Human Like AI Voice API for Accessible Public Content

By SayGov editorial team · Updated 2026-11-19

On this page, you will find a practical overview of the SayGov API, designed specifically for indie developers building accessibility tools and public information systems. We provide a straightforward, transparent way to generate human-like audio from text, helping you make content accessible to visually impaired users and non-native speakers without the complexity of enterprise contracts.

You will learn how to integrate synthetic voice into your workflows using standard endpoints, explore our voice catalog and language support, and understand the simple pay-per-character pricing model. This guide covers the technical details, pricing, and use cases relevant to public services and NGOs, so you can quickly evaluate if this API fits your project needs.

Human Like AI Voice API for Accessible Public Content

Frequently asked questions

What makes this voice human-like?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain LibriVox audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech. The eight presets cover warm narrators, upbeat speakers, and deep documentary styles to suit various accessibility needs.

Can I use this voice for commercial projects?

Yes. The underlying voices are based on LibriTTS-R (CC BY 4.0) and public-domain LibriVox readings, which allow commercial use. You can integrate these voices into your public information systems or accessibility tools without additional licensing constraints beyond the API usage fees.

How many 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, and the system guesses the language from the script if not specified.

Is my input text used for training?

No. 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 (time, characters, status) solely for billing purposes.

What audio formats are available?

You can choose from mp3, wav, opus, flac, and pcm. These formats are specified in the response_format field of the JSON request body. All formats are generated via the standard POST endpoint with the same request shape as the OpenAI speech endpoint.

Do I need to split long texts?

Yes. The API accepts up to 4096 characters per request. For longer texts, you must split the content into parts of up to 4096 characters, generate audio for each part, and then join the resulting audio files.

How fast is the audio generation?

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 sequentially, so under load, a request may wait in a queue before processing begins.

Can I change my API key if lost?

Yes. You can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. Each account has one active key at a time.

Is there a free trial available?

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. Failed requests are free, so you can test without charge.

How do I pay with USDT?

Top-ups are accepted via USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after your transfer is confirmed. There are no monthly plans, subscriptions, or invoices with VAT.

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 successfully generated audio files. You can retry the request or adjust parameters like speed or voice.

Can I clone my own voice?

No. We do not offer custom voice cloning, uploading your own voice, or voice design. You must choose from the eight available presets: aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice has a specific tone and style.

Do you offer SSML support?

No. We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. The API accepts plain text input. You can control speed and voice, but not detailed prosody or pronunciation markers via SSML tags.

Is there a phone support number?

No. We do not offer a phone number or live chat. Support is provided by email only. You can reach us via the contact page or by emailing the support address provided in your account dashboard.

First request

curl

curl https://api.b777x.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.mp3

Why choose synthetic voice for public information

Sound wave illustration for: Why choose synthetic voice for public information

Synthetic voice transforms static public notices into accessible audio, ensuring compliance for visually impaired users and non-native speakers without complex infrastructure. Our API delivers human-like clarity at scale, making government and NGO information available to everyone, regardless of literacy or language barriers.

We provide a straightforward, transparent API for generating audio from text without the complexity of enterprise contracts. This approach allows indie developers to integrate voice capabilities directly into existing public service platforms, ensuring consistent and reliable delivery of critical information.

subsections

Voice catalog for clear communication

Sound wave illustration for: Voice catalog for clear communication

Choose the right voice for your public content. Our eight presets cover every communication need, from clear news updates to warm storytelling.

Each voice is derived from licensed recordings, ensuring a consistent and professional tone across all your materials.

Neutral and instructional voices for news

Neutral and instructional voices for news

Atlas delivers a neutral, news-ready tone perfect for public announcements. Sage provides a calm, instructional voice ideal for detailed guidance and procedural explanations.

  • Atlas: Neutral, news-style delivery
  • Sage: Calm, instructional clarity

Warm and storytelling voices for engagement

Aria offers a warm, clear narrator style for engaging content. Luna adds a soft, storytelling quality that helps connect with diverse communities on an emotional level.

  • Aria: Warm, clear narration
  • Luna: Soft, storytelling engagement

Consistent tone across all languages

Every voice speaks all 23 supported languages with the same character. This ensures brand consistency whether your audience is in English, Spanish, or Hindi.

Use the same voice for a series of public notices to maintain recognition and trust.

  • All voices support all 23 languages
  • Uniform tone across regions

How the API works

Sound wave illustration for: How the API works

The TTS API converts text into audio files via a simple POST request to the standard speech endpoint. You send a JSON body containing the model, input text, voice selection, and desired format, and receive an audio file in response. This straightforward flow allows you to generate speech for public notices, accessibility content, or informational updates without complex infrastructure.

