Frequently asked questions
Can I use this API to generate audiobooks for YouTube?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. You can send text up to 4096 characters per request and receive the audio file directly. This workflow allows instructional designers to convert textbooks into accessible audio files without manual recording.
Does the API support long texts or just short phrases?
It supports long texts by splitting them into parts of up to 4096 characters and joining the resulting audio files. Typical speed is roughly real time on long texts, generating about 25 characters of text per second of generation. Short phrases take a few seconds.
How many characters can I process in one request?
You can process up to 4096 characters in a single request. For longer content, you must split the text into chunks of this size and join the generated audio files. Spaces and punctuation count toward the character limit used for pricing calculations.
Which voices are available for educational content?
Eight voices are available. For educational content, sage offers a calm, instructional tone. Luna provides a soft, storytelling style. Aria delivers a warm, clear narrator voice. Milo is friendly and conversational. Atlas is neutral for news, while Orion is deep for documentaries.
Do the voices sound natural for instructional material?
The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech. The engine processes requests sequentially, so quality remains consistent across generated audio files.
Is there a limit to how many requests I can make?
Rate limits are 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. Requests are processed one after another, so under load a request may wait in a queue.
What audio formats are supported for download?
Supported response formats are mp3, wav, opus, flac, and pcm. You specify the format in the JSON body of your POST request to the speech endpoint. The API returns the audio file directly in the response for immediate use or download.
Does the API support multiple languages?
Yes, it supports 23 languages including English, Spanish, German, French, Chinese, Japanese, and Hindi. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, defaulting to English for Latin text.
How is the pricing calculated for large texts?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and the charge is returned in full if synthesis fails. Balance does not expire, and there are no monthly plans.
Is there a free trial available for new users?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without trial credit. You can top up with USDT on the TRON network for additional balance.
Do I need to sign up with Google or email?
You can sign up on the /get-api-key/ page using Google or with an email and password. Accounts are per site. Each account has one active key, which can be issued again at any time, stopping the old key immediately.
How long does it take to generate audio files?
Typical speed is roughly real time on long texts, about 25 characters of text per second of generation. Short phrases take a few seconds. Requests are processed one after another, so under load a request may wait in a queue.
Are the voices licensed or synthetic recordings?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech. Input text is used only to produce the audio and is not used for training.
Is my input text used for training models?
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. Request metadata, including time, characters, and status, is kept for billing.
First request
curl
curl https://api.playsma77.com/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 CursVoice for Educational Content
CursVoice delivers consistent audio for educational materials, ensuring uniform narration across entire textbooks or course modules. The engine maintains stable voice characteristics without the variability often found in manual recording sessions, allowing instructional designers to scale content production efficiently.
Consistent Voice Quality
Each request generates audio with predictable tonal consistency. This reliability is critical for long-form content where listeners expect a uniform narrator voice throughout the module, reducing cognitive load and improving retention for students.
Batch Processing for Long Texts
The API handles texts up to 4,096 characters per request. For longer textbooks, split the input into manageable chunks and join the resulting audio files. This approach ensures stable synthesis for extensive course materials.
- Split text into 4,096-character segments
- Process segments sequentially
- Join audio outputs into a single file
Cost-Effective Bulk Synthesis
Pricing is flat at $10 per million characters, regardless of voice or format. Failed requests incur no charge, protecting your budget during development. This model scales linearly with usage, making it ideal for institutions producing large volumes of educational audio.
Supported Languages and Voices
CursVoice supports 23 languages, including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any supported language, though setting the language field is recommended for non-English Latin-script text to ensure accurate generation.
23 Languages Supported
We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
8 Distinct Voice Presets
Eight presets cover diverse instructional needs, from clear narration to conversational explanations. All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks.
- 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
Gender and Tone Variety
Four female and four male voices provide tonal range for educational content. Each voice has a specific style, allowing instructors to match the audio to the course material's tone.
Technical Specifications
CursVoice exposes a standard POST /v1/audio/speech endpoint compatible with OpenAI SDKs. Point your client to https://api.playsma77.com/v1 and use your API key for authentication. This ensures seamless integration into existing educational tech stacks without custom drivers.
OpenAI-Compatible Endpoint
Send JSON payloads with model, input, voice, and response_format. The API returns synthesized audio directly, supporting both tts-1 and tts-1-hd models at identical pricing.
- Base URL: https://api.playsma77.com/v1
- Auth:
Authorization: Bearer tts-... - SDK compatible: OpenAI Python/Node.js
Multiple Audio Formats
Select output formats via response_format: mp3, wav, opus, flac, or pcm. Choose mp3 for efficient storage or wav for high-fidelity playback in learning management systems.
Simple JSON Integration
Pass text up to 4,096 characters per request. For longer textbooks, split input into chunks, synthesize each, and join the resulting audio files programmatically. Adjust speed between 0.25–4.0 to control pacing.
Pricing Structure
CursVoice charges $0.01 per 1,000 characters, with a free trial of $0.50 (50,000 characters) for 7 days upon Google sign-in. Failed requests incur no charge, ensuring you only pay for successful synthesis.
Pay Per Character
Usage is calculated based on character count, including spaces and punctuation. The standard rate is $10 per 1 million characters, making long-form educational content cost-effective for bulk processing.
