Frequently asked questions
Who runs the EduEcho site?
This is an independent storefront for the EduEcho text-to-speech API. Accounts are specific to this site, api36.info. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We operate as a standalone provider for startups building online courses and LMS platforms.
Where do the voices come from?
Our voices are based on licensed recordings from LibriTTS-R, which uses public-domain audiobook readings from LibriVox. We offer eight presets, including female voices like Aria and Nova, and male voices like Felix and Milo. These are synthesized using our cloud API, not direct recordings of specific actors.
Is my text used to train the model?
No. Input text is used only to produce the audio file for your request. It is not used for training our models. This ensures your lesson scripts and course content remain private and are not ingested into our training data for future model improvements.
Do you store the generated audio?
Generated audio is returned in the response and is not stored by us. We only keep request metadata, such as time, character count, and status, for billing purposes. Your actual audio files are delivered directly to your application and are not retained on our servers.
How can I contact support?
Support is by email only. We do not offer a phone number, live chat, or SLA. You can reach us via the contact page or the email address provided in your account dashboard. We respond to inquiries as efficiently as possible via written communication.
Do you have a phone number?
No, we do not have a phone number. Support is handled exclusively through email. This allows us to maintain a lean operation focused on providing a reliable API for startups without the overhead of voice support lines. You can find our email contact details on the /contact/ page.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons Attribution license. Our voice bases come from LibriVox, which uses this license for public-domain audiobook readings. This means the source recordings are freely usable with attribution. It ensures the foundational audio data for our TTS engine is legally clear and open.
Are the voices human or AI?
The voices are AI-generated synthetic speech. Every generated file carries an inaudible watermark that marks it as synthetic. They are not direct recordings of human actors but are synthesized from licensed human voice data. They sound natural but are technically generated by our text-to-speech model.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, we do not explicitly offer refunds beyond this. Your balance does not expire, so you can use your credit for future requests whenever you are ready to generate more audio.
Is the site affiliated with OpenAI?
No. We are not affiliated with OpenAI, despite our API endpoint and request shape being compatible with the OpenAI speech endpoint. We use our own keys and infrastructure. You can use the official OpenAI SDKs by changing the base_url to our API domain, but we are a separate entity.
What data is kept for billing?
We keep request metadata for billing purposes. This includes the time of the request, the number of characters processed, and the status (success or failure). We do not store the input text or the generated audio files. This data is used solely to calculate your usage charges accurately.
Can I use the audio commercially?
Yes, you can use the generated audio commercially. The voices are based on licensed recordings, and the API is designed for startups building online courses and LMS platforms. You own the output generated from your input text.
Our Editorial Team
This site is an independent storefront for the EduEcho TTS API. We are not affiliated with OpenAI, ElevenLabs, or any other brand mentioned in comparisons. Our content is created by independent teams focused on clarity and accuracy for LMS platforms.
We prioritize practical information for startups building online courses. Our goal is to help you integrate professional voice-overs into your curriculum without unnecessary complexity or hype.
Independent Content Creators
We are course creators first. This perspective ensures our explanations focus on real-world workflows, such as converting lesson scripts into audio files programmatically. We understand the needs of LMS platforms and the importance of reliable content generation.
Technical Writers
Our documentation and code examples are written by engineers who use the API daily. We test the endpoints and SDK integration ourselves, ensuring that the curl examples and Python snippets are accurate and ready for production use.
Course Design Experts
We analyze how text-to-speech fits into educational structures. Our team reviews how different voices and speeds affect learning outcomes, helping you choose the right settings for your specific course material without making unsupported claims about pedagogical superiority.
Voice Licensing and Sources
Our voice models are synthesized from licensed recordings, ensuring clear legal provenance for your educational content. We utilize high-quality source material to maintain audio fidelity while keeping licensing costs low for startups.
LibriTTS-R License
The synthetic voices are based on the LibriTTS-R dataset, which provides a robust foundation for natural-sounding speech synthesis.
CC BY 4.0 Agreement
The voice data is based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain recordings, but the generated audio files are not explicitly licensed under CC BY 4.0.
LibriVox Public Domain
The underlying voice recordings originate from LibriVox public domain audiobook readings, ensuring that the source material is free of restrictive copyright claims.
Data Privacy Policy
We prioritize your content ownership and privacy. Our API processes your lesson scripts to generate audio files without retaining the input text for any purpose other than synthesis. Your input text is used only to produce the audio and is not used for training.
The generated audio files are returned in the API response but are not stored on our servers after delivery. This means your audio assets are ephemeral by design, reducing data exposure. You maintain full control over where and how these files are saved within your LMS or course platform.
Input Text Not Trained
Your input text is used solely to produce the immediate audio output. We do not ingest your scripts into our training dataset. Input text is used only to produce the audio and is not used for training.
