Frequently asked questions
Is the Hindi text-to-speech service truly free?
New accounts signing in with Google receive a $0.50 free trial, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password start without trial credit. After the trial or credit is exhausted, you must top up using USDT to continue using the service.
How many characters can I send in one request?
Each API request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer texts, you must split the content into parts of up to 4096 characters and join the resulting audio files after generation.
What audio formats does the API support?
The API supports five response formats: mp3, wav, opus, flac, and pcm. You can specify your preferred format in the request body. This allows flexibility for different playback environments, from web browsers to professional audio editing software.
Can I use the API for commercial NGO projects?
Yes, the API is designed for diverse audiences, including NGOs and public service teams. There are no restrictions on usage type. You pay based on characters used, with no monthly plans or seats required, making it suitable for project-based NGO work.
How do I pay with USDT?
Payments are made via USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Funds are credited automatically within minutes after your transfer is confirmed. There are no invoices, VAT, or credit card processing fees involved.
Is there a limit on how many requests I can make?
The rate limit is 60 requests per minute per API key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under heavy load, a request may wait in a queue before generation begins.
Do the voices sound natural in Hindi?
The eight voice presets can speak Hindi naturally. Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark that marks it as synthetic speech.
How long is my free trial valid?
The $0.50 free trial credit is valid for 7 days from the time you sign in with Google. If you create an account using email and password, you start without this trial credit. The balance does not expire after the trial period ends.
Can I change my API key if it gets compromised?
Yes, you can issue a new API key at any time from your account page. When a new key is issued, the old one stops working immediately. This ensures that if your key is compromised, you can secure your account instantly.
Are the voices licensed for public use?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generation. Failed requests do not consume your character limit or balance permanently.
Does the API support multiple languages simultaneously?
The API supports 23 languages, including Hindi. You can specify the language using an ISO code in the request. If not set, the system guesses the language from the script, defaulting to English for Latin text. You cannot mix languages in one request.
Can I adjust the speed of the Hindi audio?
Yes, you can adjust the speed between 0.25 and 4.0 times the normal rate. This allows you to slow down narration for clarity or speed up content for brevity. The speed parameter is included in the JSON request body.
Is there a character limit for long texts?
Each individual request is limited to 4096 characters. For texts longer than this, you must split the input into multiple requests. After receiving the audio files for each part, you join them to create the final complete audio file.
First request
curl
curl https://api.ex66.info/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.mp3Accessible Audio for Diverse Audiences
For NGOs and public service teams, audio bridges the gap between written policy and public understanding. Hindi serves over 600 million speakers globally, making it essential for inclusive communication in South Asia and diaspora communities. Delivering clear audio ensures your updates reach those who prefer listening over reading.
Why Hindi matters for global services
Reaching diverse audiences requires more than translation; it requires culturally resonant audio. Our API supports Hindi alongside 22 other languages, allowing you to distribute content in the native tongue of your beneficiaries without complex infrastructure.
Supporting low-literacy communities
Audio content lowers the barrier for individuals with limited reading proficiency. By converting text notices into clear speech, you ensure critical information about health, voting, or aid is accessible to everyone, regardless of their literacy level.
Compliance with digital accessibility standards
Providing audio alternatives helps meet digital accessibility requirements for public services. Synthetic speech offers a consistent, scalable way to offer text-to-speech capabilities without the cost of recording every update manually.
How the API Works
The API converts written text into clear audio files through a single endpoint. You send a JSON payload containing the text and voice preference, and the system returns the synthesized audio file, ensuring a straightforward workflow for public service teams.
Send text, receive audio
Simply POST your text to the speech endpoint. The system processes the request and returns the audio file in your chosen format, such as MP3, WAV, OPUS, FLAC, or PCM.
Compatible with OpenAI SDKs
The API uses the same request shape as the OpenAI speech endpoint. This means you can use official OpenAI SDKs by simply changing the base_url to our API domain.
