Frequently asked questions
What is a TTS API?
A cloud text-to-speech API that accepts text via POST requests and returns audio files. It uses a standard JSON body compatible with OpenAI SDKs, allowing you to send text and receive synthesized speech in formats like MP3 or WAV without managing infrastructure.
How do I use TTS API with Python?
Install the official OpenAI SDK, set the base_url to https://api.999sl.top/v1, and use your API key for authentication. Send a POST request to /v1/audio/speech with your text, voice selection, and desired format. The SDK handles the JSON payload and returns the audio file.
Which voices are best for educational content?
Sage offers a calm, instructional tone ideal for lessons, while Luna provides a soft, storytelling voice for narratives. Aria serves as a warm, clear narrator for general content, and Milo delivers a friendly, conversational style suitable for interactive exercises or dialogue-based learning materials.
What languages does the API support?
The API supports 23 languages including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and Russian. Any voice can speak any supported language. If the language is not specified, it guesses from the script, defaulting to English for Latin text.
How much does the API cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spending requirements.
Is there a free trial?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, covering approximately 50,000 characters. Accounts created with an email and password do not receive this trial credit. The balance does not expire after the trial period ends.
Can I use the audio in my classroom?
Yes, you can use the generated audio for educational purposes. Each file contains an inaudible watermark marking it as synthetic speech. Input text is used only to produce the audio and is not used for training models, ensuring privacy for your materials.
Do you store my input text?
Input text is used solely 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, character count, and status, strictly for billing purposes.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or split longer texts into smaller parts to ensure successful generation within the 4,096 character limit per request.
How fast is the generation?
Generation is roughly real-time, processing 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 being synthesized.
Can I clone my own voice?
No, custom voice cloning is not offered. You cannot upload your own voice or design custom voices. The API provides eight preset voices based on licensed recordings from LibriTTS-R and LibriVox, which are available for all supported languages.
Is there an SLA?
No, there is no Service Level Agreement or uptime guarantee. We do not offer enterprise contracts or certifications like SOC 2 or HIPAA. Support is available via email only, with no phone number or live chat options provided.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum deposit is $5, and credits are automatically added within minutes after the transfer. We do not accept credit cards, PayPal, or subscriptions, and no invoices with VAT are issued.
What is the character limit?
Each request accepts up to 4,096 characters in the input field. For longer texts, you must split the content into parts of this size and join the resulting audio files. Spaces and punctuation count toward the character limit.
First request
curl
curl https://api.999sl.top/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.mp3How the API Works
The SonicLesson API simplifies audio generation for educational tools. You send a JSON payload via a standard POST request, and the service returns synthesized speech. This straightforward workflow integrates seamlessly into Python scripts used for creating classroom materials or powering edtech applications.
Send Text, Get Audio
Input text is processed through the v1/audio/speech endpoint. The system returns an audio file directly in the response, eliminating the need for complex polling or secondary retrieval steps.
Python SDK Compatibility
The endpoint shape matches the OpenAI speech API. You can use the official OpenAI Python SDK by simply adjusting the base_url to https://api.999sl.top/v1. This allows developers to leverage familiar authentication and request patterns without learning a new library.
Automatic Text Splitting
For longer lessons, the API handles up to 4096 characters per request. While the API itself does not auto-split, the predictable character limit allows Python scripts to easily chunk texts and join the resulting audio files.
Voices for Every Lesson
The eight available voices cover distinct pedagogical needs, from warm narration to clear instruction. Each voice is derived from licensed recordings, ensuring a natural foundation for educational content without the complexity of custom cloning.
Female Narrators
Aria provides a warm, clear tone ideal for reading stories or explaining concepts. Nova offers a bright, upbeat style suitable for engaging young learners or highlighting key points. Luna’s soft delivery works well for storytelling, while Sage delivers calm, instructional clarity for step-by-step guides.
Male Presenters
Felix brings energy to promotional materials or quick announcements. Milo’s friendly, conversational style suits dialogue or informal explanations. Atlas remains neutral and professional, while Orion’s deep tone is effective for documentary-style content or serious subject matter.
Neutral News Tone
Atlas serves as the primary neutral voice, suitable for reading news updates or factual reports without emotional bias. Orion provides a deeper, documentary-style alternative for more serious or historical content. All voices can adapt to any supported language, though setting the language parameter ensures accurate pronunciation.
Supported Languages
The API supports 23 languages, allowing educators to create diverse classroom materials. Any voice can speak any of these languages, offering flexibility for global education projects.
If you don’t specify a language, the system guesses from the script. Latin text defaults to English, but you should set the language field for non-English Latin-script text to ensure accuracy.
Major World Languages
Support covers major global languages including Arabic, Chinese, Hindi, Japanese, Korean, Russian, Spanish, and Swahili.
These selections allow teachers to produce content for a wide range of student demographics without needing multiple specialized tools.
- Arabic
- Chinese
- Hindi
- Japanese
- Korean
- Spanish
European Languages
European language support includes Danish, Dutch, Finnish, French, German, Greek, Italian, Norwegian, Polish, Portuguese, Swedish, and Turkish.
This broad coverage ensures consistent audio quality across Western European educational contexts.
- Danish
- Dutch
- Finnish
- French
- German
- Greek
Asian Languages
Asian language options include Chinese, Japanese, Korean, and Malay.
Teachers can generate clear instructional audio for students learning these languages or using them as primary instruction languages.