This approach is critical for course creators who value intellectual property. Input text is used only to produce the audio and is not used for training.
- Input text is used only for immediate synthesis.
- Not used for model training or fine-tuning.
- Your unique course scripts remain private.
No Audio Storage
Once the audio file is delivered to your client or server via the API response, we do not store it. This eliminates long-term data retention risks associated with cloud storage providers. You are responsible for storing the audio files in your own infrastructure.
This ephemeral nature supports a clean data architecture. If you need to regenerate audio, you simply send the text again. You do not need to manage historical audio versions on our servers, simplifying your storage costs and data governance.
- Audio is not stored on our servers.
- Returned only in the immediate API response.
- You control long-term storage.
Billing Data Kept
We retain request metadata—such as timestamp, character count, and status—for billing and dispute resolution purposes. This data is necessary to verify usage against your account balance and to process refunds for failed requests accurately.
This metadata is kept only as long as required for financial compliance and does not include the content of your text or audio. It is used strictly to support your account management and ensure transparent, accurate billing for each character processed.
- Metadata kept for billing accuracy.
- Includes timestamp, character count, status.
- Does not include text or audio content.
Support and Contact
We keep support simple and direct. As an independent API provider for course platforms, we prioritize clear communication over complex support structures. You can reach our team for technical questions, billing issues, or general inquiries regarding the EduEcho API.
Email Only Support
All communication happens via email. There are no phone numbers to call and no live chat widgets to click. This approach ensures every query is documented and can be referenced later when debugging API integrations or reviewing character usage.
- Single point of contact for all account and technical questions
- No waiting in voice queues or navigating automated menus
No Phone or Chat
We do not offer real-time voice support or instant messaging. If you need immediate assistance during a live demo, you will need to use email. This allows us to maintain a lean operation and keep costs low for our startup customers.
Response Times
Response times may vary slightly depending on the volume of integration requests. For urgent billing issues, please include your API key in the subject line for faster tracking.
- Standard response: within 24 hours
- Urgent billing: include API key for faster tracking

Technical Limitations
Our API delivers complete audio files rather than streaming partial chunks in real time. Because requests are processed sequentially, longer texts may queue under load, resulting in generation times that roughly match real-time speech speed plus a few seconds for short phrases. This ensures stable, high-quality output but requires your integration to handle the full response.
We do not support SSML for precise pronunciation control or emotion tagging. The engine relies on natural language processing to interpret text, which works well for standard course scripts but lacks granular markup options. If you need custom timing or stress, you must manage it via your own text formatting before sending the request.
No Voice Cloning
We offer eight preset voices rather than custom voice cloning. You cannot upload a sample to create a unique brand voice or clone a specific instructor. Each voice is based on licensed recordings from LibriVox, ensuring clear, professional narration without the need for bespoke voice design.
- Fixed set of 8 voices (e.g., Aria, Nova, Atlas)
- No custom voice training available
- Voices cover 23 languages natively
No Streaming
Audio is returned as a complete file (mp3, wav, opus, flac, or pcm) after synthesis finishes. There is no WebSocket or real-time partial audio stream. Your LMS must wait for the full response before playing the audio, which simplifies integration but prevents instant playback for very long lessons.
No SSML
The API does not parse SSML tags for pauses, breaks, or emphasis. Control is limited to the speed parameter (0.25–4.0) and voice selection. For precise timing, consider splitting your text into smaller chunks and adjusting the speed per segment manually in your application logic.
Mission and Vision
EduEcho exists to remove the friction from audio content production for online education. By providing a reliable TTS API, we enable startups to convert lesson scripts into professional voice-overs programmatically, ensuring consistent quality without hiring multiple voice actors.
Our vision is to support course creators by simplifying the technical side of audio generation, allowing them to focus on curriculum design and student engagement rather than production logistics.
Democratizing Audio Content
We believe high-quality audio should be accessible to every course creator, regardless of budget or technical expertise. Our API allows anyone to generate professional narration from text, breaking down barriers to entry for independent educators and small teams.
By standardizing the voice generation process, we ensure that educational content remains consistent and scalable across multiple languages and voices.
Supporting Course Creators
Our platform is built specifically for the needs of online course platforms and LMS systems. We provide the tools necessary to integrate voice-overs seamlessly into learning workflows, enhancing the educational experience through clear, synthesized narration.
We aim to reduce the time and cost associated with traditional voice-over production, making it easier to produce updated or localized content quickly.
Transparent Pricing
We charge $10 per 1 million characters, with no hidden fees or subscription tiers. This straightforward model ensures that you only pay for what you use, making it easy to predict costs for large-scale course production.
There are no monthly plans, no minimum spend, and no seats to manage. Your balance does not expire, allowing you to use credits whenever you need them without pressure.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. These voices are best for core curriculum content where clarity and steady pacing are essential for retention.
23 languages
Any voice speaks any of these languages.
