Frequently asked questions
What is text-to-speech?
Text-to-speech (TTS) is a cloud API that converts plain text into audio files. You send text via a POST request and receive synthesized speech in formats like MP3, WAV, or FLAC. While usable by anyone, it is designed for government agencies and NGOs to make digital content accessible to multilingual communities without complex infrastructure.
How does text-to-speech work?
Send text via POST to /v1/audio/speech with your API key. The engine processes the input and returns an audio file. For texts over 4096 characters, split them into parts, generate each, and join the files. Requests are processed sequentially, so longer texts may queue under load.
Which languages are supported?
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 can speak any of these languages. If the language is not specified, it is guessed from the script.
What is the cost per character?
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spends, making it predictable for NGO budgeting.
Can I use my own voice?
No. We do not offer custom voice cloning, uploading your own voice, or voice design. You choose from eight presets based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech.
Is there a free trial?
Yes, signing in with Google provides $0.50 of credit (about 50,000 characters) valid for 7 days. Accounts created with email and password start without trial credit. Balance does not expire, and you can top up with USDT on the TRON network.
How do I get an API key?
Sign up on /get-api-key/ using Google or email plus password. The page displays your key, balance, and usage. Use the key in the Authorization header. You can issue a new key at any time, which immediately invalidates the old one.
What audio formats are available?
You can request MP3, WAV, OPUS, FLAC, or PCM formats by setting the response_format field. These formats ensure compatibility with various web players and accessibility tools used by government agencies and NGOs for public content distribution. The API accepts any of these five options directly in your request, allowing you to choose the best balance between file size and quality for your specific distribution needs.
Is there a rate limit?
Yes, the limit is 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures stable service for your integration.
Do you offer streaming?
No, we do not offer streaming, WebSocket, or real-time partial audio. The API returns the complete audio file after synthesis. This fits batch processing workflows common in government content updates, where teams download the generated files to store and distribute locally.
Is SSML supported?
No, SSML is not supported. We do not offer phoneme dictionaries, custom pronunciation lexicons, or emotion tags. You provide plain text, and the engine handles natural pacing. This keeps the API simple and reliable for straightforward text-to-audio conversion tasks.
Can I clone a voice?
No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design new voices. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each file includes an inaudible synthetic watermark.
Is there an SLA?
No, we do not offer an SLA, uptime guarantee, or enterprise contract. There is no on-premise install option or data-center choice. Support is by email only, with no phone number or live chat. This reflects our focus on a simple, reliable API.
How is data used?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Request metadata (time, characters, status) is kept for billing purposes. This ensures privacy for your content.
First request
curl
curl https://api.playfb7.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.mp3Making Digital Services Accessible
CivicVoice enables government agencies and NGOs to convert plain text into clear audio, ensuring digital content reaches multilingual communities without complex infrastructure. With support for 23 languages—including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish—teams can deliver accessible services to diverse populations.
Multilingual Support for Diverse Communities
Our API allows any voice to speak any of the supported languages. If the language field is omitted, the system guesses from the script, defaulting to English for Latin text. For non-English Latin-script content, explicitly setting the language ensures accuracy.
- Support for 23 distinct languages covering major global regions.
- Automatic language detection or explicit ISO code specification.
- No need for separate voice models per language.
Simple Integration for Civic Apps
The endpoint mirrors the OpenAI speech API shape, allowing teams to use existing OpenAI SDKs by simply changing the base_url. A single POST request with JSON body returns the audio file, making it easy to embed audio features into civic apps or websites without building custom synthesis infrastructure.
- RESTful API compatible with standard OpenAI SDKs.
- JSON body structure for easy integration.
- Standard HTTP requests with Bearer token authentication.
Transparent Pricing for Budget-Conscious NGOs
Pricing is straightforward: $10 per 1 million characters ($0.01 per 1,000 characters). Failed requests are free, and there are no monthly plans, seats, or minimum spends. New users receive a $0.50 trial credit valid for 7 days when signing in with Google.
- Pay only for characters processed.
- No hidden fees or subscription lock-ins.
- Crypto payments via USDT (TRC-20) for flexible budgeting.
Voice Options for Professional Communication
CivicVoice provides eight distinct voice presets tailored for professional communication, ensuring clarity and appropriate tone for diverse civic applications. These voices are grounded in licensed recordings, offering a reliable foundation for official content delivery without the need for complex infrastructure or custom voice design.
Clear Narration for Instructions
Aria offers a warm, clear narrator style ideal for step-by-step instructions. Nova provides a bright, upbeat tone suitable for engaging community updates. Sage delivers a calm, instructional voice perfect for educational materials or guided procedures.
