Frequently asked questions
What is the TTS API?
VoxEd is a cloud text-to-speech API where you send text and receive an audio file. It uses a standard JSON request shape compatible with OpenAI SDKs by changing the base URL to https://api.bet4x.top/v1. You can generate speech using simple scripts, making it ideal for educational content creation workflows.
How do I use the API?
Send a POST request to https://api.bet4x.top/v1/audio/speech with your API key in the Authorization header. Include the text in the input field, select a model like tts-1, and choose a voice. The API returns the generated audio file directly in the response for immediate use in your applications.
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 public-domain audiobook readings. Each voice offers distinct tones suitable for various educational contexts, from storytelling to instructional content.
Which languages are supported?
We support 23 languages including Arabic, Chinese, English, French, German, Hindi, Japanese, Spanish, and more. Any voice can speak any supported language. If the language parameter is omitted, the system guesses the language, defaulting to English for Latin script text. Vietnamese, Thai, Indonesian, Ukrainian, Romanian, Czech, and Bengali are not supported.
How much does it cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. There are no monthly plans, seats, or minimum spend requirements. You only pay for the characters you actually process, making it cost-effective for varying usage volumes.
How do I pay?
We accept USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Credits are added automatically within minutes after your transfer is confirmed. We do not process credit cards, PayPal, or issue invoices with VAT. Your balance does not expire.
Is there a free trial?
Yes, signing in with Google provides $0.50 in trial credit, valid for 7 days. This allows approximately 50,000 characters of generation. Accounts created with an email and password do not receive this trial credit. The trial is a one-time offer per account.
Are failed requests charged?
No. If a synthesis request fails, the charge is returned in full. You are only billed for successfully generated audio files. This ensures you do not pay for errors or processing issues that prevent the API from delivering the requested audio content.
Is my text used for training?
No. Your input text is used solely to produce the audio file for that specific request. We do not use your text data for training our models or improving the service. Your content remains private to your generation use case.
Is the audio stored after generation?
No. Generated audio is returned in the response and is not stored on our servers. We retain request metadata, such as time, character count, and status, strictly for billing and usage tracking purposes. The audio files themselves are transient.
Do you support streaming?
No, we do not support streaming, WebSocket connections, or real-time partial audio. The API returns the complete audio file after processing. Requests are processed sequentially, so longer texts may experience queue delays depending on current load.
Do you support SSML?
No, our API does not support SSML (Speech Synthesis Markup Language). You cannot use SSML tags to control pronunciation, pacing, or emphasis. You control the output primarily through the selected voice preset and the speed parameter ranging from 0.25 to 4.0.
Can I clone voices?
No, we do not offer custom voice cloning or the ability to upload your own voice. The eight available voices are fixed presets based on licensed recordings. You cannot design new voices or create custom clones for specific educational materials.
How do I contact support?
Support is available via email only. We do not offer a phone number, live chat, or on-site support. For issues regarding your API key, billing, or technical questions, please send an email to our support address. Response times may vary.
Is the site affiliated with OpenAI?
No, VoxEd is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft or any other brand mentioned in comparisons. We use a compatible request shape, so OpenAI SDKs work by changing the base URL. Our models, voices, and pricing are independent and distinct from those other brands.
API Overview
Our cloud text-to-speech API converts text into audio files via a simple POST request. The endpoint is https://api.bet4x.top/v1/audio/speech, accepting JSON bodies with fields like model, input, voice, and response_format. Texts up to 4096 characters are processed to produce downloadable audio.
Designed for educators, this service integrates easily into existing Python scripts for generating lesson audio. You can manage keys and monitor usage directly through the dashboard, ensuring straightforward integration for school developers building accessible content pipelines without complex infrastructure.
Endpoint and request format
Send a POST request to https://api.bet4x.top/v1/audio/speech with a JSON body containing your text (input), selected voice preset, and desired audio format. The API returns the generated audio file directly in the response, supporting formats like mp3, wav, opus, flac, and pcm. You can also specify a speed multiplier between 0.25 and 4.0.
- Endpoint: POST https://api.bet4x.top/v1/audio/speech
- Max input length: 4,096 characters per request
- Supported formats: mp3, wav, opus, flac, pcm
OpenAI SDK compatibility
The request structure mirrors the OpenAI speech endpoint exactly. By updating your SDK's base_url to https://api.bet4x.top/v1 and using your specific API key, you can use the official OpenAI libraries without rewriting your code. This compatibility allows schools to adopt the service with minimal changes to existing Python-based educational tools.
