Frequently asked questions
Who owns the voices used in the API?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We provide access to these recordings through our API infrastructure, ensuring that the underlying audio sources are legally licensed for this usage model.
Are the voices cloned from real people?
No. We do not offer custom voice cloning or allow uploading your own voice. The eight presets are based on specific licensed recordings. Each generated file carries an inaudible watermark marking it as synthetic speech, distinct from direct human recordings.
Do I need to attribute the voices?
The source recordings use CC BY 4.0 and public-domain licenses. While attribution is good practice, our API delivers synthesized audio files directly. Specific attribution requirements depend on your distribution channel, but the voices themselves are not attributed to individual narrators in the output.
Can I use the audio in videos?
Yes. You can use the generated audio files in videos, LMS integrations, and other media. The audio is returned in the response and not stored by us. You can use the generated files for your specific use cases.
Is the editorial team based in the US?
The provided facts do not specify the geographic location of our editorial or engineering team. We operate as a cloud API service accessible globally. Our infrastructure and support are managed remotely, with no specific mention of a US-based headquarters.
Do you have a physical office?
We do not list a physical office location. Our service is entirely cloud-based. We do not offer on-premise installations or data-center choices for customers. Support and operations are handled digitally, with no public address listed for a physical headquarters.
How do I contact support?
Support is by email only. We do not have a phone number or live chat. You can reach us via the contact page. Response times are not guaranteed by an SLA, so please allow adequate time for our team to address your inquiry.
Is the data policy GDPR compliant?
We do not claim a specific GDPR certificate or compliance status. Input text is used only to produce audio and is not used for training. Request metadata is kept for billing. Generated audio is returned in the response and not stored by us.
Do you sell user data?
No. Input text is used solely for synthesis and not for training. Generated audio is returned in the response and not stored. Request metadata (time, characters, status) is kept only for billing purposes. We do not sell user data to third parties.
Can I request a new voice?
We do not offer custom voice design or cloning. There are eight fixed presets: aria, nova, luna, sage, felix, milo, atlas, and orion. If you need a different voice, you must use one of these existing options available via the /v1/voices endpoint.
How often is the API updated?
Specific update frequencies are not published. The API supports tts-1 and tts-1-hd models. We do not provide an SLA or uptime guarantee.
Is the code open source?
No. We do not have an official open-source SDK. You can use the official OpenAI SDKs by changing the base_url or use plain HTTP requests. The core API logic and infrastructure are proprietary and not available for public inspection or modification.
Do you have a blog?
The provided facts do not mention a blog. We provide documentation at /docs/ and pricing details at /pricing/. Updates and announcements are likely shared via our contact channels or API status, but there is no dedicated blog section listed in our current structure.
Can I partner with you?
We do not have a formal partnership program listed. We operate as an independent storefront for the API. You can contact us via email to discuss potential collaborations. We do not offer enterprise contracts or dedicated support tiers for partners.
Who We Are
CourseSpeak is an independent editorial team built for engineering workflows. We operate a single storefront for the same text-to-speech API, providing predictable costs and clear technical specs for LMS integrations and audiobook generation.
Our focus is on reliable, high-volume text-to-speech processing. We handle character limits, language detection, and USDT billing so engineering teams can integrate seamlessly without corporate overhead.
Independent editorial team
Unlike large platforms, we keep the editorial and technical layers unified to ensure consistent performance for LMS and audiobook projects.
Engineering-focused
We provide standard JSON endpoints, SDK compatibility, and clear rate limits (60 requests/minute) to fit into your existing CI/CD pipelines.
No corporate backing
We are not a subsidiary of a major tech conglomerate. This independence means we offer straightforward pricing via USDT without hidden enterprise contracts or mandatory minimum spends.
Voice Licensing
CourseSpeak’s voice models are derived from the LibriTTS-R dataset, ensuring a transparent and auditable foundation for our synthetic voices.
LibriTTS-R source
We utilize the LibriTTS-R dataset as our primary source for voice synthesis. This ensures that every preset, from Aria to Orion, is grounded in real, high-fidelity recordings rather than purely algorithmic approximations.
CC BY 4.0 license
The underlying recordings are licensed under CC BY 4.0.
Public domain readings
Many of the base recordings originate from LibriVox public-domain audiobook readings.
Data Policy
CourseSpeak processes input text exclusively to generate the requested audio file. Once synthesis is complete, the raw text is not retained for any other purpose.
Input used only for generation
Your text is transmitted to the API engine solely for the purpose of creating the audio output. It is not archived for future use or repurposed beyond that specific request.
No training on data
We do not use your input text to train or improve our voice models. The data remains isolated to your immediate generation task, ensuring your content is not used for algorithmic learning.
No audio storage
Generated audio files are returned directly in the response and are not permanently stored on our servers. Only request metadata—such as timestamp, character count, and status—is kept for billing purposes.
Contact Method
CourseSpeak operates as an independent editorial team without corporate backing, focusing on reliable infrastructure for LMS integrations. We prioritize engineering clarity over marketing fluff, ensuring our API meets the precise needs of large teams generating audiobooks and course content at scale.
Email support only
Our support team is reachable exclusively via email.
No phone number
We do not maintain a public phone line. Our email support ensures that every query is logged, searchable, and resolved with written clarity.
No live chat
There is no live chat widget on our site. We prefer async communication to ensure you receive accurate, thoughtful answers to your integration questions.

Technical Limits
CourseSpeak operates as an independent storefront without corporate backing, meaning we do not offer enterprise-grade guarantees. We provide reliable engineering tools for LMS integrations, but our service level is defined by clear technical specs rather than contractual obligations.
No SLA provided
We do not offer a Service Level Agreement. While our infrastructure is designed for stability, there is no formal contract guaranteeing specific availability percentages or penalty clauses for downtime.
No uptime guarantee
We do not guarantee 100% uptime. Processing is sequential, so under heavy load, requests may queue. This is inherent to our current architecture, not a failure of service.
No certifications
We do not hold SOC 2, HIPAA, or GDPR certification certificates. Our data policy is transparent: input is used only for generation and not stored for training, but we do not provide third-party audit reports.
Affiliation
CourseSpeak operates as a single, independent storefront for the same underlying text-to-speech API. We are not a subsidiary or official branch of any major technology provider. Our infrastructure, billing, and service management are handled entirely separately from the platforms we often get compared to.
Not affiliated with OpenAI
Although our API endpoint structure and SDK compatibility mirror OpenAI’s speech endpoint, we are not OpenAI. We do not use their models, their servers, or their pricing structures. Our tts-1 and tts-1-hd models are our own licensed recordings, distinct from OpenAI’s offerings.
Not affiliated with Google
We offer Google Sign-In for convenience, but our service is not part of Google Cloud or Google AI. The voice models are not generated by Google’s neural networks. Our data policy and billing (USDT) are completely separate from Google’s ecosystem.
Independent storefront
This site is an independent storefront for the CourseSpeak API. We manage our own keys, balances, and support. Any mention of other brands is strictly for technical comparison or context. We do not resell their services, nor do they distribute ours.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. These errors stem from assuming consumer-grade features or overlooking technical constraints defined in the specification.
23 languages
Any voice speaks any of these languages.