For government digital services, these presets ensure that instructional content is delivered with clarity, helping diverse communities understand procedures without ambiguity.
- Aria: Warm, clear narrator
Calm Tone for News Updates
Luna’s soft, storytelling voice is well-suited for narrative-driven news updates or community stories. Milo’s friendly, conversational tone works well for approachable public service announcements.
Orion’s deep, documentary style provides a serious, authoritative presence for formal news broadcasts or detailed reporting.
Each voice can handle any of the 23 supported languages, allowing NGOs to maintain consistent tone across multilingual communities.
Neutral Voices for Official Announcements
Atlas delivers a neutral, news-style voice suitable for official announcements and factual reporting. Felix offers an energetic, promo-style voice for time-sensitive alerts.
These options allow agencies to select a tone that matches the gravity of the message, ensuring that official communications are received with the intended seriousness or urgency.
All voices are synthetic and carry an inaudible watermark, distinguishing them from human recordings while maintaining high audio quality.

Technical Specifications for Developers
CivicVoice provides a straightforward RESTful API compatible with the OpenAI SDK, requiring only a base_url change to https://api.playfb7.com/v1. Developers send a POST request to /v1/audio/speech with JSON containing the text, voice selection, and format preferences. The API returns the audio file directly, ensuring seamless integration into existing civic tech stacks without proprietary dependencies.
RESTful API with OpenAI Compatibility
Integration is simple: use the standard OpenAI SDK by pointing base_url to https://api.playfb7.com/v1 and passing your Bearer token. The request structure mirrors OpenAI’s speech endpoint, supporting models tts-1 and tts-1-hd. This allows developers to leverage familiar tools while accessing CivicVoice’s specific voice presets and multilingual capabilities.
Multiple Audio Formats for Web and Mobile
Choose from mp3, wav, opus, flac, or pcm to match your application’s needs. Mp3 and opus offer efficient compression for web delivery, while wav and flac provide lossless quality for archival or broadcast use. The pcm format is suitable for raw audio processing pipelines. This flexibility ensures compatibility across various government and NGO digital platforms.
Rate Limits and Request Handling
New accounts without a top-up are limited to 10 requests per minute. After the first top-up, this increases to 60 requests per minute. Requests are processed sequentially, so under heavy load, synthesis may queue. Failed requests incur no charge, ensuring cost efficiency for testing and production environments alike.
Use Cases in Public Sector
Government agencies and NGOs distribute vast amounts of text-based information, from health guidelines to civic instructions. Converting this plain text into clear audio files allows digital services to reach wider audiences without requiring complex infrastructure or specialized design teams.
The API accepts text inputs up to 4096 characters and returns audio files in formats like mp3 or wav. This straightforward workflow enables developers to integrate audio capabilities directly into existing civic applications or content management systems.
Converting Text Guides to Audio
Long procedural guides often exceed character limits. Developers split the text into parts of up to 4096 characters using their own logic, send each part to the API, and join the resulting audio files client-side. This approach ensures reliable delivery of detailed instructions without server-side complexity.
The process supports various tones, from calm instructional voices to neutral news readers, allowing agencies to match the audio style to the content type, whether it is a simple parking regulation or a complex health advisory.
- Split text into 4096-character chunks
- Send each chunk to the API
- Join returned audio files client-side
- Supports mp3, wav, opus, flac, pcm
Accessibility for Visually Impaired Users
Providing an alternative audio format helps make text-based information more accessible to users with visual impairments. By generating synthetic speech from existing web content, agencies can offer an immediate auditory alternative without waiting for professional studio recordings.
Each generated file carries an inaudible watermark marking it as synthetic speech, maintaining transparency about the content's origin. Input text is used only for synthesis and is not stored or used for training, respecting user privacy.
- Instant audio generation from existing text
- Inaudible synthetic watermark included
- Input text not used for training
- No long-term storage of generated audio
Language Learning for Non-Native Speakers
Non-native speakers benefit from hearing official announcements and guides in their preferred language. The API supports 23 languages, including English, Spanish, Chinese, and Arabic, allowing agencies to serve diverse linguistic communities effectively.
Developers can specify the language ISO code to ensure accurate pronunciation, avoiding reliance on automatic detection. This precision helps non-native speakers understand critical civic information, such as voting procedures or emergency alerts, without language barriers.
- Support for 23 languages
- Explicit language code setting recommended
- Clear pronunciation for official content
- Suitable for non-native speaker audiences
How It Works
Converting text to speech with CivicVoice is straightforward. You send a request to our API endpoint, and the system processes your input to generate clear audio. This simple workflow allows government agencies and NGOs to integrate voice capabilities into their digital services without managing complex infrastructure.
