Frequently asked questions
Can I generate a specific game show host tone?
You can choose from eight preset voices, such as Felix for energetic promo styles or Atlas for neutral news delivery. While you cannot create custom tones, these presets allow you to simulate distinct character voices for your online modules without hiring voice actors.
Which voices sound most like a quiz master?
Felix offers an energetic, promo style suitable for lively quiz segments. Atlas provides a neutral, news-like tone for clear instructions. Aria serves as a warm narrator, while Sage delivers calm, instructional delivery ideal for structured educational content.
How long does it take to generate audio?
Generation is roughly real-time, processing about 25 characters per second. Short phrases take a few seconds, while longer texts may queue under load. Failed requests are processed quickly and do not incur charges, ensuring efficient workflow for your course production.
Do I need technical skills to use the API?
The API uses a standard JSON body similar to OpenAI, so existing SDKs work by changing the base URL. You can also use the ready curl example provided on the /get-api-key/ page. Basic HTTP knowledge is sufficient for integration.
Is the audio copyrighted for commercial courses?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each file includes an inaudible watermark marking it as synthetic speech. You can use these audio files in your commercial online courses without additional licensing fees.
Can I use the voices for student projects?
Yes, you can generate audio for student projects using your account. Since voices are based on CC BY 4.0 licensed data, the resulting synthetic speech is suitable for educational use. Just ensure you follow the attribution requirements of the source licenses.
What happens if the API 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, protecting your budget when testing different voices or formats for your instructional content.
Do you support non-English languages?
Yes, we support 23 languages including Spanish, French, German, and Japanese. Any voice can speak any supported language. If the language is not set, it is guessed from the script, but you should specify it for non-English Latin-script text to ensure accuracy.
Can I upload my own voice for characters?
No, we do not offer custom voice cloning or uploading your own voice. You must use the eight available presets. These presets are based on licensed recordings and provide distinct tones suitable for various character roles in your educational modules.
How is pricing calculated for long courses?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count. For long courses, split text into parts of up to 4,096 characters per request and join the resulting audio files. Balance does not expire.
Is there a limit on characters per request?
Yes, each request can contain up to 4,096 characters of input text. For longer scripts, you must split the text into multiple requests, generate the audio for each part, and then join the files. This ensures consistent quality and manageable processing times.
Do I need a subscription to start?
No, there are no monthly plans or subscriptions. You pay only for what you use. Accounts created with Google sign-in receive a $0.50 free trial valid for 7 days. You can top up with USDT on the TRON network as needed.
Can I get a refund for unused credit?
Unused credit does not expire and remains in your balance. However, the product facts do not mention a refund mechanism for unused top-up credit. Failed requests are refunded automatically. For specific refund policies on top-ups, please contact support via email.
How do I check my API usage?
The /get-api-key/ page displays your balance, characters left, and usage history. You can also monitor your account status and key details directly on this dashboard. This allows you to track character consumption and manage your budget for course production.
First request
curl
curl https://api.combowin.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.mp3Why use synthetic voices for course game shows?
Creating consistent character voices for educational game shows used to mean hiring voice actors for every module update. Synthetic voices solve this by providing reliable, character-based audio that stays identical across all your course content, ensuring learners recognize the host or narrator instantly regardless of which lesson they are taking.
Consistent character tone across modules
Maintain the exact same personality for your game show host from Module 1 to Module 10. Unlike human recordings which may vary due to fatigue or microphone differences, our API ensures your chosen voice remains uniform.
Instant updates without re-recording
Need to change a quiz question or update a trivia answer? Just send the new text through the API and receive the audio file in seconds. You do not need to schedule studio time, wait for an actor, or re-record entire segments to make minor content corrections.
Cost-effective content scaling
Generating audio is priced at $10 per million characters, making it affordable to produce extensive dialogue trees or long-form simulations. With a free trial credit of $0.50, you can test the workflow immediately without committing to a monthly subscription or minimum spend.
Available voices for educational roles
For educators building interactive modules, selecting the right voice persona is crucial for maintaining student engagement without hiring professional voice actors. Our API provides eight distinct presets, each rooted in licensed recordings, allowing you to assign specific character roles to different parts of your curriculum.
Whether you need a high-energy host for a quiz bowl or a calm narrator for a case study, you can mix and match voices to create a consistent auditory experience across your entire course library.
