mirrors the OpenAI speech structure, allowing your existing integrations to adapt with minimal code changes. By simply updating the base URL to https://api.playokpk.com/v1, you can utilize standard OpenAI SDKs to send text and receive audio files directly.
OpenAI Compatible
We follow the same request shape as the OpenAI speech endpoint. This means you can use the official OpenAI SDKs by changing the base URL to our API domain. Your existing code structure remains largely intact, reducing the learning curve for your engineering team.
- Same JSON body structure as OpenAI
- Works with standard OpenAI SDKs
- Minimal code changes required
Standard Formats
Receive audio in formats that fit any playback environment. We support MP3, WAV, OPUS, FLAC, and PCM. These are standard formats ensuring compatibility with most legal transcription tools and internal document review systems.
- MP3, WAV, OPUS, FLAC, PCM
Simple API Key
Authentication is straightforward using a single Bearer token. Send your key in the Authorization header for every request. You can generate a new key at any time via the dashboard, instantly invalidating the previous one for security.
- Bearer token authentication
- Instant key rotation
- Single active key per account
Pricing for Teams
LexiSpeak bills strictly by usage at $10 per 1 million characters, meaning you pay $0.01 for every 1,000 characters processed. Spaces and punctuation count toward this total, ensuring predictable costs for large contract batches. Failed requests are free, so you only pay for successful audio generation.
Per Character Rate
Pricing scales linearly with volume. At roughly 25 characters per second of audio, long case files generate efficiently.
No Monthly Fees
There are no monthly plans, seats, or minimum spend requirements. Your balance does not expire, and you can top up whenever needed. Accounts start with a $0.50 credit (valid 7 days) when you sign in with Google.
Transparent Costs
Top-ups are processed via USDT (TRC-20) on the TRON network, with a minimum of $5. Credits are automatic and typically available within minutes. No invoices, VAT, or hidden fees apply.
- USDT on TRON (TRC-20) only
- No cards or PayPal
- No monthly subscriptions
- Balance never expires

Security & Data
Your input text is used strictly to generate the audio file for that specific request. It is not ingested into our training data or used to improve the voice engine, ensuring your confidential case details and contracts remain private to your session.
No Training Data
We do not use your case files, contracts, or internal memos to train our models or improve the voice engine. The text you send exists only long enough to produce the audio response.
- Input text is used only to produce the audio and is not used for training.
No Storage of Audio
Generated audio is returned in the response and not stored. Once the audio file is delivered to your application, we do not retain a copy of the synthesized speech on our servers.
Metadata Only
We retain only request metadata, such as timestamp, character count, and status, for accurate billing and usage tracking. This minimal data ensures you can verify your usage without exposing the content of your legal documents.
System Requirements
To ensure smooth processing, each API request must contain input text of up to 4,096 characters. For documents exceeding this limit, split the text into chunks and join the resulting audio files. Short phrases may take a few seconds to generate, while longer texts process at roughly real-time speed (25 characters per second).
Requests are processed sequentially, so high volume may cause brief queuing. Failed requests incur no charge, but standard rate limits apply to successful submissions to maintain service stability for your legal team’s workflow.
Character Limits
Each request accepts a maximum of 4,096 characters. Spaces and punctuation count toward this total. For longer contracts or case files, split the text into manageable segments and concatenate the output audio files.
Supported Formats
Choose from mp3, wav, opus, flac, or pcm via the response_format field. These standard formats integrate easily with most legal review platforms and internal media players.
Rate Limits
New accounts start with a limit of 10 requests per minute. After your first top-up, the limit increases to 60 requests per minute per API key. This ensures fair usage while supporting batch processing needs.
Why Legal Teams Choose Us
We prioritize consistency and transparency over marketing claims. Our synthetic speech output is reliable for repeated review sessions, and every file carries an inaudible watermark to clearly mark it as AI-generated. We do not offer custom voice cloning.
Consistent Output
Legal teams need predictable results. Our engine processes requests sequentially, ensuring that every document is rendered with the same voice characteristics and pacing. This consistency helps reviewers focus on content rather than adapting to varying audio styles.
No Voice Cloning
We stick to eight licensed voices based on LibriTTS-R and LibriVox readings. This means you get clear, usable audio without the legal overhead of negotiating rights for cloned voices. If you need a specific voice, you choose from our preset list.
Clear Pricing
We charge $0.01 per 1,000 characters with no per-seat fees. One API key serves your entire team, and there are no monthly plans or minimum spends. Failed requests are free, so you only pay for successful synthesis.

Get Started Today
To begin, create your account using your existing Google credentials or a standard email address. This process is instant and requires no complex verification steps for legal teams looking to start immediately.
Once registered, you are directed to a dashboard that displays your unique API key, current balance, and usage statistics. You can also generate a new key at any time if needed for security purposes.
Sign Up with Google
Click the 'Sign in with Google' button on the login page. This method grants you immediate access to a free trial credit of $0.50, valid for 7 days, allowing you to test the service without a credit card.
- Instant account creation
- Free trial credit included
- No payment details required
Get Your API Key
Your API key is generated automatically upon sign-up. It is displayed on your dashboard alongside your current balance and character usage. You can revoke and replace this key at any time from the same page.
- One active key per account
- Instant replacement capability
- Visible on dashboard
Try the Demo
Use the provided curl example on the dashboard to test the API immediately. Paste a contract excerpt to hear how the system handles legal terminology with voices like Atlas or Sage. This helps verify audio quality before processing large volumes.
- Ready-to-use curl example
- Test with contract text
- Verify pronunciation accuracy
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. These comprehensive legal documents streamline compliance for our large distributed teams across multiple jurisdictions.
23 languages
Any voice speaks any of these languages.
