Frequently asked questions
What is the NewsVoice API?
NewsVoice API is a cloud text-to-speech service that converts text into audio files via a simple POST endpoint. It mirrors the OpenAI speech endpoint structure, allowing newsrooms to integrate synthetic voice generation directly into their digital distribution pipelines using standard HTTP requests and JSON bodies.
How does it differ from Google Docs read aloud?
Unlike Google Docs read aloud, which is a manual browser feature, NewsVoice provides programmatic access via API. It supports 8 distinct voice presets, multiple audio formats, and handles high-volume batch processing for news scripts, enabling automated audio generation for broadcast and digital platforms without manual intervention.
Is it better for large editorial teams?
Yes, it is designed for large editorial teams needing reliable, high-volume audio generation. The API processes requests sequentially with a 60 requests-per-minute limit per key, allowing teams to automate news updates efficiently. It handles long texts by splitting them into parts and joining the resulting audio files seamlessly.
How much does it cost per character?
The cost is $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successfully generated audio files, making it cost-effective for high-volume newsroom workflows and daily broadcast updates.
What are the rate limits for news workflows?
Each API key allows 60 requests per minute. New accounts start with a limit of 10 requests per minute until the first top-up is processed. This limit supports steady newsroom workflows, and longer texts are handled by splitting input into 4,096-character chunks to ensure consistent delivery.
Which languages are supported for news content?
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If the language is not specified, it guesses from the script, defaulting to English for Latin text.
Can I use any voice for any language?
Yes, all 8 voice presets can speak any of the 23 supported languages. For example, the 'aria' voice can deliver news in French, while 'atlas' can read scripts in Japanese. This flexibility allows editorial teams to maintain consistent branding across different linguistic markets without needing separate voice profiles.
Is there a free trial for newsrooms?
Accounts signed up with Google receive $0.50 of trial credit, valid for 7 days, covering approximately 50,000 characters. Email-based accounts start without trial credit. This allows newsrooms to test integration and voice quality before committing to USDT top-ups for their ongoing broadcast audio production needs.
How do I pay with USDT?
Payments are made via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes of transfer. There are no subscriptions or monthly plans; you simply top up your balance as needed, which never expires, supporting flexible newsroom budgeting.
Are failed requests charged?
No, failed requests are free. If synthesis fails, the charge is returned in full. This ensures that your newsroom’s budget is only consumed by successfully generated audio files, providing predictable costs for your editorial team’s daily audio production workflows without unexpected charges for errors.
Do you offer custom voice cloning for news anchors?
No, custom voice cloning is not offered. We do not offer voice design or uploading your own voice. The API provides 8 fixed presets like 'atlas' for neutral news delivery or 'aria' for clear narration. Voices are based on licensed recordings from LibriTTS-R and LibriVox. Newsrooms must select from these existing voices rather than uploading unique anchor recordings.
Is there an SLA for uptime?
There is no Service Level Agreement (SLA), uptime guarantee, or certifications (SOC 2, HIPAA, GDPR). Requests are processed sequentially, so under load, a request may wait in a queue. This means generation times can vary during peak usage, which newsrooms should account for when scheduling time-sensitive broadcast audio deliveries.
How is my input text used?
Input text is used solely to produce the audio file and is not used for training models. Generated audio is returned in the response and not stored. Only request metadata, such as time, character count, and status, is kept for billing purposes, ensuring data privacy for news content.
Can I get a VAT invoice?
No, there are no invoices with VAT. Payments are made via USDT on the TRON network, and the service operates without traditional subscription models or invoicing systems. Newsrooms should manage their own accounting records based on the automatic balance updates and transaction history available in their account dashboard.
First request
curl
curl https://api.playwin333.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 News Teams Choose Our API
Newsrooms require rapid audio production for breaking stories. Our API processes large volumes of text efficiently, allowing editorial teams to generate broadcast-ready audio files without manual recording delays. The system handles requests sequentially, ensuring stable output even during high-traffic periods.
Unlike manual voiceover workflows, our solution offers consistent voice quality across global editions. Editors can distribute the same script in multiple languages while maintaining a uniform brand tone, streamlining digital distribution and reducing production bottlenecks.
