Frequently asked questions
What is the best TTS API for NGOs?
CivicVoice is a reliable text-to-speech API designed for government agencies and NGOs to make digital content accessible. It helps teams convert plain text into clear audio for multilingual communities without complex infrastructure, offering straightforward integration via standard HTTP requests. It supports 23 languages and charges $0.01 per 1,000 characters, with no monthly plans or minimum spend.
How much does CivicVoice cost?
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 if synthesis fails, ensuring you only pay for successful audio generation.
Does CivicVoice support multiple languages?
Yes, we support 23 languages including English, Spanish, French, Arabic, Hindi, and Japanese. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, though setting it explicitly is recommended for non-English Latin text.
Can I use the OpenAI SDK with CivicVoice?
Yes. The endpoint matches the OpenAI speech endpoint shape. You can use the official OpenAI SDKs by changing the base_url to https://api.playfb7.com/v1 and using your CivicVoice key. This allows for easy integration with existing codebases familiar with the OpenAI format.
What audio formats are supported?
We support mp3, wav, opus, flac, and pcm formats. You can specify the desired format in the request body using the response_format field. This flexibility allows you to choose the best balance between file size and quality for your specific delivery needs.
Is there a free trial available?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API quality before committing to a top-up.
How do I top up my balance?
Top-ups are done via USDT on the TRON network (TRC-20) only. The minimum amount is $5. Credits are automatically added within minutes after the transfer is confirmed. We do not accept cards, PayPal, or offer subscriptions, keeping the process simple and direct.
Does CivicVoice store my input text?
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. We keep request metadata, such as time and characters, strictly for billing purposes and audit trails.
What are the rate limits?
You are limited to 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 fair usage across all accounts.
Which voices are available?
We offer eight presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). These voices are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech for transparency.
Is CivicVoice suitable for accessibility?
Yes, CivicVoice is designed to help teams convert plain text into clear audio for multilingual communities. By providing standard audio formats and multiple voice options, it serves as a practical tool for making digital content accessible to diverse audiences, including those with visual impairments.
How long does synthesis take?
Typical speed is roughly real time, generating about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed one after another, so under heavy load, a request may experience slight delays due to queuing.
Can I generate long texts?
Each request accepts up to 4,096 characters. For longer texts, you should split the input into parts of this size and join the resulting audio files. This approach allows you to generate full documents or lengthy articles efficiently using the API.
What payment methods are accepted?
We accept USDT on the TRON network (TRC-20) only. There are no credit cards, PayPal, or invoices with VAT. Balance does not expire, and there are no monthly plans or subscriptions. This crypto-only model simplifies international payments for global NGOs and agencies.
Is there a minimum spend?
There is no minimum spend for using the API. However, the minimum amount for a top-up is $5. You can use your balance for any number of requests, regardless of size, as long as you have sufficient credits to cover the cost.
Why NGOs Need TTS
CivicVoice provides a reliable text-to-speech API designed for government agencies and NGOs to make digital content accessible. Our solution helps teams convert plain text into clear audio for multilingual communities without complex infrastructure.
Accessibility Compliance
Modern standards require digital content to be accessible to diverse audiences, including those with visual impairments or reading difficulties. Converting plain text into audio files allows NGOs to meet these requirements efficiently. The API supports 23 languages, ensuring that non-English speaking communities can access information in their native tongue without manual recording.
Content Repurposing
NGOs often produce extensive reports, press releases, and educational materials. Transforming these documents into audio formats extends their reach to listeners who prefer auditory consumption. With a limit of 4,096 characters per request, longer texts can be split and joined seamlessly, preserving the narrative flow for complex reports.
Cost Efficiency
Operating with limited budgets requires precise spending. CivicVoice charges a flat rate of $0.01 per 1,000 characters, with no monthly fees or tiered structures. Failed requests are free, and there is no minimum spend. This pay-per-use model ensures that funds are used only for successful audio generation.
CivicVoice API Overview
CivicVoice offers a straightforward REST endpoint for converting text into high-quality audio. By sending a simple JSON payload to our API, organizations can generate speech files without managing complex infrastructure or deploying servers. The service handles the synthesis engine, returning standard audio formats ready for immediate use in websites, apps, or digital publications.
Simple REST Endpoint
Our API accepts text input and returns audio files via a single POST request. This simplicity allows development teams to integrate speech synthesis quickly, focusing on content delivery rather than backend complexity. The endpoint is designed to be reliable and easy to test, supporting standard HTTP methods and JSON bodies.
OpenAI SDK Compatibility
The request structure mirrors the OpenAI speech endpoint, allowing teams to use the official OpenAI SDKs by simply changing the base_url to https://api.playfb7.com/v1. This compatibility reduces integration friction, enabling existing codebases to connect with minimal code changes. Note that while the request shape is identical, the underlying inference engine differs from OpenAI’s models.
