Frequently asked questions
What is Azure Text to Speech API?
Azure Text to Speech is a cloud service by Microsoft that converts text into natural-sounding speech. It offers various voices, languages, and customization options like SSML. It is a paid service with complex configuration, requiring developers to manage keys and endpoints for integration into applications.
How does SageVoice compare to Azure?
SageVoice uses the same API shape as OpenAI, making it easy to switch by changing the base URL. We offer simpler pricing at $0.01 per 1,000 characters with no monthly plans. Unlike Azure, we do not offer SSML or voice cloning, focusing instead on straightforward, reliable audio generation for assistive tech.
Is SageVoice easy to use for non-developers?
Yes. Our API is designed to be as easy as sending a text message. You can generate audio by sending a simple POST request with your text and voice choice. The /get-api-key/ page provides a ready curl example, allowing non-technical users to start generating speech without complex code or setup.
What 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 you do not set the language, it guesses from the script, defaulting to English for Latin text.
How much does SageVoice cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. You can start with a $0.50 trial credit valid for 7 days. Top-ups are made via USDT on the TRON network, with no monthly plans, seats, or minimum spend required for your account.
Can SageVoice handle long texts?
Yes, but you must split texts into parts of up to 4096 characters per request. You then join the resulting audio files. Typical generation speed is roughly real-time, about 25 characters per second. Requests are processed sequentially, so under load, a request may wait in a queue before processing begins.
Are the voices natural and clear?
We offer 8 presets based on licensed recordings from LibriTTS-R and LibriVox. Voices like Aria, Nova, Luna, and Sage provide clear, natural speech. Every generated file carries an inaudible watermark marking it as synthetic. The voices are designed for clarity, making them ideal for elderly care and accessibility tools.
How is data privacy handled?
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, characters, and status, strictly for billing purposes. We do not store the actual audio content after delivery.
What is the trial period?
New accounts signed in with Google receive $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. There is no monthly plan, so you only pay for what you use, with no minimum spend required.
How do I get started with SageVoice?
Go to /get-api-key/ and sign up with Google or email. You will receive a Bearer token to authenticate your requests. Use the provided curl example to send a POST request to https://api.twelve99.info/v1/audio/speech. You can top up your balance via USDT on the TRON network when needed.
Can I use SageVoice for assistive devices?
Yes. Our API is designed to generate clear, natural speech for assistive devices and elderly care tools. The simple JSON request format allows easy integration into no-code workflows. The reliable audio generation and transparent pricing make it suitable for building accessible applications without complex technical overhead.
Is there a limit on requests per minute?
Yes, the limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. This ensures fair usage and reliable processing. If you exceed the limit, requests may be queued or rejected. You can issue a new key if needed, stopping the old one immediately.
What formats can the audio be generated in?
You can choose from mp3, wav, opus, flac, and pcm formats. These options allow flexibility for different assistive devices and playback environments. Simply specify your preferred format in the request body. The audio is returned directly in the response, ready for immediate use in your application or device.
Does SageVoice offer voice cloning?
No, we do not offer voice cloning. We provide 8 preset voices based on licensed recordings. You cannot upload your own voice or design custom voices. This keeps the service simple and reliable. If you need a specific voice, choose from our existing presets like Aria, Felix, or Atlas.
First request
curl
curl https://api.twelve99.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.mp3Why Choose SageVoice for Assistive Tech?
SageVoice offers a straightforward Text-to-Speech API designed for non-technical users and assistive device makers. By matching the familiar structure of popular APIs, we make integration as simple as sending a text message, requiring no complex development teams to get started.
Our engine generates clear, natural speech optimized for elderly users. With transparent pricing based on character count, you avoid hidden fees and monthly subscriptions, ensuring reliable audio generation for care tools without unexpected costs.
Easy Integration for Non-Developers
Send text and receive an audio file with a single POST request. We support standard formats like MP3 and WAV, allowing easy integration into existing accessibility workflows without needing dedicated engineers.
No proprietary SDKs are required; use standard HTTP requests or familiar OpenAI-compatible libraries to start generating speech immediately.
- Single endpoint for audio generation
- Standard MP3, WAV, and OPUS formats
Clear Speech for Elderly Users
Our voices are designed for clarity and natural rhythm. The 'Sage' voice provides a calm, instructional tone ideal for guiding users through daily tasks, while 'Aria' offers a warm, clear narration for reading content.