Send text, receive audio files instantly

Input text up to 4,096 characters is processed to produce synthetic speech, provided the model is specified. For longer content, split the text into chunks and join the resulting audio files. Generation typically takes a few seconds for short phrases, scaling to roughly real-time for longer texts.

  • Endpoint: POST /v1/audio/speech
  • Max input: 4,096 characters per request
  • Format: JSON body with input, voice, and model fields

Support for standard audio formats

The API returns audio in common formats including MP3, WAV, OPUS, FLAC, and PCM. Choose the format that best suits your accessibility requirements or bandwidth constraints. Failed requests incur no charge, ensuring you only pay for successful audio generation.

  • Supported formats: mp3, wav, opus, flac, pcm
  • No storage of generated audio after delivery
  • Inaudible watermark marks synthetic speech

Simple integration with existing tools

The endpoint mirrors the OpenAI speech API structure, allowing immediate use with official OpenAI SDKs by adjusting the base_url to https://api.b777x.info/v1. Authenticate with your API key sent as a Bearer token in the Authorization header. This compatibility simplifies integration into existing web or mobile applications.

  • Compatible with OpenAI SDKs
  • Auth: Authorization: Bearer <key>
  • Base URL: https://api.b777x.info/v1

Supported languages and regions

Sound wave illustration for: Supported languages and regions

Supporting 23 languages allows public services to reach diverse communities without managing separate voice assets. Any voice can speak any of these languages, ensuring consistency across all content types.

23 languages for global reach

Our API supports 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 broad coverage helps NGOs communicate effectively with non-native speakers and local populations alike.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Automatic language detection

The API guesses the language from the script if you do not specify it. Latin script defaults to English, but setting the language parameter is recommended for non-English Latin text to ensure accuracy.

Manual language override for clarity

For precise control, set the language field to an ISO code. This overrides automatic detection, which is useful when mixing scripts or ensuring correct pronunciation in multilingual public notices.

Note: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and other languages are not supported.

Pricing model for nonprofits

Sound wave illustration for: Pricing model for nonprofits

Access transparent, usage-based pricing designed for budget-conscious organizations. Our model charges strictly per character processed, ensuring you only pay for what you actually generate. This structure eliminates the risk of paying for unused capacity during slow periods, making it ideal for variable public information workflows.

Pay per character usage

Costs are calculated at $0.01 per 1,000 characters, with spaces and punctuation included. Failed requests incur no charge, protecting your budget during peak usage or network issues.

No monthly fees or subscriptions

Unlike enterprise contracts, there are no minimum spend requirements, seat limits, or recurring subscription costs. You maintain full control over your spending, scaling up or down based on your public information needs.

Transparent billing with USDT (TRC-20)

Top-ups are processed via USDT on the TRON network (TRC-20) with a $5 minimum. Balances are credited automatically within minutes and never expire. We do not offer invoices with VAT or traditional payment methods, keeping the process simple and direct.

Pricing model for nonprofits

Technical reliability

Sound wave illustration for: Technical reliability

Reliable infrastructure ensures your public information tools remain accessible during high-demand periods. The API uses a standard RESTful endpoint structure, making it straightforward to integrate with existing government or NGO web systems without requiring custom middleware or complex protocol adapters.

Performance is maintained through predictable rate limits, ensuring stable delivery of audio files even under load. Input text is used solely for synthesis and is not retained for training, providing clear data privacy for sensitive citizen information.

Standard API endpoint structure

The service exposes a single primary endpoint for speech generation: POST https://api.b777x.info/v1/audio/speech. This follows a familiar JSON body pattern, allowing you to send text, select a voice, and specify audio formats in a single request. Metadata such as character count and status are logged for billing but do not affect the audio output itself.

Response formats include mp3, wav, opus, flac, and pcm, covering compatibility with most web players and accessibility tools. Requests are processed sequentially, meaning long texts may queue briefly but are guaranteed to complete without data loss or corruption.

Rate limits for stable performance

Each API key is limited to 60 requests per minute, with a initial threshold of 10 requests per minute until the first top-up. This design prevents sudden traffic spikes from overwhelming the synthesis engine, ensuring consistent latency for public-facing applications.

Long texts exceeding 4,096 characters are split into segments by the client application. The client application can join the resulting audio files seamlessly, maintaining a continuous listening experience for users accessing public notices or educational content.

No data training for privacy

Input text is processed exclusively to generate the requested audio file and is not used to train future models. This ensures that specific public notices or citizen data remain private and are not repurposed for algorithmic improvements without consent.

Generated audio is returned directly in the response and is not stored on our servers after delivery. Only request metadata—such as timestamp, character count, and status—is retained for billing purposes, minimizing the data footprint associated with your public services.