High-volume audio generation for breaking news
The API accepts text inputs up to 4096 characters, enabling quick synthesis of news briefs. Generation speed approximates real-time, processing roughly 25 characters per second. This allows editors to produce audio updates almost as fast as they write, crucial for evolving stories.
Under load, requests queue automatically. With a limit of 60 requests per minute per key, teams can sustain steady output without overwhelming the service. Failed requests incur no charge, protecting your budget during peak news cycles.
- Sequential processing ensures stable output
- Real-time generation speed for quick updates
- Queue management handles high load
Consistent voice across global editions
Eight distinct voice presets ensure uniform editorial standards across all channels. Whether using the neutral Atlas for hard news or the deep Orion for documentaries, the audio quality remains consistent regardless of the language spoken.
Support for 23 languages allows a single voice to anchor content globally. This eliminates the variability of hiring different voice talent for each regional edition, ensuring listeners hear the same authoritative tone worldwide.
Direct alternative to Google Docs read aloud
Google Docs read-aloud offers limited, low-fidelity synthetic voices suitable only for internal preview. Our API provides high-quality, broadcast-ready audio files in formats like MP3, WAV, and OPUS. This is a programmatic solution for professional distribution, not just internal listening.
By switching the OpenAI SDK base URL, news teams can integrate this TTS directly into their content management systems. This replaces manual recording or basic text-to-speech tools with a reliable, scalable infrastructure.
Voice Presets for Editorial Content
Our API provides eight distinct voice presets derived from licensed recordings, ensuring consistent audio quality for editorial workflows. These voices are designed for clarity and neutrality, making them ideal for reading news scripts, updates, and press releases without the distraction of overly expressive tones.
Each preset maintains a professional demeanor suitable for broadcast or digital distribution, allowing editorial teams to select the most appropriate voice for their specific content type and audience expectations.
Atlas: Neutral, reliable news anchor tone
Atlas delivers a neutral, clear delivery style that mimics the cadence of a professional news anchor. Its balanced tone ensures that complex news updates are communicated with authority and clarity, making it the default choice for breaking news alerts and daily briefings where neutrality is paramount.
- Ideal for breaking news and press releases
- Neutral tone ensures factual neutrality
- Clear articulation for complex data
Orion: Deep, documentary-style narration
Orion offers a deep, resonant voice suitable for long-form content or documentary-style segments. Its rich timbre adds gravitas to investigative reports or feature stories, providing a listening experience that feels polished and engaging without sacrificing the informational integrity of the script.
- Best for long-form features
- Adds gravitas to investigative reports
- Engaging yet professional delivery
Sage: Calm, instructional reporting voice
Sage provides a calm, instructional tone perfect for explanatory journalism or tutorial-style updates. Its steady pacing helps listeners digest detailed information, making it an excellent choice for explaining policy changes, technical updates, or educational news segments where clarity and patience are key.
- Ideal for explanatory journalism
- Steady pacing aids comprehension
- Best for policy or technical updates
Language Support for Global News
Our API supports 23 languages, including Arabic, Hindi, Spanish, and Japanese, allowing news teams to distribute content globally without hiring local voice talent. Every voice can speak any supported language, ensuring consistent audio quality across different regions.
You can explicitly set the language code or rely on automatic detection. For texts in Latin script that are not English, you must specify the language to avoid incorrect pronunciation. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and all others not in the list.
23 supported languages including Arabic, Hindi, Spanish
We support 23 languages: 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 deliver any of these languages, allowing editorial teams to maintain a single audio style across diverse markets.
Automatic language detection or explicit setting
Set the language field in your request for precise control, especially for non-English Latin-script text. If omitted, the system guesses the language from the script. Explicitly setting the code prevents mispronunciation in multilingual news segments.
Latin script defaults to English without configuration
If you send Latin-script text without specifying a language, the API defaults to English. This simplifies workflows for English-language news desks but requires explicit configuration for other Latin-based languages like French or Spanish to ensure accurate accent and intonation.
