Frequently asked questions
Who runs the DubSync API?
DubSync API is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We provide the engine that fits into your localization workflow, operated independently to serve freelancers and agencies directly.
Are the voices copyrighted?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file carries an inaudible watermark marking it as synthetic speech.
Do you use my text for training?
No. Input text is used only to produce the audio and is not used for training. We respect your data privacy by ensuring your specific content remains isolated to the generation process, allowing you to use the output for your projects without worrying about model retraining.
Do you store my generated audio?
Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, strictly for billing purposes. Your actual audio files are delivered to you and are not retained on our servers after the synthesis is complete.
Is there an uptime guarantee?
We do not offer an SLA or uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds. We aim for reliability but do not promise specific availability percentages.
Do you have a physical office?
We do not have a physical office. As an independent storefront, we operate remotely to keep costs low and pass savings to you. We do not offer on-premise installs or data-center choices. Our entire operation, from API infrastructure to support, is managed digitally.
Can I contact you by phone?
No, we do not have a phone number. Support is by email only. We do not offer live chat or phone support. Email remains our primary channel for assisting freelancers and agencies with their API keys, billing questions, or technical issues regarding the TTS engine.
Is there a live chat option?
No, there is no live chat option. We rely on email support to handle inquiries efficiently. This allows us to maintain a focused workflow for our freelancers and agencies without the overhead of real-time chat agents, ensuring your questions are answered by knowledgeable staff.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint shape, so official OpenAI SDKs work by changing the base_url. However, we are an independent provider using our own engine and pricing, completely separate from OpenAI’s services and infrastructure.
Do you offer enterprise contracts?
No, we do not offer enterprise contracts. We have no monthly plans, no seats, and no minimum spend. Our model is designed for flexibility, allowing you to pay only for what you use via USDT top-ups. There are no complex contracts or volume commitments required.
Is there a GDPR certificate?
No, we do not have a GDPR certificate. We also do not offer certifications like SOC 2 or HIPAA. We process data simply: input text is used for generation, and metadata is kept for billing. We do not claim specific regulatory compliance certifications for our infrastructure.
Do you have a WordPress plugin?
No, we do not have a WordPress plugin. We also do not offer a browser extension or a mobile SDK. You can integrate our API using the official OpenAI SDK or plain HTTP requests. Our solution is designed to fit into your existing localization workflow via code.
Can I use the voices commercially?
Yes, you can use the voices commercially. Our voices are based on LibriTTS-R (CC BY 4.0) and public-domain readings. Every generated file carries an inaudible watermark marking it as synthetic speech. You can use these audio files for your dubbing projects without additional licensing fees beyond the API cost.
How do I contact support?
Support is by email only. We do not have a phone number, live chat, or physical office. You can reach us through the contact page on our site. We are here to help freelancers and agencies with their TTS needs, but all communication goes through email.
Who we are
We are DubSync API, an independent team of developers and voice enthusiasts who build cloud text-to-speech tools specifically for localization freelancers and indie creators. We focus on providing a reliable, straightforward API that integrates into your existing dubbing workflow.
Independent TTS providers
Our engine is designed from the ground up for high-volume voiceover production. We provide the core TTS technology without the overhead of a massive enterprise platform, ensuring that your projects run efficiently whether you are dubbing a short indie film or a long-form e-learning course.
Built for freelancers
We understand the pressure of tight deadlines. Our API allows you to generate audio files using standard JSON requests, fitting into your automation scripts. With 23 languages and 8 distinct voice presets, you can maintain consistent quality across diverse projects without juggling multiple tools.
No corporate overhead
No complex contracts, no minimum spend, and no seat licenses. You pay only for what you use, with transparent pricing at $0.01 per 1,000 characters. This simplicity means more of your budget goes toward creativity and less toward administrative overhead or unused features.
Voice licensing and origins
DubSync API’s voice presets are rooted in high-quality, ethically sourced audio. Our voices are based on the LibriTTS-R dataset, providing a consistent base for all generated audio.
LibriTTS-R base data
Our eight voice presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are derived from the LibriTTS-R dataset. This provides a consistent, high-fidelity base for all generated audio, ensuring realistic intonation across our 23 supported languages.
CC BY 4.0 licensed
The underlying voice data is licensed under CC BY 4.0. This transparent licensing model allows us to deliver synthetic speech for your commercial dubbing and localization projects.
LibriVox public domain sources
The voice data originates from LibriVox, a community of public-domain audiobook readers. By leveraging these existing recordings, we maintain cost-effective scalability for freelancers and agencies.
Data privacy policy
When you send text to our API, it is processed solely to generate the requested audio file. We do not repurpose your input data for any other purpose beyond delivering the final sound file to your application.
Text used only for synthesis
Your input characters are processed exclusively to create the audio response.
No training on input
The text you submit is never added to our training datasets. Your unique scripts, scripts for dubbing projects, or localized content remain yours and are not used to train future voice models.
Audio not stored
Generated audio files are returned directly in the response and are not retained on our servers after delivery. We keep only request metadata—such as timestamp, character count, and status—for accurate billing purposes.
Technical infrastructure
DubSync API runs entirely in the cloud, delivering audio files via standard HTTP requests. You send text to our endpoint and receive an audio file back. There is no infrastructure to manage on your side, no servers to patch, and no local dependencies to configure.
Cloud-based API
You simply connect via HTTPS. The service handles the heavy lifting of audio synthesis, allowing you to focus on your localization workflow rather than server maintenance.
Standard JSON endpoints
We use standard RESTful endpoints with a familiar JSON request shape. You POST your text and parameters to https://api.playtk71.com/v1/audio/speech. The response returns the audio file directly, making it easy to integrate into existing scripts or automation tools.
OpenAI SDK compatible
Because our request structure mirrors the OpenAI speech endpoint, you can use the official OpenAI SDKs. Just change the base_url to https://api.playtk71.com/v1 and provide your API key. This means you can likely drop our API into your current code with minimal changes.

Honest limitations
We believe in transparency about what our API can and cannot do right now. Understanding these boundaries helps you plan your dubbing workflows correctly without unexpected surprises during integration.
Our focus remains on delivering reliable, high-quality static audio files via a straightforward REST interface that fits seamlessly into your existing localization pipeline.
No streaming support
We do not offer WebSocket or streaming endpoints. Audio is generated as a complete file and returned in the response body. This means you must wait for the full synthesis to finish before proceeding.
No custom voice cloning
You cannot upload a sample to clone a specific voice. We provide eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) based on licensed LibriTTS-R data. These are fixed assets available to all users.
No SLA guarantees
We do not promise specific uptime percentages or financial credits for downtime. Our service is offered "as is" without enterprise-level service level agreements or on-premise deployment options.
Support is handled via email only, with no phone number or live chat available for immediate troubleshooting during peak dubbing deadlines.
Contact and support
We keep things simple. Our support team is available to help with any questions about your API key, billing, or integration issues. We focus on solving your specific problems efficiently.
Email support only
All inquiries are handled via email. This allows us to provide detailed, written responses that you can reference later when debugging your localization workflow. You can reach us at [email protected].
No live chat
We do not offer live chat widgets. This decision helps us maintain a focused team that can dedicate full attention to your tickets without the distractions of real-time conversations. Expect a thorough reply rather than a quick ping.
No phone number
There is no direct phone line for support. As a cloud API provider, we prioritize asynchronous communication that fits into your freelance schedule. Email remains our primary and only channel for assistance.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Locators master cultural nuance while dubbing artists breathe soul into characters for global audiences.
23 languages
Any voice speaks any of these languages.