Synthetic speech includes an inaudible watermark, ensuring transparency without affecting the listening experience for elderly users relying on clear audio cues.
Transparent Pricing Without Hidden Fees
Pay only $0.01 per 1,000 characters. There are no monthly plans, seats, or minimum spend requirements. Failed requests are free, so you only pay for successful audio generation.
Start with a free $0.50 trial valid for 7 days. Top-ups via USDT on the TRON network (TRC-20) are credited automatically, ensuring your balance never expires.
- $0.01 per 1,000 characters
- No monthly subscriptions or hidden fees
How It Compares to Azure Text to Speech API
While Azure offers extensive customization, SageVoice simplifies the process by providing a direct POST endpoint that accepts standard JSON. This structure mirrors the familiar OpenAI API format, allowing assistive device makers to integrate speech synthesis without learning complex proprietary schemas or managing intricate configuration trees.
Simpler API Structure
You send text and receive audio in a single request. There is no need to manage separate endpoints for voice selection or waveform generation. The API handles the conversion internally, returning a ready-to-play audio file that works seamlessly with existing hardware.
- Single POST endpoint for all synthesis tasks
- Standard JSON request body format
- No separate configuration endpoints required
Fewer Complex Configurations
Azure often requires setting multiple parameters for pitch, rate, and pronunciation. SageVoice reduces this to essential fields: model, voice, speed, and response_format. This minimal configuration reduces integration errors, making it easier for non-technical teams to deploy speech features in care robots or reading aids without deep XML or SSML knowledge.
Direct Audio Output
The API returns audio files directly in formats like MP3, WAV, or OPUS. There is no need for post-processing or converting raw PCM streams, though PCM is available as a format. This direct output ensures that assistive devices can play audio immediately, reducing latency and simplifying the hardware stack for elderly care applications.
Voices Designed for Clarity
Clear speech is critical for elderly users and assistive devices. Our voices are chosen for natural clarity and ease of understanding, ensuring that audio outputs remain accessible without complex configuration.
Each voice offers a distinct tone suitable for different assistive contexts, from storytelling to instructional guidance. All voices support 23 languages and can speak any language in the set.
Aria: Warm and Clear Narrator
Aria delivers a warm, clear narration style ideal for audiobooks and general reading tasks. Her tone is gentle and easy to follow, making her suitable for long-form content for elderly users.
- Warm, clear narrator tone
- Ideal for storytelling and books
- Supports all 23 languages
Nova: Bright and Upbeat
Nova provides a bright and upbeat voice, perfect for keeping users engaged during interactive assistive tasks. Her energetic tone works well for reminders or short alerts that need to capture attention.
- Bright, upbeat tone
- Good for alerts and reminders
- Supports all 23 languages
Sage: Calm and Instructional
Sage offers a calm, instructional voice designed for clarity during step-by-step guidance. Her steady pace and neutral tone help users understand instructions without distraction, making her ideal for care robots and reading devices.
- Calm, instructional tone
- Ideal for step-by-step guidance
- Supports all 23 languages
Supporting Multiple Languages
SageVoice supports 23 languages, ensuring clear speech for diverse elderly users and assistive device audiences. Whether your users speak Arabic, Hindi, or Spanish, our API delivers natural, understandable audio without complex configuration.
23 Languages Available
We cover major global languages including English, German, French, Japanese, and Korean. Any voice can speak any of these languages, allowing you to build inclusive assistive tools that serve a broad demographic without needing multiple voice engines.
- 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
If you do not specify a language, the system guesses it from the text script. Latin script defaults to English, but for other languages using Latin characters, you should set the language parameter to ensure accurate pronunciation.
Consistent Quality Across Languages
Our 8 voice presets maintain consistent clarity and tone across all supported languages. This reliability helps elderly users, who may struggle with varying audio qualities, understand instructions or news content clearly regardless of the language used.
Fast and Reliable Generation
SageVoice delivers audio at roughly real-time speed, processing about 25 characters of text per second for long passages. Short phrases may take a few seconds, ensuring natural pacing without unnecessary delay.
Real-Time Generation Speed
For most use cases, generation feels immediate. However, requests are processed sequentially, so high load may introduce brief queue waits.
