Frequently asked questions
Who runs this site?
ReadAloud Freelance is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or any other major brand. Our team supports freelancers and bloggers by providing a simple, direct API endpoint for generating high-quality audio files from text, without the complexity of managing infrastructure.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from the LibriTTS-R dataset. These recordings originate from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech.
Are the voices licensed?
Yes, the underlying recordings are sourced from LibriTTS-R under a CC BY 4.0 license.
Is my text data sold?
No. Your input text is used exclusively to produce the audio file for your request. We do not use your text for training our models or for any other commercial purposes. Once the audio is generated, the text itself is not stored for long-term analysis or resale to third parties.
Is my audio stored?
No. Generated audio is returned directly in the API response and is not stored on our servers after delivery. We only retain request metadata, such as the time, character count, and status, specifically for billing purposes. Your actual audio content is transient and does not remain in our storage.
How long is metadata kept?
We keep request metadata, including timestamp, character count, and status, for billing purposes. This data allows us to accurately track your usage against your balance and ensure correct charges for each request.
Do you have a phone number?
No, we do not have a phone number. Our communication channels are limited to email. If you need assistance with your API key, billing, or technical questions, you will reach our support team via email, ensuring a clear written record of your query.
How do I contact support?
Support is available via email only. You can reach us through the contact page or by emailing our support team directly. We do not offer phone support or live chat. Please include your account details and a description of your issue to help us resolve your request efficiently.
Who We Are
We understand the pressure of client deadlines and the need for reliable, high-quality audio without the overhead of managing infrastructure.
Our team focuses on delivering straightforward, honest APIs that fit into your existing workflow.
Editorial Team
We are a small editorial team of writers and developers who build text-to-speech tools for people like you. We understand the pressure of client deadlines and the need for reliable, high-quality audio without the overhead of managing infrastructure.
- Writers and developers with TTS experience
- Focus on reliable, high-quality audio
- Small, dedicated team
Freelancer Focus
Our team focuses on delivering straightforward, honest APIs that fit into your existing workflow. We test every voice and format to ensure consistency, so you can trust the output for blogs, accessibility projects, and client deliverables.
- Fits into existing workflow
- Consistent output for blogs and accessibility
- Straightforward, honest API
Voice Licensing
ReadAloud Freelance’s voice models are built on licensed recordings from the LibriTTS-R dataset, derived from LibriVox public-domain audiobook readings. This foundation ensures high-quality synthetic speech without the need for custom voice design or celebrity impersonations.
The dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
LibriTTS-R Source
Our eight voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are based on the LibriTTS-R dataset. This collection comes from LibriVox, a community of volunteers reading public-domain books. Each voice captures distinct tones, from warm narrators to energetic promos, all grounded in real human recordings.
CC BY 4.0
The underlying audio data is licensed under CC BY 4.0. This means the source material is freely available for use and adaptation, provided attribution is given where required. We leverage this open license to keep our API accessible and cost-effective for freelancers who need reliable, high-quality TTS without complex licensing chains.
Data Policy
We respect the work you do for your clients. Your input text is used solely to generate the audio response and is never retained for model training or future analysis.
Text Usage
The text you send via the API is processed to create the speech file and is not stored long-term. This ensures your client’s content remains private during generation.
Audio Storage
Generated audio is returned directly in the API response and is not stored on our servers after delivery. Only request metadata—such as time, character count, and status—is kept for billing purposes.
Honest Limits
We build for freelancers who need reliable tools, not corporate promises. Our infrastructure is designed for efficiency, but we do not wrap it in Service Level Agreements. You get a straightforward API that processes requests in sequence, prioritizing clear delivery over guaranteed milliseconds of latency.
No SLA
We do not offer formal Service Level Agreements or penalty clauses for downtime. Our system processes requests one after another, so high volume can lead to queuing. This keeps costs low and predictable for your freelance projects, but it means no contractual guarantee on response times.
No Uptime Guarantee
While we aim for consistent operation, occasional interruptions may occur without notice. For mission-critical commercial broadcasts, you might want to keep a backup plan, but for most blog and accessibility work, our API remains a steady, affordable choice.

Contact
We built this API for freelancers who need reliable tools without bureaucratic hurdles. Our support team understands the pressure of client deadlines and the nuances of accessibility projects. We prioritize clear, direct communication to help you integrate the API quickly and resolve issues without unnecessary delays.
When you reach out, you can expect a human response that focuses on solving your specific problem.
Email Support
All inquiries are handled via email. This ensures every question is logged, reviewed, and answered with the necessary context. You will receive a response from a team member who understands both the technical details of the API and the practical needs of freelance workflows.
We do not use automated ticket queues that lose context. Your email goes directly to our support channel, where we track your issue until resolution. This approach allows us to maintain high-quality, personalized assistance even during peak usage periods.
- Support via [email protected]
- No automated ticket numbers
- Direct access to technical context
No Phone
We do not offer a phone number. For freelancers working remotely or across time zones, email provides a written record of the solution, which is often more useful than a verbal conversation. You can reference the exact wording when explaining the fix to a client or documenting your workflow.
This also keeps our operations lean, allowing us to focus resources on maintaining the API’s reliability and adding features rather than staffing a call center.
Technical Approach
The ReadAloud Freelance TTS API is designed for developers who prefer direct, predictable integrations. By focusing on a clean API-first architecture, we ensure that your text-to-speech workflows are lightweight and easy to implement without unnecessary overhead. This approach allows you to generate audio files programmatically and integrate them directly into your projects, whether you are building a custom web app or automating content creation for blogs.
Our technical foundation relies on well-established standards that freelancers already know and trust. We support the same request shape as the OpenAI speech endpoint, meaning you can use official OpenAI SDKs by simply changing the base URL. This familiarity reduces the learning curve and lets you focus on delivering high-quality speech to your clients, rather than figuring out a proprietary protocol.
API First
The ReadAloud Freelance TTS API is designed for developers who prefer direct, predictable integrations. By focusing on a clean API-first architecture, we ensure that your text-to-speech workflows are lightweight and easy to implement without unnecessary overhead. This approach allows you to generate audio files programmatically and integrate them directly into your projects, whether you are building a custom web app or automating content creation for blogs.
Our technical foundation relies on well-established standards that freelancers already know and trust. We support the same request shape as the OpenAI speech endpoint, meaning you can use official OpenAI SDKs by simply changing the base URL. This familiarity reduces the learning curve and lets you focus on delivering high-quality speech to your clients, rather than figuring out a proprietary protocol.
- - POST https://api.ub150.net/v1/audio/speech for audio generation
- - GET /v1/voices to list available presets
- - GET /v1/models for model details
- - JSON body with standard fields like model, input, voice, and speed
Open Standards
We believe in using open, documented standards that don't lock you into a single ecosystem. Our API endpoints are straightforward and follow common RESTful patterns, making it easy to integrate with a wide variety of programming languages and frameworks. This openness ensures that you have full control over your data and can switch or adapt your tech stack as needed without being tied to a specific vendor's proprietary tools.
By adhering to open standards, we also ensure that our API remains compatible with the broader developer community. This means you can leverage existing tools, libraries, and community knowledge to enhance your TTS integration. Whether you are using Python, JavaScript, or any other language, you can rely on the same consistent experience and predictable outcomes.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. For content creators working with diverse audiences, language support is critical.
23 languages
Any voice speaks any of these languages.