Felix: Energetic host for quizzes
Felix brings an upbeat, promotional energy perfect for timed quizzes or rapid-fire trivia. His clear, energetic tone keeps students alert and engaged during high-paced learning segments.
- Ideal for quiz introductions and countdown sequences
- Engages students with a bright, active tone
Atlas: Neutral announcer for instructions
Atlas offers a neutral, news-style delivery that ensures clarity for complex instructions. His balanced tone reduces cognitive load, making him ideal for conveying rules or transitioning between lesson modules.
- Perfect for clear, unbiased instruction delivery
- Reduces distraction in complex learning steps
Luna: Soft storyteller for narratives
Luna provides a soft, storytelling voice suitable for case studies or historical narratives. Her gentle tone creates an immersive atmosphere, helping students connect emotionally with the material.
- Enhances storytelling and case study immersion
- Creates a calm, focused learning environment
Supported languages and formats
Educators can generate content in 23 languages, including English and Spanish, ensuring your modules reach diverse audiences without hiring local voice talent. Whether you are teaching history or science, the same engine delivers consistent quality across regions.
You can choose from five output formats—MP3, WAV, OPUS, FLAC, and PCM—to match your LMS player capabilities. MP3 is ideal for web delivery, while WAV offers uncompressed clarity for archival purposes.
23 languages including English and Spanish
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. Every voice can speak any of these languages, allowing you to mix languages within a single course module.
- Full support for major European and Asian languages
- Consistent voice quality across all 23 languages
MP3, WAV, OPUS, FLAC, PCM outputs
Select the format that best fits your bandwidth and quality needs. MP3 and OPUS are efficient for web delivery, while WAV and FLAC provide lossless audio for high-fidelity playback. PCM is available for raw audio processing.
- MP3 for web compatibility
- WAV and FLAC for lossless quality
- OPUS for efficient streaming
- PCM for raw data
Auto-language detection for Latin scripts
If you do not specify a language, the API guesses it from the script. Latin text defaults to English, but for non-English Latin-script text, set the language parameter to ensure accurate pronunciation. This prevents mispronunciations in languages like Dutch or Swedish.
- Automatic detection for Latin scripts
- Default to English for Latin text
- Explicit
languageparameter recommended for non-English Latin text
How the API works for educators
Generate audio for your learning modules by sending text to our API endpoint. You can use standard HTTP POST requests with JSON bodies, making it easy to integrate into your existing workflow without needing our own SDK.
Send text via simple HTTP POST
Construct your request with the desired model (tts-1 or tts-1-hd), input text, and voice preset. The endpoint accepts up to 4096 characters per call, allowing you to generate concise quiz questions or instructions efficiently.
- Endpoint: POST https://api.combowin.top/v1/audio/speech
- Auth: Bearer token in header
- Standard JSON body structure
Receive audio files in seconds
After submission, you receive the synthesized audio file directly in the response. For longer texts, split them into chunks under the 4096-character limit and join the resulting files. Typical generation speed is roughly real-time, though queue times may occur under load.
- Formats: mp3, wav, opus, flac, pcm
- Real-time speed on long texts
- Queue processing during high demand
Manage balance via TRC-20 USDT
Fund your account using USDT on the TRON network (TRC-20). Transfers are credited automatically within minutes, allowing you to start generating content immediately. There are no monthly subscriptions or credit card fees to manage.
- Minimum top-up: $5
- Credited within minutes
- No expiration on balance
Integration with LMS platforms
AudioTeach integrates seamlessly with any learning management system that supports standard HTML5 audio elements. Since the API returns standard audio files (MP3, WAV, or OPUS), you can embed voice lines directly into course modules using simple HTML tags like <audio> or <source>. This ensures broad compatibility across desktop and mobile browsers without requiring specialized plugins or proprietary media players within your LMS environment.
Works with any platform supporting HTML5 audio
You can generate character dialogues or quiz instructions and embed them directly into your course content. Because the output is a standard audio file, it plays natively in most LMS platforms, allowing learners to hear consistent voice lines whether they are on a desktop computer or a mobile device.
No mobile SDK required
Your learners do not need a dedicated app to hear the content. The audio files are served via standard web protocols, ensuring that students can access game show host voices or narrator tones directly through their browser. This reduces friction for users and eliminates the need for app-specific development or maintenance.
