Frequently asked questions
Who runs PlayTQTQ?
PlayTQTQ is an independent storefront for a cloud text-to-speech API. It is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We operate as a standalone service designed for YouTube creators, providing a simple API endpoint without the complexity of larger enterprise pipelines.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI. Our API uses the same request shape as the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base_url. However, we are a separate entity with our own pricing, voices, and infrastructure.
Where do voices come from?
Our eight voice presets 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, ensuring transparency about the audio's origin and nature.
Is my data safe?
Input text is used only to produce the audio and is not used for training. We keep request metadata (time, characters, status) for billing purposes. We do not offer specific certifications like SOC 2 or HIPAA.
Do you store my audio?
No. Generated audio is returned in the response and is not stored on our servers after delivery. Only request metadata required for billing and usage tracking is retained. This ensures your content remains yours without lingering copies in our infrastructure.
How do I contact support?
Support is available by email only. There is no live chat, phone number, or ticketing system. We handle all customer inquiries through email, so please ensure your contact details are correct in your account settings for timely assistance.
Is there a phone number?
No. We do not offer a phone number for support. All communication is conducted via email. This allows us to maintain a lean, independent operation focused on providing a reliable API without the overhead of traditional telephone support channels.
Do you offer SLA?
No. We do not offer a Service Level Agreement (SLA) or uptime guarantee. There is no enterprise contract or on-premise install option. Our service is designed for flexibility, but we do not guarantee specific availability percentages or compensation for downtime.
Are voices copyrighted?
The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. While the source material is public domain or CC licensed, the specific voice presets are our curated selection.
Can I sue for voice issues?
We do not offer emotion tags, so specific voice issues are limited to the eight presets. Content creators are responsible for ensuring their use complies with local laws. We provide the tool; you manage the legal context of your content.
Who owns the generated audio?
You own the generated audio files produced by your requests. The input text is not used for training, and the audio is not stored by us. You retain full rights to the MP3, WAV, or other format files you download for your videos.
Do you use AI training?
No. Input text is used only to produce the audio and is not used for training our models. We do not use your data to improve our voice engines. The generation is immediate, and your specific inputs remain private to your billing records.
Is the API open source?
No. We do not provide an official SDK of our own, nor is our API code open source. You can use the OpenAI SDK by changing the base_url, or use plain HTTP. The underlying engine and infrastructure are proprietary to PlayTQTQ.
Where are servers located?
We do not specify exact server locations or offer data-center choices. Our service is cloud-based, and we do not provide on-premise installation options.
Who We Are
PlayTQTQ is an independent storefront for a cloud text-to-speech API, built by a small editorial team that understands the specific needs of YouTube creators. We focus on delivering reliable, copyright-safe narration without the complexity of large enterprise pipelines or the overhead of unnecessary features.
Independent Editorial Team
We are a self-contained team dedicated to maintaining a simple, honest API. Our decisions are driven by what creators actually need for their videos, not by corporate roadmaps or investor pressure.
- Small, focused team
- Direct decision-making
- Creator-first design
Focus on Content Creators
Our interface and documentation are tailored for YouTube creators who need straightforward audio generation. We prioritize clear pricing, easy integration via standard HTTP, and voices that fit narrative and documentary styles without requiring technical expertise.
No Affiliation with Major Brands
PlayTQTQ is not affiliated with OpenAI, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We operate independently, using our own infrastructure and keys. Our API is compatible with the OpenAI SDK format, but we are a separate entity with our own pricing, voices, and data policies.
Voice Licensing and Sources
PlayTQTQ voices are built from high-quality recordings of narrators reading classic literature. We use the LibriTTS-R dataset, which provides clean, isolated speech segments ideal for training modern neural TTS models.
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and readings from LibriVox.
LibriTTS-R Dataset
The LibriTTS-R dataset serves as the foundational training material for our eight voice presets.
CC BY 4.0 License
LibriTTS-R is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
Public Domain Audiobooks
Many of the source recordings come from LibriVox, which hosts public domain audiobooks.
Data Policy and Privacy
PlayTQTQ is built for YouTube creators who need reliable narration without data leakage concerns. Our processing is transparent: input text is used solely to generate the audio file and is not used for training our models. Generated audio is returned in the response and not stored on our servers.
Input Text Not Used for Training
Your scripts remain yours. We process the text to synthesize speech but do not retain it for model improvement or resale. This ensures your unique content stays private and is not ingested into any training dataset.