Rate limits and speed
Each API key is limited to 60 requests per minute after any top-up, with a lower limit of 10 requests per minute before the first deposit. Generation speed is roughly real-time on long texts (about 25 characters per second); short phrases take a few seconds. During high load, requests may queue, but typical usage remains efficient for bulk lesson audio creation.
Voices and Languages
The API offers eight distinct voice presets, each derived from licensed recordings in the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings. These voices are designed for clarity and consistency, ensuring reliable audio output for educational materials.
Each voice is trained to handle a wide range of text types, from instructional content to narrative storytelling. The voices are gender-neutral in their core design but offer distinct tonal qualities to suit different pedagogical needs.
8 preset voices
We provide eight voice options to match your content's tone. All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0).
The available voices are carefully selected for their clarity and natural rhythm in educational contexts.
- 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
23 supported languages
Our service supports 23 languages, allowing you to create accessible content for diverse student populations. Any voice can speak any of the supported languages.
If the language parameter is not set, the system guesses the language from the script. For non-English Latin-script text, we recommend explicitly setting the language to ensure accuracy.
- Arabic
- Chinese
- Danish
- Dutch
- English
- Finnish
Voice characteristics
Each voice has a specific character profile, from the warm narrator to the deep documentary style. These characteristics help educators select the most appropriate audio for their lesson plans.
All generated files carry an inaudible watermark, marking them as synthetic speech. This ensures transparency in your educational materials.
Pricing and Payment
We charge $0.01 per 1,000 characters, including spaces and punctuation, at a rate of $10 per million characters. Failed requests are free, with the charge returned in full if synthesis fails. There are no monthly plans, seats, or minimum spend requirements.
$10 per 1 million characters
Costs are calculated based on input text length. Each request supports up to 4096 characters. For longer lesson plans, split the text into parts and join the resulting audio files.
USDT (TRC-20) top-up
We accept USDT on the TRON network (TRC-20) only. There is no PayPal, credit card, or invoice option. The minimum top-up is $5, and funds are credited automatically within minutes. Your balance never expires.
Free trial and failed requests
Signing in with Google grants $0.50 of trial credit (approx. 50,000 characters) valid for 7 days. Email-based accounts start without trial credit. You can issue a new API key at any time, invalidating the old one immediately.
Data and Privacy
VoxEd’s TTS API processes input text solely to generate the requested audio file. We do not use your lesson plans or reading materials to train our models or improve the engine. The data remains strictly within the context of your immediate request.
Input text usage
Your text is processed in real-time to produce the audio output. Input text is used only to produce the audio and is not used for training.
No training on data
We guarantee that the text you submit is not used to train our TTS models. Your content remains yours, ensuring that specific educational materials or proprietary texts are not absorbed into the base model’s training data.
Audio storage policy
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. We retain request metadata—including timestamp, character count, and status—solely for billing and usage verification purposes.

Technical Limitations
The API delivers complete audio files rather than streaming them in real-time. This means you must wait for the full synthesis to finish before receiving the data, which is suitable for batch processing lesson plans but not for live interactive dialogue. There is no WebSocket support for partial audio chunks.
No streaming or WebSocket
Requests are processed sequentially, so under load, a request may wait in a queue. You receive the final audio file once generation is complete, rather than hearing it as it is produced.
No SSML support
The endpoint does not support Speech Synthesis Markup Language (SSML). You cannot use tags to control pauses, emphasis, or pronunciation rules within the input text.
Fixed voice presets
There are only eight preset voices and no option for custom voice cloning or uploading your own voice samples. Each generated file carries an inaudible watermark to mark it as synthetic speech.
Support and Contact
VoxEd operates without a call center or live chat widget. Our support team is reachable exclusively via email, ensuring that every inquiry is logged and tracked. This asynchronous model allows our engineers to provide detailed, context-aware answers rather than quick, generic replies.
We do not offer a phone number for immediate assistance. If you encounter a critical issue with your API key or billing, email remains the most reliable channel to reach our team directly without waiting on hold.
Email support only
All communications go through our support email address. This ensures a clear record of your technical questions, billing details, and voice-specific inquiries. You can reach us at [email protected] for any account or integration questions.
No live chat or phone
Unlike many consumer apps, we do not maintain a live chat window or a dedicated phone line. This approach reduces overhead and keeps our pricing competitive for educational institutions.
Response times
For complex technical issues involving API endpoints or voice selection, it may take up to 48 hours to provide a detailed solution. Urgent billing issues are typically resolved faster.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. These voices are built from licensed recordings, providing a natural listening experience suitable for diverse classroom materials.
23 languages
Any voice speaks any of these languages.