- Chinese
- Hindi
- Japanese
- Korean
- Malay
Pricing for Educators
SonicLesson charges a flat rate of $0.01 per 1,000 characters, making budgeting predictable for classroom materials. Spaces and punctuation count toward the total, so test short phrases to gauge actual costs. Failed synthesis requests are free, ensuring you only pay for usable audio.
The pricing structure scales linearly with usage. There are no hidden fees for format changes or speed adjustments, allowing developers to optimize audio quality without worrying about variable costs.
Per Character Rate
The standard rate is $10 per 1 million characters. This simple metric applies to all models and voices, regardless of language or format selected.
- $0.01 per 1,000 characters
- Includes spaces and punctuation
- Failed requests are free
Free Trial Credit
New accounts signed in with Google receive $0.50 in credit, sufficient for approximately 50,000 characters. This trial is valid for seven days, giving educators time to test voice quality before committing funds.
- $0.50 initial credit
- Valid for 7 days
- Requires Google sign-in
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. Top-ups are made via USDT (TRC-20) with a $5 minimum. Balance never expires, and unused credits remain available for future lessons or projects.
- No monthly subscriptions
- No minimum spend
- Balance never expires
Technical Limits
The API enforces strict boundaries to ensure consistent delivery for classroom materials and edtech tools. Understanding these limits helps developers design robust workflows that avoid errors during peak usage periods.
Character Limits
Each request supports up to 4096 characters. For longer lessons, split the text into chunks and join the resulting audio files. Spaces and punctuation count toward this limit.
Rate Limits
Keys allow 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed.
Processing Speed
Generation typically takes about 25 characters of text per second of audio. Short phrases may take a few seconds, while long texts process at roughly real-time speed. Under load, requests may queue and wait.

Audio Formats
The API supports five standard audio formats, allowing you to choose the right balance between file size and quality for your educational materials or edtech applications.
MP3 for Web
MP3 is the default and most efficient choice for web playback. It offers small file sizes that load quickly in browsers and mobile apps, making it ideal for classroom audio lessons and interactive exercises.
WAV for Quality
WAV provides uncompressed, high-fidelity audio. Use this format when audio quality is critical, such as for language learning materials or when the audio will undergo further editing or processing by teachers.
FLAC for Archiving
FLAC offers lossless compression, preserving every detail of the synthetic voice without the large file size of WAV. It is perfect for long-term archiving of generated educational content.
Data Privacy
Your input text is processed solely to generate the requested audio file. We do not use your educational materials, lesson plans, or student data to train our models or improve the engine. The raw text is transient and not retained for future learning.
Generated audio files are returned in the response and are not stored on our servers. Once the synthesis is complete and the file is delivered, the audio content is gone. We keep no copies for advertising or secondary use.
No Training Data
The text you send via the API is used exclusively for the immediate synthesis of the audio response. It is not ingested into our training dataset to influence future voice models or improve language processing. Your specific classroom content remains yours.
No Audio Storage
Synthesized audio files are returned in the HTTP response and are not persisted on our infrastructure. We do not store the resulting audio files after delivery. This ensures that your narrated lessons or educational recordings are not archived by our platform.
If you need to keep the audio, you must save it to your own storage immediately upon receipt. Our system acts as a transient processor, not a content repository.
Metadata Only
We retain minimal metadata strictly for billing and operational transparency. This includes the timestamp of the request, the number of characters processed, and the request status (success or failure).
This metadata allows you to verify charges against your dashboard and troubleshoot issues without revealing the actual content of your text or audio.
- Request timestamp
- Character count
- Request status (success/failure)
- Model used (tts-1 or tts-1-hd)
Getting Started
Create your account at /get-api-key/ using Google or email. The dashboard displays your active API key, current balance, and a ready-to-use cURL example.
Copy the key and send a POST request to the speech endpoint. The service processes your text and returns the audio file directly in the response.
Get API Key
Sign up on the /get-api-key/ page. You receive one active key per account, visible immediately in your dashboard.
- Google or email sign-up
- Instant key generation
- Dashboard balance display
First Request
Use the official OpenAI SDK or plain HTTP. Set the base URL to https://api.999sl.top/v1 and include your Bearer token in the Authorization header.
- POST /v1/audio/speech
- JSON body with model and input
- Direct audio file response
Documentation
Visit /docs/ for full endpoint details, voice presets, and language codes. The guide covers all supported request fields and error handling.
Why Choose This API
SonicLesson strips away the enterprise overhead, offering a straightforward API that indie developers and educators can integrate without signing complex contracts or waiting for approvals. It is built for reliability, not buzzwords.
Simple Integration
Use standard OpenAI SDKs by simply adjusting the base URL. The API handles format selection automatically, so you can focus on your code, not edge cases.
- Compatible with official OpenAI Python SDKs
- Automatic text splitting for long lessons
- No custom SDK to learn
Transparent Pricing
Pay only for what you use at $0.01 per 1,000 characters. There are no monthly subscriptions, hidden fees, or minimum spend requirements. Failed requests are refunded immediately.
- $0.01 per 1,000 characters
- No monthly subscriptions
- Refunds for failed requests
Editorial Focus
We prioritize clarity and honesty over marketing hype. Our voices are based on licensed recordings, and our documentation reflects exactly what the API does, without promising features that do not exist.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The language’s dominance in data and education tools means libraries handle text splitting and format conversion natively.
23 languages
Any voice speaks any of these languages.