- Works with standard OpenAI client libraries
- Easy migration for existing integrations
Simple JSON integration
Integration requires only a standard HTTP POST request with a JSON body. Define the model, input text, voice, and desired response format to receive your audio file instantly.
- Standard JSON structure
- Minimal code required
Voices and Languages
CivicSonic provides eight distinct voice presets, ranging from the warm, clear narrator Aria to the deep, documentary-style Orion. These voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings.
8 distinct voice presets
Our library includes four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). Each preset offers a unique tone, from bright and upbeat to calm and instructional, allowing NGOs to match the voice to their specific content type.
- Aria: Warm, clear narrator
23 languages supported
The API supports 23 languages, including English, Hindi, Spanish, and French. Any voice can speak any of these languages, enabling consistent audio production across diverse regions. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text.
Hindi voice capabilities
Hindi is fully supported across all eight voices, making it ideal for reaching low-literacy communities in India and abroad. The system accurately handles Hindi script, ensuring clear pronunciation for public service announcements and educational content.
Free Trial for NGOs
NGOs often operate with tight budgets and need to verify API reliability before committing to long-term infrastructure. Our trial removes the financial risk from your initial testing phase, allowing product teams to evaluate voice quality and integration speed using real-world public service content.
This approach ensures that your team can validate the solution's fit for diverse audiences without upfront capital expenditure.
7-day Google sign-in trial
Sign up using your existing Google account to activate the trial immediately. This streamlined process lets your team begin testing within minutes, ensuring rapid validation of the API for your specific use cases.
$0.50 credit included
You receive $0.50 of credit, which provides approximately 50,000 characters of generation. This volume is sufficient to test multiple voices, formats, and languages, including Hindi, without depleting your balance during initial evaluation.
No credit card needed
No payment method is required to start. This eliminates administrative friction for public sector teams who may have complex procurement processes, allowing immediate access to the API for proof-of-concept work.
Transparent Pricing
CivicSonic uses a straightforward character-based pricing model tailored for public service budgets. You pay only for what you generate, with no hidden fees or minimum commitments. This transparency helps NGOs forecast costs accurately when producing audio content for diverse audiences.
Failed requests are free, ensuring you are not charged for synthesis errors. There are no monthly plans, seats, or subscriptions to manage. Your balance never expires, allowing you to pause usage without losing funds.
$10 per million characters
The rate is $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this total, providing clear predictability for long-form content like news broadcasts or educational modules.
This model scales linearly. Whether you are generating short announcements or lengthy reports, the cost remains consistent and easy to calculate.
Pay-as-you-go model
There are no monthly plans, seats, or minimum spend requirements. You top up your account as needed and spend only what is required for your current projects.
Accounts created with email do not include trial credit, ensuring flexibility for various organizational structures.
USDT TRC-20 payments
Top-ups are processed via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes of transfer.
This method avoids traditional banking delays, invoices, or VAT complications. There are no subscriptions, and you can issue a new API key at any time without affecting your existing balance.

Technical Specifications
The API enforces a rate limit of 60 requests per minute per key, increasing to 10 per minute before the first top-up. Requests are processed sequentially, so under load, synthesis may queue briefly. Typical generation speed approximates real-time, producing roughly 25 characters of text per second for long texts, while short phrases may take a few seconds.
Request limits and rates
Each API key supports up to 60 requests per minute. Before the initial top-up, the limit is 10 requests per minute. Since requests are processed one after another, high-volume batches may experience slight delays due to queuing.
Audio formats available
You can choose between mp3, wav, opus, flac, or pcm formats via the response_format parameter. This allows flexibility for different deployment environments, from web players to archival storage.
Character limit per request
Each API call accepts up to 4096 characters of input text. For longer documents, split the text into chunks and join the resulting audio files. Spaces and punctuation count toward the character limit.