Generated Audio Not Stored
The audio files you generate are returned directly in the API response and are not kept on our servers after delivery. This minimizes storage risks and ensures you retain full ownership of the audio you download for your videos.
Metadata Kept for Billing
We retain request metadata including the timestamp, character count, and status for each call. This data is used exclusively to calculate your usage-based charges ($0.01 per 1,000 characters) and to verify that failed requests are credited correctly.
Honest Limitations
We built PlayTQTQ to be simple and predictable for YouTube creators, which means we skip complex real-time features. We do not offer streaming audio, WebSocket connections, or SSML support. You send a text request and receive a finished audio file, such as an MP3, ready to download and edit in your video timeline.
We also do not offer custom voice cloning. Our eight voices are based on licensed recordings from the LibriTTS-R dataset, derived from public-domain audiobooks. You cannot upload your own voice or design a new one, but you get consistent, copyright-safe narration without the complexity of managing custom models.
No Streaming or WebSocket
We do not provide real-time audio streaming or WebSocket connections. Requests are processed one after another, so under load a request may wait in a queue. For most YouTube workflows, this is not a limitation; you generate the audio file, download it, and edit it offline.
No Custom Voice Cloning
We do not offer custom voice cloning or the ability to upload your own voice. Our eight presets—like Aria, Nova, and Felix—are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobooks. This ensures your narration is copyright-safe without the need for complex voice design pipelines.
No SLA or Uptime Guarantee
We operate as an independent API and do not provide an SLA or uptime guarantee. While we aim for high reliability, we do not offer enterprise contracts or on-premise installations. For most creators, this means straightforward, predictable pricing without hidden fees or complex support tiers.

Contact and Support
PlayTQTQ is an independent API built for YouTube creators who prefer straightforward, asynchronous communication. We keep our support structure simple to ensure every query receives focused attention without the noise of generalist help desks.
Email Support Only
All inquiries are handled via email. This allows our team to provide detailed, written responses that you can reference later, which is especially useful for technical troubleshooting or billing questions.
- Support email: [email protected]
No Phone or Live Chat
We do not offer phone lines or live chat widgets. By avoiding real-time channels, we eliminate hold times and ensure that your support ticket is processed in the order it was received, without priority bias.
Response Times
Typical response time is within 24 hours on business days. During high load periods, such as major API updates or billing cycles, responses may take up to 48 hours. We prioritize clarity over speed.
Technical Infrastructure
PlayTQTQ operates as a cloud-based REST API, meaning you interact with the service entirely via standard HTTP requests. There is no software to install on your local machine or server. You simply send your text payload to our endpoints and receive the generated audio file directly in response. This architecture ensures low overhead and easy integration into any existing content creation pipeline, from simple scripts to complex automation workflows.
The API is designed to be OpenAI-compatible, using the same request shape and endpoint structure as the widely adopted OpenAI speech endpoint. By changing the base_url to https://api.playtqtq.com/v1 and using your PlayTQTQ API key, you can leverage official OpenAI SDKs without rewriting your code. This compatibility allows YouTube creators to quickly swap in alternative TTS engines or switch providers if needed, ensuring your workflow remains flexible and vendor-agnostic.
Cloud-Based API
Our infrastructure runs entirely in the cloud, eliminating the need for local processing power or specialized hardware. You send text and receive audio files, keeping your local environment clean and efficient.
- No local software installation required
- Scales automatically with demand
OpenAI-Compatible Endpoint
We mirror the standard OpenAI speech endpoint structure. This means you can use familiar libraries and SDKs with minimal configuration changes.
Simply update your base_url to https://api.playtqtq.com/v1 and inject your unique PlayTQTQ key to get started immediately.
- Uses standard JSON request bodies
- Compatible with official OpenAI SDKs
Standard HTTP Methods
The API relies on standard HTTP methods: POST for generating speech and GET for retrieving voice lists or model information.
This simplicity ensures broad compatibility with virtually any programming language or automation tool, from Python scripts to Node.js applications.
- POST for audio generation
- GET for metadata and voices
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This style helps retain viewer attention by reducing the 'read-aloud' fatigue often associated with standard TTS.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Creative Commons Attribution 4.0
- openai-python on GitHub
- curl documentation
- LibriTTS-R paper (arXiv 2305.18802)
- OpenAI API reference: create speech
- IETF RFC 7845: Ogg Opus
- MDN: Web Speech API
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
- TRON developer hub: TRC-20
- W3C WAI: making audio and video accessible
