Frequently asked questions
Who runs PodcastVoice?
PodcastVoice 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 focuses on providing a simple, reliable API for content creators and podcasters to generate high-quality narration and voiceovers instantly.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These voices originate from LibriVox public-domain audiobook readings. Each generated file includes an inaudible watermark to mark it as synthetic speech, ensuring transparency about the audio source and its synthetic nature.
Is my text data used for training?
No. Your input text is used only to produce the specific audio file requested. We do not use your text for training our models or improving the API. Your creative content remains yours, processed solely for the immediate generation of your audio output.
Do you store generated audio?
No. Generated audio is returned directly in the API response and is not stored on our servers. We retain request metadata, such as time, character count, and status, strictly for billing purposes. Your actual audio files are transient and not kept after delivery.
How is the API different from OpenAI?
We use the same request shape as the OpenAI speech endpoint, so you can use the official OpenAI SDKs by changing the base_url. However, we are a separate entity offering specific voice presets and a different pricing model. We are not OpenAI and offer distinct voice options.
Can I sue if the audio is bad?
We provide no SLA, uptime guarantee, or enterprise contract, and no certifications. While we strive for quality, we do not guarantee specific outcomes for every request. You can test voices with your free trial credit before committing. Our terms govern liability, but we do not offer formal warranties on audio quality.
Do you have a physical office?
We do not list a physical office or provide a phone number or live chat. As an independent API provider, we operate remotely to keep costs low for creators. Our support and operations are managed digitally, allowing us to focus entirely on delivering a reliable text-to-speech API service.
How do I contact support?
Support is available by email only. You can reach us via the contact page or by emailing our support team. We aim to respond to your inquiries promptly via email communication.
Is the site affiliated with OpenAI?
No. PodcastVoice is an independent storefront. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We simply offer an API compatible with the OpenAI request shape, but we are a separate company with our own voices and pricing.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, we do not offer automatic refunds. Since audio is generated instantly, you can test with your free trial credit. We do not process refunds for completed, successful audio generations.
What happens to my API key if I leave?
You can issue a new API key at any time. When you do, the old key stops working immediately. You can manage your keys directly from your account dashboard. There is no minimum spend or contract, so you can start or stop using the API freely.
Are the voices permanent?
The eight voice presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are stable, but we do not guarantee they will never change. As an independent provider, we may update or adjust voice options. We aim to maintain consistency for your podcasting workflow, but changes are possible.
Do you track my usage?
Yes, we track request metadata including time, character count, and status for billing purposes. We count spaces and punctuation as characters. This data ensures accurate billing at $0.01 per 1,000 characters. We do not store the actual audio files or use your text for other purposes.
Is the API open source?
No, we do not offer an open-source SDK or make our core API code public. We provide an HTTP API compatible with the OpenAI format. You can use the official OpenAI SDK or plain HTTP requests. We are a proprietary service, not an open-source project.
Our Mission
PodcastVoice was built for creators who want professional narration without the studio overhead. We provide a straightforward API that lets you generate high-quality voiceovers instantly, fitting seamlessly into your existing podcast workflows.
Empowering Creators
Our API gives you full control over your audio assets. Generate intros, segment narration, or create voiceovers on demand. You own the output, and our tools are designed to scale with your content production needs.
- Direct API access for custom integrations
Simplifying Audio Production
Stop waiting for studio slots or editing hours. With a simple API call, you get audio files ready for your editor. Our system handles the synthesis, so you can focus on scripting and storytelling.
Independent Standards
We operate independently, offering clear pricing and transparent limits. No hidden subscriptions or surprise fees. Just a reliable engine for your audio needs, powered by licensed voices and open standards.
Voice Licensing
PodcastVoice offers eight distinct voices crafted from licensed recordings, providing a curated catalog tailored for natural storytelling. These voices range from warm narrators to energetic promo styles, ensuring your podcast intros and voiceovers sound professional without the need for expensive studio time.
LibriTTS-R Source
Our voice library is built on the LibriTTS-R dataset, which contains high-quality speech recordings optimized for text-to-speech synthesis. This foundation ensures consistent audio quality across all eight presets, from Aria’s clear narration to Orion’s deep documentary tone.
CC BY 4.0 License
The underlying voice data is licensed under CC BY 4.0, allowing us to legally aggregate and offer these voices as part of our API service. This license ensures that the core audio assets are freely available for commercial and non-commercial use, provided proper attribution is maintained where required.
Public Domain Origins
Many of the source recordings originate from LibriVox, featuring public-domain audiobook readings. This means the original performances are free from copyright restrictions, allowing us to focus on engineering and integration rather than licensing complexities. The result is a transparent, cost-effective solution for creators.