Technical Integration for Editors
Editors integrate NewsVoice API directly into content workflows using standard HTTP clients or the official OpenAI SDK. By simply changing the base_url to https://api.playwin333.com/v1, existing code connects instantly without requiring a custom library or SDK download.
OpenAI SDK compatible with simple base_url change
The API mirrors the OpenAI speech endpoint structure, allowing teams to reuse familiar authentication patterns. Pass your tts-... key via the Authorization header, and the SDK handles the JSON serialization automatically.
- Use OpenAI SDKs with
base_url=https://api.playwin333.com/v1 - Standard
Authorization: Bearerauthentication - No custom client libraries required
JSON API endpoint: POST /v1/audio/speech
Send text up to 4,096 characters per request via a simple POST call. The endpoint accepts parameters for model, voice, speed, and response_format, returning the audio file directly in the response body.
- Endpoint:
POST https://api.playwin333.com/v1/audio/speech - JSON body with
input,voice, andmodelfields - Returns audio file directly
Support for MP3, WAV, OPUS, FLAC, PCM formats
Select the output format that fits your broadcast or digital distribution pipeline. Choose from MP3, WAV, OPUS, FLAC, or PCM. Note that OPUS is not streaming; there is no streaming support.
- MP3, WAV, OPUS, FLAC, PCM
- No additional conversion steps needed
- Choose format per request
Pricing Model for Large Teams
Our pricing is strictly usage-based at $10 per 1 million characters, equating to $0.01 per 1,000 characters. This model scales effortlessly with your editorial output, ensuring you pay only for what you broadcast. Spaces and punctuation count toward the total, providing predictable cost attribution for every news segment or update generated.
Unlike traditional enterprise contracts, there are no monthly plans, no per-seat fees, and no minimum spend requirements. You retain full flexibility to ramp up volume during breaking news cycles without committing to long-term subscriptions or managing complex seat allocations for your distributed team.
$10 per 1 million characters processed
The rate is $0.01 per 1,000 characters, including spaces and punctuation. This straightforward metric allows finance teams to accurately forecast audio production costs based on script length and frequency. Long-form content is processed efficiently, with typical generation speed roughly matching real-time playback for standard news scripts.
- $10 per 1,000,000 characters ($0.01 per 1,000 characters)
- Spaces and punctuation count toward character limits
- No hidden fees for format or speed adjustments
No monthly plans or per-seat fees
We eliminate the overhead of managing multiple licenses or paying for idle editors. Your API key provides unlimited access to the engine, regardless of how many editors or systems trigger requests. This flat-rate structure simplifies budgeting for large teams where usage fluctuates significantly between routine updates and major breaking news events.
- No monthly subscription tiers
- No per-seat licensing fees
- No minimum spend requirements
Failed requests are free, no wasted budget
If a synthesis request fails due to technical issues, the charge is returned in full. You are not billed for audio that was not successfully delivered. This ensures your budget is strictly allocated to usable audio files, protecting your operational efficiency when integrating with automated publishing workflows.
- Full refund on failed synthesis requests
- No charge for unusable audio
- Predictable cost per successful output
Data Privacy and Usage Rights
For editorial teams managing sensitive breaking news scripts, knowing how input data is handled is critical. Our API ensures that the text you send for synthesis is used exclusively to generate the audio file and is not used to train or improve our underlying models. This isolation means your editorial content remains distinct from the training corpus.
Input text not used for training models
The text payload you submit is processed solely for immediate audio generation. It is not retained for model retraining, ensuring that your unique news narratives do not inadvertently influence future voice outputs or become part of the public training dataset.
Generated audio returned in response, not stored
Once the synthesis is complete, the resulting audio file is returned directly in the API response. We do not store the generated audio files themselves, minimizing the risk of your content lingering in our storage infrastructure beyond the immediate delivery window.
Inaudible watermark marks synthetic speech
Every audio file generated by our API carries an inaudible digital watermark. This watermark explicitly marks the file as synthetic speech, providing a clear audit trail for broadcast compliance and helping distinguish AI-generated news updates from human-recorded voiceovers.
