Frequently asked questions
Who runs the SyncVoice API?
SyncVoice API is an independent storefront operating at playbd2.com. It is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. The service provides a cloud text-to-speech API endpoint that accepts standard JSON requests. Accounts are managed independently per site, allowing localization agencies to integrate the API directly into their existing workflows without relying on third-party platform dependencies.
Where do the voices come from?
The eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These sources include readings from LibriVox public-domain audiobooks. Each generated audio file carries an inaudible watermark to mark it as synthetic speech. The voices are algorithmic presets derived from these licensed sources, not custom-cloned recordings of specific individuals.
Is my data used for training?
No. Input text is used exclusively to produce the requested audio file. It is not used for model training or improving the engine. Generated audio is returned in the response and is not stored by the system. Only request metadata, such as time, character count, and status, is retained for billing purposes.
How long is my audio stored?
Generated audio is not stored after it is returned in the API response. The system does not retain copies of the created audio files. Only request metadata, including timestamp, character count, and status, is kept for billing and usage verification. This ensures that your localized audio assets remain under your control.
Do you have a physical office?
There is no on-premise installation option. Support is handled entirely via email, so a physical office is not required for customer communication or service delivery.
Can I speak to a human on the phone?
No. SyncVoice API does not offer a phone number or live chat support. All customer support is conducted via email only. This applies to all inquiries, including technical issues or billing questions. There is no direct voice line available for customers to call for immediate assistance or verbal explanations.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons Attribution license. The SyncVoice API uses voices derived from LibriTTS-R, which is licensed under CC BY 4.0. This means the source recordings allow for reuse and modification, provided attribution is given. The API voices are based on these licensed recordings from LibriVox public-domain audiobook readings.
How do I contact support?
Support is available via email only. There is no phone number or live chat option. You can reach the support team through the contact page at https://playbd2.com/contact/. Email is the sole channel for all inquiries, including technical issues, billing questions, and general support requests for localization agencies using the API.
Do you offer refunds?
Failed requests are free, with the charge returned in full if synthesis fails. There is no explicit mention of refunds for successful requests. Top-ups are made via USDT on the TRON network. Balance does not expire. Refunds are specifically guaranteed only in the case of failed synthesis requests, not for general dissatisfaction.
Is the API owned by OpenAI?
No. SyncVoice API is an independent storefront and is not affiliated with OpenAI. It uses a similar request shape to the OpenAI speech endpoint, so OpenAI SDKs work by changing the base URL. However, the service, keys, and infrastructure are owned and operated independently by SyncVoice at playbd2.com.
Can I sue for errors?
The API does not offer an SLA or uptime guarantee. There is no enterprise contract or specific liability terms mentioned. While failed requests are free, there is no explicit guarantee of performance. Customers assume the risk of errors, as there is no certified SLA or on-premise install.
How do I verify the voice licenses?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0). These sources include readings from LibriVox public-domain audiobooks. Each generated file carries an inaudible watermark marking it as synthetic speech. The API uses these licensed presets, and the CC BY 4.0 license allows for their use with attribution.
Who We Are
SyncVoice API operates as an independent entity, distinct from major cloud providers. Our editorial team directly manages the API infrastructure and voice presets, ensuring that the 8 available voices remain consistent and accurate for enterprise clients. We focus on reliable, programmatic audio generation rather than consumer-facing features.
Editorial Team Overview
We are engineers and localization specialists who understand the technical constraints of global media production. Our team manages the API infrastructure and voice presets directly, ensuring that the 8 available voices remain consistent and accurate for enterprise clients.
Mission and Values
We provide a reliable TTS API designed for localization agencies processing high volumes of video voice-overs. Our mission is to replace manual recording workflows with programmatic audio generation at scale, offering predictable pricing and strict data policies.
Independent Operation
SyncVoice is not affiliated with OpenAI, ElevenLabs, or other brands mentioned in comparisons. We operate independently, maintaining full control over voice licensing from LibriVox and the underlying API architecture without external dependencies or shared infrastructure agreements.
Voice Licensing
SyncVoice API generates synthetic speech from licensed voice recordings rather than cloning specific individuals. Our voice models are derived from the LibriTTS-R dataset, ensuring clear legal provenance for commercial localization workflows.
LibriTTS-R Dataset
We utilize the LibriTTS-R dataset, which contains high-quality audio from public-domain audiobook readings. This foundation allows us to offer eight distinct voice presets without infringing on proprietary voice rights.