- Use standard OpenAI SDKs with updated base URL.
- Identical JSON request shape for
POST /v1/audio/speech. - Drop-in replacement for existing TTS integrations.
Transparent Pricing
Pricing is strictly usage-based at $10 per 1 million characters, or $0.01 per 1,000 characters. There are no monthly fees, subscription tiers, or hidden costs. Failed requests are free, ensuring you only pay for successful audio generation. This model aligns with NGO budgets, allowing predictable costs based on actual content volume.
- $0.01 per 1,000 characters.
- No monthly fees or subscriptions.
- Failed requests are free.

Voice Selection
The CivicVoice API provides eight distinct voice presets, allowing organizations to select the most appropriate tone for their specific content needs. Each voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring high-quality, natural-sounding speech for diverse audiences.
These presets cover a range of tones, from warm narrators to energetic promos, enabling NGOs to tailor their audio content effectively without requiring custom voice design or expensive production resources.
8 Distinct Presets
Our API offers eight specific voice options, each with a defined character. This variety ensures that your audio content matches the context, whether you are producing news updates, educational materials, or promotional announcements.
The voices are designed to be clear and distinct, helping listeners distinguish between different types of content in multilingual community broadcasts.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Gender and Tone Variety
The selection includes four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). This balance allows teams to choose voices that best fit their brand identity or the preferences of their target communities.
Each voice carries a specific tonal quality, from the deep, documentary style of Orion to the bright, upbeat nature of Nova, providing flexibility for different types of public service announcements.
Consistent Quality
All voices are generated from the same underlying engine, ensuring consistent audio quality across all presets. This consistency is crucial for organizations producing large volumes of content, as it maintains a uniform listening experience.
Every generated file includes an inaudible watermark to mark it as synthetic speech, helping maintain transparency with your audience without affecting the audio quality.
Language Support
CivicVoice supports 23 languages, enabling NGOs to reach diverse communities effectively. This range includes major global languages like English, Spanish, and Hindi, as well as regional languages such as Swahili and Malay, ensuring broader accessibility for multilingual populations.
23 Languages Available
Our API covers Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This selection allows organizations to produce content for a wide variety of linguistic groups without needing separate infrastructure for each language.
- Arabic, Chinese, Danish, Dutch, English
- Finnish, French, German, Greek, Hebrew
- Hindi, Italian, Japanese, Korean, Malay
- Norwegian, Polish, Portuguese, Russian, Spanish
- Swahili, Swedish, Turkish
Multi-Script Support
Each voice can speak any of the 23 supported languages, regardless of script. Whether your audience reads Latin, Cyrillic, Arabic, or Asian scripts, the API handles the phonetic rendering accurately. This flexibility simplifies content creation for regions with multiple writing systems.
Automatic Language Detection
If the language field is omitted, the API guesses the language from the script. Latin text defaults to English. For non-English Latin-script text, you should explicitly set the language code to ensure accuracy. Unsupported languages like Vietnamese or Thai are not available.
Pricing for Non-Profits
CivicVoice offers a straightforward pricing structure designed for organizations with variable usage patterns. At $0.01 per 1,000 characters, costs remain predictable regardless of the volume of text converted to speech. This flat rate applies equally to standard and high-definition models, ensuring no hidden fees for higher quality audio.
$0.01 per 1,000 Characters
The base cost is calculated per character, including spaces and punctuation. For context, the free trial provides $0.50 credit, allowing approximately 50,000 characters of synthesis. This rate applies to both the 'tts-1' and 'tts-1-hd' models, meaning you can upgrade quality without changing your budget expectations.
No Monthly Fees
Unlike many competitors, there are no recurring subscription charges or minimum monthly commitments. You only pay for what you use. If your NGO has a quiet month with minimal audio generation, your bill reflects that zero usage. This flexibility is ideal for project-based funding cycles.
Pay-Per-Use Model
The pay-per-use model ensures you retain full control over your budget. Failed requests are free, so you only pay for successful audio generations. You can top up your balance with USDT on the TRON network whenever needed, with no expiration on the remaining credit.
Integration Guide
Integrating CivicVoice into your NGO’s digital workflow requires sending a POST request to the speech endpoint. The API accepts a JSON body containing the text, voice selection, and desired audio format, making it straightforward to automate content generation for multilingual communities.
JSON Body Format
Send a POST request to https://api.playfb7.com/v1/audio/speech with a JSON payload. Include the model ("tts-1" or "tts-1-hd"), the input text (up to 4096 characters), and the voice preset. You can also specify response_format (mp3, wav, opus, flac, pcm) and speed (0.25–4.0).
Authentication with Bearer Token
Include your API key in the Authorization header as Bearer tts-.... Each account holds one active key; issuing a new one immediately invalidates the old one. Ensure your key is securely stored in your application’s environment variables to prevent unauthorized usage of your character balance.