Handling Long Texts Easily
Inputs up to 4096 characters are supported. The system automatically splits longer texts, synthesizes each part, and joins the audio files seamlessly for continuous playback.
Consistent Performance
Audio quality remains stable across all 23 supported languages. Failed requests incur no charge, ensuring you only pay for successfully generated audio.

Simple Pricing Model
SageVoice charges $0.01 per 1,000 characters, including spaces and punctuation. This straightforward metric ensures you only pay for what you generate, making budgeting predictable for assistive device projects.
Pay Per Character Used
Each request processes up to 4096 characters. Longer texts are split and joined automatically, so you pay only for the actual audio produced.
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free
No Monthly Subscriptions
There are no monthly plans, seats, or minimum spend requirements. Your balance does not expire, allowing you to top up only when needed.
Free Trial Available
Sign in with Google to receive $0.50 in credit, valid for 7 days. This covers approximately 50,000 characters for testing integration.
- Google sign-in required
- $0.50 initial credit
- 7-day validity period
Easy Setup Process
Getting started with SageVoice is designed to be as simple as sending a text message. You can create your account directly on our /get-api-key/ page using Google or your email. No complex contracts or credit card checks are required to begin your journey.
Once registered, you receive a unique API key instantly. This key allows you to access the API immediately, enabling you to start generating clear, natural speech for your assistive devices or elderly care tools without any technical overhead.
Get Your API Key Quickly
Sign up on our /get-api-key/ page using Google or email. You receive an API key immediately. Your balance and key are displayed clearly on your dashboard, ready for use.
- Google or email sign-up
- Instant API key generation
- Clear dashboard overview
Test with a Simple Request
Use the provided curl example to send your first request. The API accepts standard JSON bodies, making it compatible with tools you already know. You can test voice clarity and speed with a short phrase.
- Copy-paste ready curl example
- Standard JSON format
- Immediate audio response
Start Generating Audio Today
With your key active, you can begin generating audio for your assistive devices. Use the /v1/audio/speech endpoint to convert text into clear speech files. Start with the free trial credit to ensure it fits your needs.
- Use free trial credit
- Generate audio files instantly
- No setup delay
Data Privacy and Security
When you send text to generate speech, we use it only to create the audio file for that specific request. Once the audio is returned to you, we do not store the generated audio files or the original text. This ensures your content remains private and transient, used solely for the immediate synthesis task.
Text Used Only for Generation
Your input text is processed exclusively to produce the audio response. We do not retain the text or the resulting audio files after delivery, ensuring that your specific content does not persist in our systems beyond the immediate transaction.
No Training on Your Data
Unlike some services, we do not use your input text or generated audio to train our models. Your data remains yours, and we do not incorporate your specific content into our voice engine’s development corpus.
Secure API Connections
All API requests are transmitted over secure connections. We keep request metadata, such as time, character count, and status, strictly for billing purposes. This limited data allows us to accurately track your usage and ensure transparency in your account balance.
Support for Assistive Device Makers
SageVoice simplifies audio integration for assistive hardware, allowing makers to focus on device design rather than complex voice synthesis pipelines. By sending a simple POST request, your device receives a ready-to-play audio file without managing streaming protocols or custom SDKs.
Ideal for Care Robots
Care robots require clear, natural speech to guide elderly users. SageVoice’s models like Aria and Sage provide warm, instructional tones that feel less robotic than generic synthesizers.
- Supports 4096 characters per request for longer instructions
- Audio formats like WAV and PCM are widely supported by embedded systems
Suitable for Hearing Aids
For hearing aid audio processing, clarity is key. Our voices are optimized for natural cadence, ensuring that speech remains intelligible even for users with residual hearing loss.
- Multiple formats including MP3 and Opus for efficient bandwidth usage
- Consistent quality across 23 languages for diverse patient populations
Perfect for Reading Devices
Braille displays and talking books benefit from Sage’s calm, instructional voice. The API’s straightforward structure allows non-technical makers to integrate text-to-speech without deep engineering resources.
- No need for SSML or phoneme dictionaries
- Transparent pricing helps budget for hardware mass production
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The voice should sound warm and clear, avoiding harsh or monotone delivery that can cause listener fatigue over extended use.
23 languages
Any voice speaks any of these languages.