Integration for developers

Sound wave illustration for: Integration for developers

Integration is straightforward because the API follows the standard OpenAI request shape. You can use the official OpenAI SDKs by simply changing the base_url to https://api.b777x.info/v1 and providing your site-specific key. This allows indie developers to leverage existing client libraries without learning a new protocol.

OpenAI SDK compatibility

The endpoint POST /v1/audio/speech accepts the same JSON body structure as OpenAI’s speech endpoint. This means you can swap the base URL in your existing OpenAI integration code with minimal changes, ensuring quick adoption for tools already built around that standard.

cURL examples for quick start

For immediate testing, use cURL to send a POST request with your bearer token. The request body includes the model, input text, voice preset, and desired response format. This method requires no external libraries, making it ideal for quick validation of voice quality and latency.

JSON request body structure

The JSON body requires model ("tts-1" or "tts-1-hd"), input (text up to 4096 characters), voice (one of 8 presets), and response_format. Optional fields include speed (0.25–4.0) and language (ISO code). Optional fields include speed (0.25–4.0) and language (ISO code). Failed requests return zero charge, ensuring cost predictability during development.

Use cases in public sector

Sound wave illustration for: Use cases in public sector

The API enables rapid conversion of public notices into audio, ensuring compliance with accessibility standards for visually impaired users without manual recording costs.

Audio versions of public notices

Generate MP3 or WAV files for council updates, emergency alerts, or service changes. The API handles up to 4096 characters per request; longer documents must be split by the client application.

  • Supports 23 languages for diverse communities
  • Automatic language detection or manual override
  • No minimum spend for occasional updates

Voice assistants for information desks

Integrate synthetic voices into kiosk systems or phone trees. Use neutral voices like Atlas for news or Milo for conversational queries, ensuring clear, consistent tone across all interactions without hiring voice actors.

  • 8 distinct voice presets available
  • Speed adjustment from 0.25x to 4.0x
  • Approximate real-time synthesis for interactive responses

Educational content for schools

Convert textbooks, reading lists, or exam instructions into audio. With voices like Luna for storytelling or Sage for instructional content, schools can support non-native speakers and students with reading difficulties effectively.

  • Clear, human-like narration
  • Supports multiple audio formats
  • Privacy: text not used for training

Get started with a trial

Sound wave illustration for: Get started with a trial

Start by creating an account on the /get-api-key/ page using your Google credentials. This method provides an instant $0.50 trial credit, valid for 7 days, allowing you to generate approximately 50,000 characters of audio immediately. Alternatively, you can sign up with an email and password, though this option does not include the initial trial balance.

Once registered, your account dashboard displays your unique API key, current balance, and a ready-to-use cURL example. You can regenerate your key at any time, with the previous one stopping instantly. This straightforward setup ensures you can begin testing accessibility features without complex enterprise contracts or billing delays.

Sign up with Google for instant credit

Select the Google sign-in option on the /get-api-key/ page to receive $0.50 in trial credit immediately. This credit is valid for 7 days and covers about 50,000 characters, giving you ample room to test voice quality and integration speed without financial commitment.

Accounts created via email do not receive this trial credit. If you prefer email authentication, you can top up later using USDT on the TRON network, with a minimum deposit of $5 credited automatically within minutes.

  • Instant $0.50 credit for Google sign-ups
  • Valid for 7 days
  • Covers ~50,000 characters
  • No email trial credit

Generate your API key

Your account dashboard on /get-api-key/ displays your active API key, starting with 'tts-'. This single key authenticates all requests to the API endpoint. You can issue a new key at any time, which immediately invalidates the old one, ensuring tight security control.

Use the key in the Authorization header as 'Bearer tts-...'. The dashboard also shows your current balance and character usage, helping you track consumption during your trial period without needing external billing tools.

Test with sample text

Send a POST request to https://api.b777x.info/v1/audio/speech with your key, a model (tts-1 or tts-1-hd), and sample text. The API returns an audio file in your chosen format (mp3, wav, opus, flac, or pcm). For texts over 4096 characters, split them into parts and join the resulting audio files.

Use the provided cURL example from the dashboard to verify connectivity. Check the response for the audio data or any error codes. Failed requests incur no charge, allowing you to experiment freely with different voices and languages.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Allow users to choose their preferred voice or disable audio entirely.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. W3C WAI: making audio and video accessible
  3. OpenAI API reference: create speech
  4. Tether (USDT)
  5. TRON developer hub: TRC-20
  6. LibriTTS-R corpus (OpenSLR 141)
  7. openai-python on GitHub
  8. LibriVox public-domain audiobooks
  9. curl documentation
  10. Python documentation
  11. LibriTTS-R paper (arXiv 2305.18802)
  12. IETF RFC 7845: Ogg Opus

More on this site