Quick Start with cURL
Test the endpoint immediately using cURL. Replace [YOUR_API_KEY] with your actual key from the dashboard. This command sends a short English text using the "nova" voice and returns the audio file directly in your terminal or script output for immediate verification.
- curl -X POST https://api.playfb7.com/v1/audio/speech \
- -H "Authorization: Bearer [YOUR_API_KEY]" \
- -H "Content-Type: application/json" \
- -d '{"model": "tts-1", "input": "Hello world", "voice": "nova", "response_format": "mp3"}'
Audio Formats
The API allows you to select the output format via the response_format parameter, giving you control over file size and compatibility. You can choose between MP3, WAV, OPUS, FLAC, or PCM based on your specific deployment needs.
Each format serves a distinct purpose, from lightweight web delivery to lossless archival. The choice affects file size and processing time but does not alter the voice quality or language support.
MP3 for Web
MP3 is the standard choice for web playback due to its broad browser support and efficient file size. It is ideal for embedding audio players in NGO websites or mobile apps where bandwidth conservation is important.
While MP3 provides good compression, it is used for standard playback rather than real-time streaming protocols, as the API returns complete audio files upon request completion.
- Supports standard web audio players
- Balances quality and file size
- Ideal for on-demand playback
WAV for High Quality
WAV provides uncompressed, lossless audio data, ensuring the highest fidelity for your generated speech. This format is suitable for professional editing workflows or archival storage where no data loss is acceptable.
The trade-off is a significantly larger file size compared to compressed formats. WAV files are best when you need to process the audio further in post-production.
- Uncompressed audio data
- Lossless quality
- Best for editing and archiving
OPUS and FLAC Options
OPUS offers advanced compression, making it suitable for efficient storage and transmission over networks. FLAC provides lossless compression, reducing file size while preserving exact audio quality.
Both formats are valid options for specific use cases where standard MP3 or WAV do not meet your technical requirements. Select the format that best aligns with your infrastructure constraints.
- OPUS: efficient compression
- FLAC: lossless compression
- Alternative formats for specific needs
Rate Limits and Performance
The API enforces a strict limit of 60 requests per minute per key, with a lower threshold of 10 requests per minute for accounts before their first top-up. This predictable ceiling ensures stable performance for integration pipelines, though it requires careful planning for high-volume batch operations.
60 Requests Per Minute
Each API key allows up to 60 requests per minute. Before the first top-up, this limit drops to 10 requests per minute. This structure supports steady integration without sudden drops, provided clients respect the per-key constraint.
- 60 requests/minute after top-up
- 10 requests/minute before first top-up
- Per-key limit, not per IP
Queue Processing
Requests are processed sequentially. Under heavy load, a request may wait in a queue before synthesis begins. Clients should account for this latency when designing their submission workflows.
Real-Time Generation Speed
Generation speed is roughly real-time, processing about 25 characters of text per second of audio produced. Short phrases may take a few seconds to complete, while long texts generate proportionally longer durations.

Data Privacy
CivicVoice processes your input text strictly to generate the requested audio file. We do not use your content to train or improve our underlying models, ensuring that sensitive community data remains yours.
No Training on Input
Your text is used solely for synthesis and is not retained for model training. This ensures that your specific content, whether it’s public notices or internal reports, remains distinct from our training dataset.
No Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. This minimizes the risk of data retention issues for time-sensitive NGO communications.
Metadata for Billing Only
We retain only request metadata—such as timestamp, character count, and status—for accurate billing purposes. This data is kept minimal and is not used for analytics or profiling your usage patterns.
Payment Methods
CivicVoice uses a straightforward payment model designed for operational efficiency. Top-ups are processed exclusively via USDT on the TRON network (TRC-20). This method ensures that funds are credited automatically within minutes of transfer, allowing your team to start generating audio without administrative delay.
USDT on TRON Network
We accept only USDT on the TRON network. This cryptocurrency standard avoids the friction of traditional banking systems and international wire fees. Transfers are verified on-chain, ensuring that your account balance updates reliably and quickly.
- Supported network: TRON (TRC-20)
- Currency: USDT (Tether)
- Auditable on-chain transactions
Minimum $5 Top-Up
The minimum top-up amount is $5. There is no maximum limit, and your balance never expires. This low entry point allows small NGOs to test the service with minimal upfront commitment.
No Credit Cards
We do not accept credit cards, PayPal, or maintain monthly subscriptions. There are no invoices with VAT to manage. This simplifies accounting for non-profits that prefer direct crypto transfers over traditional merchant processing fees.
Comparison with Alternatives
Comparing civic voice against established providers clarifies our specific value for non-profits and government agencies. We focus on transparent, per-character pricing without hidden infrastructure costs, while maintaining compatibility with standard developer tools.