Send Text via API Endpoint
Use the standard POST method on https://api.playfb7.com/v1/audio/speech with a JSON body. You can use the OpenAI SDK by adjusting the base URL, or send a plain HTTP request. Include your model (tts-1 or tts-1-hd), the text input (up to 4096 characters), and your chosen voice.
- Endpoint: POST /v1/audio/speech
- Format: JSON
- Auth: Bearer token in header
Receive Audio File Instantly
The API returns the generated audio file directly in the response. You can choose formats like mp3, wav, opus, flac, or pcm depending on your needs. Failed requests are free, ensuring you only pay for successful synthesis. The audio is ready for immediate use in your application.
Handle Long Texts with Splitting
For texts exceeding 4096 characters, split the input into smaller parts and send each separately. The API returns individual audio files for each part. Your client application should then concatenate these files into a single continuous audio stream for playback. This ensures high-quality generation without character limit issues.
- Max 4096 characters per request
- Client-side concatenation required
- Join files for continuous playback

Languages Supported
CivicVoice supports 23 languages, ensuring your digital content reaches diverse communities without complex infrastructure. Any voice can speak any supported language, and the API automatically detects the language from the script if not explicitly set.
European Languages
We cover major European languages including English, French, German, Spanish, Italian, Portuguese, Russian, Polish, Dutch, Danish, Finnish, Swedish, Norwegian, Greek, and Turkish. For non-English Latin-script text, you should explicitly set the language parameter to ensure accuracy.
Asian Languages
Support includes Chinese, Japanese, Korean, Hindi, and Malay. This allows government agencies to provide clear audio instructions and news updates for multilingual communities without needing separate voice models for each region.
African and Middle Eastern Languages
We include Arabic, Hebrew, and Swahili to serve broader demographic needs. These languages are fully integrated into the same API endpoint, maintaining consistent pricing and technical behavior across all supported regions.
Pricing Overview
CivicVoice charges $10 per million characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you only pay for successful synthesis. The balance never expires, offering predictable costs for long-term projects.
Pay Per Character
The rate is $0.01 per 1,000 characters. This flat structure simplifies budgeting for NGOs and government agencies without hidden volume tiers or per-minute fees.
Free Trial Credit
Signing in with Google provides $0.50 in credit, valid for 7 days. This allows teams to test integration without immediate payment. Email-based accounts start without trial credit.
Crypto Payments
Top-ups are processed via USDT on the TRON network (TRC-20). The minimum deposit is $5, and funds are credited automatically within minutes. No invoices, VAT, or credit cards are required.
- Minimum top-up: $5
- Network: TRON (TRC-20)
- Auto-credit within minutes
Why Choose CivicVoice?
CivicVoice offers a straightforward pricing model for government and NGO budgets. You pay $0.01 per 1,000 characters, with failed requests refunded in full. There are no monthly subscriptions, seat fees, or minimum spend requirements. Top-ups via USDT (TRC-20) are processed automatically within minutes, and your balance never expires.
No Hidden Fees
We do not charge for voice selection or speed adjustments. The $10 per million character rate applies uniformly across all models and formats. Accounts start with a $0.50 free trial valid for seven days, allowing you to test the API before committing funds.
- Pay only for successful synthesis
Data Privacy Focused
Your input text is used solely to generate the audio file and is not used for training our models. The generated audio is returned in the response and not stored on our servers. We retain only request metadata, such as time and character count, necessary for billing purposes.
Editorial Transparency
We maintain clear records of all operations. Our voices are derived from licensed LibriTTS-R recordings and public-domain LibriVox readings. Every generated file contains an inaudible watermark marking it as synthetic speech, ensuring clarity about the content's origin for public accountability.

Get Started
Access the API quickly by creating an account on our /get-api-key/ page. You can sign in with Google for an immediate $0.50 trial credit, valid for seven days, or use an email and password. Once registered, your unique API key is displayed alongside your balance and usage statistics, ready for immediate integration into your civic applications.
Sign Up for API Key
Visit the /get-api-key/ page to register. Google sign-up provides instant trial credit, while email accounts start with a zero balance. Your key is issued immediately and can be rotated anytime.
View Documentation
Explore the /docs/ section for full technical details. The documentation covers all eight voice presets, supported formats, and rate limits (10 requests per minute before top-up, 60 after). It also includes ready-to-use curl examples for quick testing.
Contact Support
We offer support via email only. There is no phone number or live chat. For technical questions or billing inquiries regarding your API usage, please reach out through the contact form on our /contact/ page.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Simplify grant applications to empower indie developers navigating complex government and NGO funding landscapes effectively.
23 languages
Any voice speaks any of these languages.