CC BY 4.0 License
The underlying dataset is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This permits commercial use, including your internal and client-facing voice-over projects.
LibriVox Source Material
Voice samples originate from LibriVox public-domain recordings. These are established literary readings, not celebrity or influencer impressions, ensuring consistent, professional audio quality suitable for corporate and agency environments.
Data Policy
SyncVoice API treats input text as ephemeral data used exclusively for the synthesis of the requested audio file. Your source scripts are not retained after processing and are never used to train our voice models or improve the engine, ensuring that your localized content remains proprietary to your agency.
Input Text Usage
The text payload is processed in real-time to generate the audio output and is discarded immediately upon completion. This ensures that your translation assets and localization drafts remain confidential and are not ingested into our training datasets.
Audio Storage Policy
Generated audio files are returned directly in the API response and are not stored on our servers. Once your system receives the file, SyncVoice holds no copy of the synthesized voice-over, eliminating long-term storage liabilities for your agency.
Metadata Retention
We retain request metadata—including timestamp, character count, voice used, and status—to facilitate accurate billing and usage auditing. This data is strictly limited to operational and financial record-keeping and is not shared with third parties.
Technical Infrastructure
SyncVoice API operates as a cloud-native service, eliminating the need for on-premise hardware or data-center selection. Requests are processed sequentially. There is no official SDK of our own; integration relies on standard HTTP clients or the official OpenAI SDK with an adjusted base URL, ensuring broad compatibility across existing localization pipelines.
Cloud-Based Delivery
The service is entirely cloud-based, delivering audio files via standard HTTP responses. This architecture removes the need for local voice server maintenance, allowing localization agencies to scale processing power independently of their internal IT resources. There is no on-premise install option or choice of physical data centers.
API Architecture
The core endpoint is POST https://api.playbd2.com/v1/audio/speech, accepting JSON bodies identical to the OpenAI speech schema. This design allows teams to reuse existing OpenAI SDK configurations by simply updating the base_url and authentication header. The endpoint handles model selection (tts-1 or tts-1-hd), voice presets, and format output in a single synchronous call.
- Standard JSON request/response format
- Compatible with OpenAI SDKs
- Single synchronous HTTP call
Scalability
Scalability is managed through rate limiting rather than manual server provisioning. Each API key is capped at 60 requests per minute, with a baseline limit of 10 requests per minute before top-ups. For high-volume localization jobs, text is split into 4096-character chunks and processed sequentially. Under heavy load, requests may wait in a queue.
- 60 requests/minute per key
- Sequential processing queue
- No manual server scaling

Contact and Support
SyncVoice operates as an independent API provider without a traditional support desk. Our team manages all inquiries through a single, dedicated email channel, ensuring that every message is handled with the same technical precision as our API documentation.
Email Support Only
We do not maintain a live chat widget or a public-facing help center. All communication occurs via email, which allows us to attach technical logs, code snippets, or billing details directly to your ticket without the friction of switching interfaces.
No Phone or Chat
Unlike many SaaS platforms, we offer no phone support or real-time chat. This deliberate choice reduces overhead and keeps our pricing competitive for high-volume localization agencies who prefer asynchronous, documented communication over immediate verbal resolution.
Response Times
We aim to respond to all inquiries within one business day. While we do not guarantee a specific SLA, our small, dedicated team ensures that technical and billing questions receive prompt, accurate answers from people who understand the API deeply.
Limitations and Honesty
SyncVoice API operates as an independent service without enterprise-level contractual obligations. We do not offer SLAs, on-premise installations, or certifications (SOC 2, HIPAA). Our infrastructure is cloud-based, and while we strive for reliability, we make no uptime guarantees.
No SLA Guarantee
Unlike enterprise contracts, we do not offer SLAs, on-premise installations, or certifications (SOC 2, HIPAA).
No Custom Cloning
We do not offer custom voice cloning or the ability to upload your own voice recordings. Our eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0). We do not imitate real people’s voices, celebrities, or politicians.
Transparent Pricing
Pricing is straightforward: $10 per 1 million characters. Failed requests are free. We do not use monthly plans, seats, or subscriptions. All charges are visible in your dashboard, with no hidden fees for VAT or invoices.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This scope targets core localization needs without unnecessary fragmentation.
23 languages
Any voice speaks any of these languages.