Data Privacy
We respect your creative process. Your input text is used strictly for the purpose of generating the requested audio file and is not retained for training our models. Once the audio is delivered, the input text is not stored indefinitely.
No Training Data Use
Unlike many consumer-grade TTS services, we do not use your scripts to improve our neural networks. Your unique narration styles and content remain yours, ensuring your intellectual property is not repurposed for our model development.
Temporary Storage
Generated audio files are returned directly in the API response and are not permanently stored on our servers. This minimizes the risk of data leakage and ensures your content is ephemeral unless you choose to save it locally.
Billing Metadata
We retain minimal metadata required for accurate billing and troubleshooting. This includes the timestamp, character count, and request status. This data is used solely to verify your usage and to resolve any potential disputes.
Technical Infrastructure
PodcastVoice operates entirely as a cloud-based API, allowing you to generate narration and voiceovers instantly without managing servers or hardware. You simply send text via HTTP and receive audio files, streamlining your production workflow from script to final audio.
Cloud-Based API
Our infrastructure handles the heavy lifting of synthesis in the cloud. You focus on content creation while our endpoints process your requests, ensuring consistent performance without the overhead of maintaining your own audio servers.
OpenAI Compatible
Because our endpoint structure mirrors the OpenAI speech API, you can use the official OpenAI SDKs by simply changing the base_url to https://api.playgb168.com/v1. This compatibility means you likely already have the code to integrate our voice engine into your existing tools.
- Supports
tts-1andtts-1-hdmodels - Standard JSON request body
- Uses standard
Authorization: Bearerheaders
Rate Limiting
To ensure fair usage, we enforce a limit of 60 requests per minute per API key. New accounts without top-ups start with a lower limit of 10 requests per minute. This structure helps maintain stable generation times for all creators.
Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real time (about 25 characters per second), but short phrases may take a few seconds.
- 60 requests/minute after top-up
- 10 requests/minute for new accounts
- Sequential processing ensures stability

Support & Contact
PodcastVoice is built by creators for creators, which means we prioritize clear, direct communication over corporate bureaucracy. We don't hide behind automated menus or endless call queues. When you need help with your API key, billing, or voice selection, you speak directly to humans who understand the technical nuances of TTS.
Email Support Only
We handle all inquiries via email. This allows us to maintain detailed records of your specific technical context and billing history, ensuring accurate solutions without the noise of live chat interruptions.
- Direct access to support staff
- Detailed ticket history for context
- No automated menu loops
No Live Chat
We do not offer live chat widgets. Our workflow is designed for asynchronous, thoughtful responses rather than real-time pressure. This ensures you receive complete, verified answers rather than quick, potentially incomplete guesses.
Response Times
While we do not guarantee a specific hour-by-hour response window, we aim to reply within 24 hours on business days. For urgent billing issues or API key resets, we often respond faster. Complex technical queries may take slightly longer as we verify your usage logs.
- Target: <24 hours on business days
- Urgent billing: often faster
- Complex queries: variable duration
Transparency
PodcastVoice operates with zero hidden fees. There are no monthly plans, no subscription seats, and no minimum spend requirements. You pay only for what you generate, and failed requests are refunded in full. Your balance never expires, and there are no invoices with added VAT complications.
We keep our limits honest and visible. The API processes requests sequentially, meaning load can affect speed. We also do not offer streaming or real-time partial audio, ensuring you always know exactly what you are getting when you integrate our simple POST endpoint.
No Hidden Fees
We charge strictly by character count: $0.01 per 1,000 characters. There are no platform fees, no tiered pricing structures, and no surprise costs for high-quality formats like FLAC or Opus. You top up with USDT (TRC-20), and the credit appears automatically.
Failed synthesis requests are free. If the API returns an error, you are not charged. This ensures you only pay for successful audio generation, keeping your production costs predictable and transparent.
Clear Pricing
Our pricing is flat and simple: $10 per million characters. Spaces and punctuation count as characters. This single rate applies to both the standard 'tts-1' and high-definition 'tts-1-hd' models, which use the same engine and voice presets.
There are no hidden costs for language support or voice selection. All eight voices are included in the base price. Whether you are generating a 5-minute podcast intro or a 4,096-character narration, the cost is calculated directly from your input text length.
Honest Limits
We do not promise infinite speed. Requests are processed sequentially, so under heavy load, synthesis may wait in a queue. Typical speed is roughly real-time (25 characters per second), but short phrases may take a few seconds to generate.
We are transparent about our constraints. We do not offer streaming audio, SSML, or custom voice cloning. Our rate limit is 60 requests per minute per key. We do not provide an SLA or uptime guarantee, ensuring you know exactly what to expect from our independent API.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice is built from licensed LibriTTS-R recordings, providing a professional foundation for high-quality audio generation.
23 languages
Any voice speaks any of these languages.