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You maintain control over your budget without recurring costs, paying only for the audio generated.
Transparent Billing
Top-ups are processed via USDT on the TRON network (TRC-20), with a $5 minimum. Credits are credited automatically within minutes and never expire. Account balances and character usage are visible in your dashboard.
Integration Workflow
CursVoice provides a straightforward integration path for instructional designers converting textbooks and course materials into audio. The workflow relies on standard HTTP requests, requiring only an API key and JSON payloads to generate speech files efficiently.
API Key Generation
Create an account on the /get-api-key/ page using Google or email. The dashboard displays your single active key, initial balance, and a ready-to-use cURL example for immediate testing.
Request Format
Send a POST request to the speech endpoint with a JSON body containing the model, input text, voice preset, and response format. The interface mirrors OpenAI’s structure, allowing you to use official SDKs by simply adjusting the base URL.
- Use models: tts-1 or tts-1-hd
- Input text max: 4096 characters
- Set voice from 8 presets
- Choose format: mp3, wav, opus, flac, pcm
Response Handling
The API returns the audio file directly in the response. For texts exceeding 4096 characters, split the input into parts, generate each segment, and join the resulting audio files to reconstruct the full narration.

Use Cases for Instructional Designers
CursVoice enables instructional designers to transform static course materials into accessible audio formats without manual recording. By converting textbooks and lecture notes into speech, teams can distribute content across multiple platforms seamlessly.
Textbook Audio Conversion
Convert dense educational texts into listenable formats for mobile learning. The API handles long-form content by splitting inputs up to 4096 characters, ensuring consistent audio quality across entire chapters.
- Convert textbooks into audio files
- Handle long-form content automatically
- Maintain consistent voice quality
Course Module Narration
Generate narration for video lectures or standalone audio modules. With 8 distinct voice presets, designers can match the tone of each module, from neutral news styles to warm storytelling.
- Narrate video lectures
- Choose from 8 voice presets
- Match tone to module content
Accessibility Compliance
Meet accessibility standards by providing audio alternatives for visual content. The synthetic speech includes an inaudible watermark, clearly marking generated audio.
- Meet accessibility standards
- Provide audio alternatives
- Clear synthetic speech marking
Performance and Limits
CursVoice handles long-form educational content by splitting input text into segments of up to 4096 characters per request. This ensures stable synthesis without truncation, allowing instructional designers to process textbooks and course materials efficiently.
Character Limits per Request
Each API call accepts a maximum of 4096 characters, including spaces and punctuation. For texts exceeding this limit, clients must split the input and join the resulting audio files. This constraint applies uniformly to both tts-1 and tts-1-hd models.
- Maximum input: 4096 characters per request
- Spaces and punctuation count toward the limit
- Client-side splitting required for longer texts
Rate Limiting Details
Accounts are limited to 60 requests per minute per API key. New accounts without a top-up start with a lower limit of 10 requests per minute. These limits apply to synthesis endpoints and ensure fair usage during peak processing times.
- Standard limit: 60 requests/minute
- Initial limit: 10 requests/minute
- Limit resets per API key
Processing Speed
Generation speed is approximately real-time for long texts, averaging 25 characters of text per second of audio. Short phrases may take a few seconds to process. Requests are processed sequentially, so high concurrent load may introduce queue delays.
- Long texts: ~25 chars/sec audio speed
- Short phrases: few seconds latency
- Sequential processing under load
Data Privacy and Usage
CursVoice processes your educational content with a strict data isolation policy. Input text is used solely to generate the audio file and is never retained for training purposes, ensuring your course materials remain proprietary.
No Training on Input Data
We do not use your submitted text to improve our voice models. The text is processed in real-time to produce the audio response and is not stored in our training datasets.
Temporary Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. This ensures that your synthesized audio files exist only where you save them, reducing your own storage dependencies.
Metadata Retention
We retain request metadata, including timestamp, character count, and status, strictly for billing accuracy and usage tracking. This minimal data allows you to reconcile charges against your usage logs.
Getting Started
Create an account on the /get-api-key/ page to access your API key and balance. You can sign up using Google for immediate access or via email and password.
New Google sign-ins receive $0.50 in trial credit (approx. 50,000 characters) valid for 7 days. Email-based accounts start without trial credit.
Free Trial Credit
Google sign-ups include $0.50 credit, valid for 7 days. Email accounts start with zero balance. Top up via USDT (TRC-20) for ongoing usage.
- $0.50 credit for Google sign-ups
- 7-day validity
- USDT (TRC-20) top-ups only
Google Sign-Up
Navigate to /get-api-key/ and select Google authentication. Your API key and usage dashboard appear instantly. Email/password sign-up is also available.
- Instant key generation
- No credit card required
- Simple dashboard access
Documentation Access
Review the /docs/ page for full endpoint details, request formats, and voice options. Use the OpenAI SDK with a modified base_url or plain HTTP requests.
- OpenAI-compatible endpoints
- Clear JSON examples
- Voice and format lists
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The request shape is identical to industry standards, meaning minimal code changes are needed to switch or integrate.
23 languages
Any voice speaks any of these languages.