Use Cases for Public Sector
Public sector teams can automate the conversion of daily bulletins into audio, ensuring consistent delivery for radio streams or community boards without manual recording. This reduces production time while maintaining a professional, clear tone suitable for official communications.
Audio news broadcasts
Generate daily updates or emergency alerts quickly using the tts-1 or tts-1-hd model. The API handles the text-to-audio workflow, allowing teams to push audio files directly to broadcast endpoints or community speakers.
- Automate daily news bulletins
- Rapid emergency alert generation
- Consistent voice quality across broadcasts
Educational content creation
Convert written learning materials into audio format for low-literacy communities or students with visual impairments. With support for Hindi and 22 other languages, educators can distribute accessible content at scale.
- Support for diverse linguistic needs
- Accessible format for visual impairments
- Scalable content distribution
Multilingual announcements
Produce clear announcements in multiple languages for diverse populations. Use the language parameter to ensure accurate pronunciation in Hindi, Spanish, or Arabic, reaching residents who may not read the primary language fluently.
- Inclusive community communication
- Accurate language-specific pronunciation
- Support for 23 languages
Data Privacy and Licensing
CivicSonic prioritizes data integrity for public service workflows. Your input text is processed solely to generate the audio file and is not retained for training purposes. This ensures that sensitive community communications remain confidential and are not repurposed by the engine.
Input text not used for training
When you send text to the API, it is used exclusively for synthesis. We do not store or analyze your input content to improve our models, keeping your public announcements and internal drafts private.
Licensed voice recordings
All eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This provides a clear, legal foundation for using synthetic speech in your NGO or government projects without complex clearance.
No data storage of audio
Generated audio files are returned directly in the response and are not stored on our servers. Only request metadata—such as time, character count, and status—is kept for billing purposes, ensuring minimal data footprint.
- Input text used only for synthesis
- Audio files not stored post-delivery
- Metadata kept only for billing
Get Started Today
To begin using CivicSonic for your public service audio needs, visit the /get-api-key/ page on ex66.info. You can create an account instantly using your Google credentials, which also activates a free trial with $0.50 credit valid for seven days. This allows you to test the API without entering payment details.
Once registered, your unique API key is displayed on the dashboard alongside your current balance and usage statistics. You can generate a new key at any time, with the previous one stopping immediately. This key authenticates your requests to the API endpoint, ensuring secure access to the TTS engine.
Sign up with Google
Navigate to the /get-api-key/ page and select the Google sign-in option. This method provides immediate access to your account dashboard and activates the $0.50 free trial credit, valid for 7 days. No credit card is required to start testing the service.
- Instant account creation via Google OAuth
- Automatic activation of $0.50 trial credit
- No credit card required for sign-up
Generate your API key
Your API key is generated automatically upon login and displayed on the dashboard. You can view your balance, characters remaining, and usage data directly from this page. If needed, you can issue a new key at any time, which immediately invalidates the previous one.
- Key displayed immediately after login
- Real-time balance and usage tracking
- Instant key rotation with old key invalidation
Test with Hindi text
Use the provided curl example or OpenAI SDK to send a POST request to https://api.ex66.info/v1/audio/speech. Include your API key in the Authorization header and specify the desired voice and input text. The API returns the audio file directly in the response.
Ensure you set the language parameter if using non-English Latin script to ensure correct pronunciation. For Hindi, the system automatically detects the script, but explicit language codes are recommended for clarity. Test with short phrases first to verify audio quality and latency.
- POST request to /v1/audio/speech endpoint
- Include Bearer token in Authorization header
- Specify voice and input text in JSON body
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The platform is designed for large enterprises, often including features and support levels that small NGOs may not need.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriTTS-R paper (arXiv 2305.18802)
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
- LibriVox public-domain audiobooks
- Creative Commons Attribution 4.0
- ISO 639 language codes
- Python documentation
- curl documentation
- Node.js documentation
- openai-python on GitHub
- OpenAI API reference: create speech