We avoid subjective claims about setup complexity. Instead, we highlight concrete differences in pricing models, language support, and voice selection that directly impact budget and accessibility goals for digital content creation.
vs. OpenAI TTS
Our API uses the same request shape and model names (tts-1, tts-1-hd) as OpenAI, allowing you to switch by changing the base_url. However, we are not affiliated with OpenAI and use our own inference engine. We offer 23 languages with 8 distinct voice presets, whereas OpenAI’s selection is more limited.
We charge $0.01 per 1,000 characters with no monthly fees. Unlike OpenAI’s tiered subscription models, our pay-per-use structure aligns better with variable NGO budgets. Failed requests are free, ensuring you only pay for successful audio generation.
- Same JSON body format as OpenAI Speech endpoint
- Not affiliated with OpenAI
- $0.01 per 1,000 characters, no monthly fees
- 23 languages vs. OpenAI's smaller set
vs. ElevenLabs
CivicVoice provides 8 licensed voice presets from LibriTTS-R and LibriVox sources. While ElevenLabs is known for advanced voice cloning, we do not offer custom voice cloning or emotion tags, keeping the product simple and predictable.
Our pricing is straightforward: $10 per million characters. ElevenLabs often involves complex tiered plans. We support 23 languages with consistent quality across all voices, avoiding the need for multiple subscriptions to cover diverse community needs.
- 8 distinct presets, no custom cloning
- Simple per-character pricing
- 23 languages supported
- Licensed voices from public domain sources
vs. Google Cloud TTS
Google Cloud TTS often requires complex setup and infrastructure management. CivicVoice offers a simple REST endpoint with standard HTTP requests, reducing integration overhead for indie developers and small teams.
We do not charge for storage or per-voice configuration. Our API returns audio directly in the response, with no audio stored on our servers. This simplifies compliance and reduces long-term costs for government agencies handling sensitive content.
- Simple REST endpoint
- No storage costs
- Direct audio response
- No complex infrastructure management
Getting Started
CivicVoice offers a straightforward path for NGOs to begin using text-to-speech technology. The process is designed to be immediate and low-friction, allowing teams to focus on content rather than complex infrastructure setup.
Sign Up with Google
Navigate to the /get-api-key/ page and authenticate using your Google account. This method creates an instant account specific to the playfb7.com domain, providing immediate access to your API dashboard without waiting for email verification.
Free Trial Credit
Upon signing in via Google, you receive $0.50 of trial credit, valid for seven days. This allowance covers approximately 50,000 characters, allowing you to test voice quality and integration limits before committing to paid usage.
Generate Your First Audio
Use the provided curl example on your dashboard to send a POST request to the speech endpoint. By specifying a model like tts-1 and a voice such as aria, you receive an audio file directly in the response, ready for immediate deployment.
Support and Contact
Support for CivicVoice is handled exclusively via email. There is no phone number, live chat, or ticketing system to navigate. This approach keeps our operational costs low, allowing us to maintain our affordable per-character pricing model for non-profits and government agencies who need reliable access without premium support overhead.
Email Support
Send your inquiries to [email protected]. We handle all questions regarding billing, API limits, or integration issues through this single channel. While we do not guarantee a specific response time, our team reviews all messages and provides clear, factual answers to help you resolve issues efficiently.
- Email only: [email protected]
Documentation
Our documentation provides the essential technical details for integration. It includes the standard request shape for the /v1/audio/speech endpoint, authentication requirements, and a ready-to-use cURL example directly on your dashboard. The guides cover voice selection, language codes, and response formats without unnecessary complexity.
FAQ
Frequently asked questions address common concerns about character limits, voice selection, and payment methods. You will find clear explanations on how to split long texts, why spaces count as characters, and how USDT top-ups are processed. The FAQ is updated whenever we make changes to the API or pricing structure.

Conclusion
CivicVoice offers a straightforward, pay-per-use text-to-speech API tailored for NGOs and government agencies. With transparent pricing at $0.01 per 1,000 characters and no monthly fees, teams can allocate resources efficiently without complex infrastructure or hidden costs.
Reliable Infrastructure for Accessibility
The API provides consistent audio quality across 23 languages and 8 distinct voices. By handling text splitting and format conversion, it allows NGOs to focus on content rather than technical details, ensuring multilingual communities receive clear audio accessible on any device.
Simple Integration
Using standard REST endpoints compatible with OpenAI SDKs, developers can integrate speech synthesis quickly. Authentication via Bearer token and JSON-based requests make it easy to add voice capabilities to existing digital platforms or mobile apps without significant code changes.
Get Started Today
Create an account to receive a free trial credit of $0.50, valid for seven days. This allows you to test the API with up to 50,000 characters before committing to a top-up via USTRC-20. No credit card is required to begin.
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.