Performance and Reliability
Audio generation runs at roughly real-time speed, producing approximately 25 characters of text per second of audio. For short phrases, synthesis typically takes a few seconds. Longer texts are split into 4096-character chunks and stitched together, maintaining consistent timing across the full broadcast segment.
Roughly real-time generation speed
Audio generation runs at roughly real-time speed, producing approximately 25 characters of text per second of audio. For short phrases, synthesis typically takes a few seconds. Longer texts are split into 4096-character chunks and stitched together, maintaining consistent timing across the full broadcast segment.
60 requests per minute rate limit per key
Each API key is limited to 60 requests per minute. Before the first top-up, this limit is reduced to 10 requests per minute. This constraint applies per key, allowing teams to distribute load across multiple keys if higher throughput is required for breaking news updates.
Queue processing under high load
Requests are processed sequentially. During periods of high demand, a request may wait in a queue before synthesis begins. This ensures stable processing but may introduce slight delays during peak usage times for large editorial teams generating multiple audio files simultaneously.
Setup and Onboarding
Getting started requires less than two minutes. Visit /get-api-key/ to create an account using your Google credentials or a standard email and password. This process is specific to playwin333.com and establishes your unique identity within the NewsVoice API ecosystem.
Once registered, you immediately receive a Bearer token. The dashboard displays your API key, current balance, and character usage statistics. You can begin sending POST requests to /v1/audio/speech instantly without waiting for manual approval or credit card verification.
Sign up with Google or email for API key
Accounts are created instantly via the /get-api-key/ page. You may choose Google authentication for speed or standard email/password for enterprise workflows. Each account is tied to the playwin333.com domain, ensuring clear separation from other storefronts in the network.
- Google OAuth or email/password registration
- Instant account creation
- Domain-specific account isolation
Free trial credit of $0.50 available
New accounts signed up with Google receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters of test audio to evaluate voice quality and integration speed before committing funds.
Accounts created via email and password start with zero balance and no trial credit. You must top up via USDT (TRC-20) on the TRON network to begin generating audio.
- $0.50 trial for Google sign-ups
- ~50,000 characters of test audio
- 7-day validity period
- No trial for email-only accounts
Instant key issuance and balance tracking
Your API key is generated immediately upon account creation. You can view your key, current balance, and character consumption directly on the dashboard. The key is active for POST requests to the API base URL without delay.
Balance does not expire. You can issue a new key at any time, which immediately invalidates the previous one. All transaction metadata is visible for auditing purposes, ensuring transparency for large editorial teams tracking usage.
- Immediate key activation
- Real-time balance dashboard
- Revocable key management
- Transparent usage metadata
Comparison to Manual Reading
Manual voiceover production requires scheduling talent, recording, and editing, a process that can take hours or days for a single news segment. Our API delivers audio in near real-time, with generation speeds averaging roughly one second per 25 characters of text. This allows editorial teams to produce audio assets on demand without waiting for studio availability.
Faster than human voiceover production
Human voiceover production involves booking studios, coordinating talent schedules, and post-production editing. Our API generates audio files directly from text, with typical speeds of roughly 25 characters per second of audio. This eliminates the logistical delays of traditional recording, allowing newsrooms to produce audio assets on demand without waiting for studio availability.
- Eliminates studio booking and talent scheduling delays
- Generates audio in seconds rather than hours
- No post-production editing required for standard scripts
Instant updates for changing news scripts
News scripts often change minutes before broadcast. With manual production, a script edit requires re-recording the entire segment. Our API allows editors to update text and regenerate audio instantly, ensuring the broadcast asset matches the latest editorial decisions without starting the production cycle from scratch.
Consistent tone across all languages
Maintaining brand voice across global editions is difficult with diverse human talent. Our eight voice presets, such as Atlas for neutral news or Orion for documentary style, ensure a consistent auditory identity. Since every voice supports all 23 languages, the same tonal quality is preserved whether the content is in English, Spanish, or Arabic.
- Uniform brand voice across 23 languages
- Eight preset voices for consistent tone
- No variation due to different talent
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.