Standard OpenAI SDK compatibility
If your LMS or middleware already uses the OpenAI Python or Node.js SDKs, you can switch our API by simply updating the base_url to https://api.combowin.top/v1. The request shape remains identical to the OpenAI speech endpoint, meaning your existing code for sending text and receiving audio will work with minimal configuration changes.

Pricing for course creators
AudioTeach charges $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this limit. Failed requests are free, with charges returned in full if synthesis fails.
$10 per million characters
Pricing is straightforward: $0.01 per 1,000 characters. This allows you to budget precisely for long course modules or short quiz feedback lines without hidden costs.
- Characters include spaces and punctuation.
- Failed requests are refunded instantly.
No monthly fees or subscriptions
There are no monthly plans, seats, or minimum spend requirements. You only pay for what you generate, making it ideal for projects with fluctuating content needs.
Free trial credit available
Sign in with Google to receive $0.50 in credit (about 50,000 characters), valid for 7 days. Email/password accounts start without trial credit.
- Top-ups via USDT (TRC-20) start at $5.
Voice quality and licensing
Our voices are built from licensed recordings sourced from LibriTTS-R, derived from public-domain audiobook readings on LibriVox. This foundation ensures a natural, consistent tone suitable for educational narration without the need for hiring multiple voice actors.
Licensed recordings from LibriVox
Each voice preset is based on licensed data from LibriTTS-R, providing a reliable foundation for clear, character-based audio lines used in online modules.
Synthetic watermark for identification
Every generated audio file carries an inaudible watermark, clearly marking the content as synthetic speech for transparency in your course materials.
Text not used for training models
Input text is processed solely to produce your audio and is not used to train our underlying models, keeping your specific course content private.
Common use cases in e-learning
AudioTeach helps course creators build engaging interactive modules without hiring voice actors. By generating distinct character voices, you can maintain consistent tone across multiple lessons while keeping production costs low. Synthetic speech allows instant updates to content without re-recording sessions.
Educators can quickly prototype game show elements, quiz feedback, and simulation dialogues. This approach scales easily, letting you add new audio lines as your curriculum grows. Each generated file is ready for immediate integration into standard HTML5 audio players.
Trivia game introductions
Use Felix’s energetic voice to announce trivia rounds or quiz starts. His upbeat tone keeps learners engaged and signals the start of interactive segments without the need for a live host. You can generate unique intros for each module, ensuring fresh content every time.
- Announce quiz start times with high energy
- Create varied intro lines for different difficulty levels
- Maintain consistent host identity across all modules
Feedback voice lines for quizzes
Provide instant audio feedback for correct or incorrect answers using Atlas or Sage. Neutral, clear narration helps learners understand results without distraction. Since requests are processed sequentially, you can generate feedback lines on-demand, ensuring accurate character counts and timely delivery.
- Clear audio confirmation for correct answers
- Constructive feedback for incorrect responses
- No need for pre-recorded static audio files
Character dialogue for simulations
Bring simulations to life with Luna’s soft storytelling or Milo’s conversational tone. Assign different voices to various characters in your e-learning scenarios, creating a more immersive experience. This method allows for rapid iteration of dialogue scripts without scheduling voice actors.
- Assign distinct voices to multiple characters
- Generate dialogue for branching scenarios
- Update scripts instantly without re-recording
Technical limits and considerations
The API enforces a strict 4096-character limit per request, requiring you to split longer scripts into manageable chunks. Since requests are processed sequentially, high traffic may introduce queue delays, making real-time interactivity less predictable during peak usage.
4096 character limit per request
Each API call handles up to 4096 characters, including spaces and punctuation. For longer game show segments or educational narratives, you must split the text and join the resulting audio files client-side.
- Count spaces and punctuation toward the limit
- Split long scripts into smaller chunks
- Join audio files in your LMS player
Queue processing under high load
Requests are processed one after another, so generation speed depends on current server load. Short phrases take a few seconds, while longer texts may wait in a queue, affecting real-time quiz pacing.
- Generation takes a few seconds for short texts
- Long texts may experience queue delays
- Plan for slight latency in interactive modules
No SSML or emotion tags
The API does not support SSML or custom emotion tags. Voice character is determined by selecting one of the eight presets, such as Felix for energetic hosts or Luna for soft storytelling.
- No SSML support
- No custom emotion tags
- Use voice presets for tone
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Technical terms and specific instructions are articulated with precision.
23 languages
Any voice speaks any of these languages.
