Frequently asked questions
Who runs BotVoice?
BotVoice is an independent storefront for a cloud text-to-speech API. We help product teams integrate reliable TTS into voice assistants and chatbots without managing infrastructure. We provide a straightforward API with clear pricing and standard formats to speed up your voice UX development.
Where do the voices come from?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We use eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These recordings form the basis of our synthetic speech engine.
Is the content licensed?
Yes. The underlying voice recordings are licensed under CC BY 4.0 from LibriTTS-R and are public-domain readings from LibriVox. Generated audio files are returned in the response and not stored by us, ensuring your input text is used only for synthesis.
Do you sell user data?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) solely for billing purposes.
How do I contact support?
Support is by email only. We do not offer a phone number or live chat. You can reach us via the contact page or by emailing our support team for assistance with your account or API usage.
Is this an official OpenAI site?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint shape matches the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base URL to ours.
Do you offer enterprise contracts?
No. We do not offer enterprise contracts, SLAs, or uptime guarantees. We have no minimum spend, no monthly plans, and no seats. Our model is straightforward: pay per character used, with no complex tiered pricing or custom agreements.
Can I use the voices commercially?
Yes. The underlying recordings are from public-domain sources or licensed under CC BY 4.0. You can use the generated audio for commercial projects like voice assistants and chatbots.
How is the audio watermarked?
Every generated file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded in the audio output to identify the content as AI-generated, distinguishing it from human-recorded audio without affecting the listening experience.
Do you store the input text?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Only request metadata (time, characters, status) is kept for billing purposes.
Is there a SLA for uptime?
No. 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 (about 25 characters per second); requests are processed one after another, so under load a request may wait in a queue.
Do you have a phone number?
No. We do not have a phone number or live chat. Support is by email only.
What is the character limit per request?
The input field accepts up to 4096 characters per request. For longer texts, you should split them into parts of up to 4096 characters and join the resulting audio files. Spaces and punctuation count toward the character limit.
How do I report a bug?
You can report bugs by contacting our support team via email. Since we do not offer live chat or a phone number, email is the primary channel for technical support and issue reporting for the BotVoice API.
Who We Are
BotVoice is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or any other brand. Our editorial team manages this site to provide clear, factual information for product teams integrating TTS into voice assistants and chatbots.
Editorial Team
We focus on practical, step-by-step guidance for developers. Our content reflects the actual capabilities of the API, avoiding hype and unverified claims. We ensure every detail matches the technical reality of the service.
Independent Storefront
This site operates independently to sell the same API used by many. We handle the storefront experience, billing, and documentation. The API endpoint remains consistent: POST https://api.playfk9.com/v1/audio/speech. We do not resell a different product; we provide direct access to the infrastructure.
Focus on Voice UX
Product teams need reliable speech generation without managing servers. We provide standard formats like mp3 and wav, supporting 23 languages. Our goal is to help you build consistent voice experiences for chatbots and assistants using clear, documented endpoints.
Our Mission
BotVoice exists to help product teams integrate reliable text-to-speech into voice assistants and chatbots without managing infrastructure. We provide a straightforward API with clear pricing and standard formats to speed up your voice UX development.
Our goal is to remove friction from the integration process, allowing developers to focus on conversational design rather than audio engineering details.
Simplify TTS Integration
We offer a standard API endpoint that mirrors the OpenAI speech format, meaning you can use existing OpenAI SDKs by simply changing the base URL. This eliminates the need for custom client code or learning a new integration pattern.
The API handles audio generation; for texts longer than 4096 characters, you must split the text into parts and join the resulting audio files.
- Standard JSON body with model, input, voice, and speed fields
- Supports mp3, wav, opus, flac, and pcm formats
- Automatic text chunking for inputs exceeding 4096 characters
Transparent Pricing
Pricing is straightforward: $10 per 1 million characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you only pay for successful synthesis.
There are no monthly plans, seats, or minimum spends. You top up via USDT on the TRON network, and the balance never expires.
- $0.01 per 1,000 characters
- $0.50 free trial credit for Google sign-ups
- No hidden fees or VAT invoices
Developer First Approach
We prioritize clarity and reliability over hype. Our documentation provides ready-to-use curl examples and precise rate limits (60 requests per minute).
Accounts are created directly through the storefront, giving you immediate access to your API key, balance, and usage stats without enterprise sales cycles.
- 60 requests per minute limit
- Instant key issuance and rotation
- Support via email only, no live chat or phone number
Voice Licensing
BotVoice’s voice presets are grounded in real, licensed recordings rather than synthetic generation from scratch. Each voice model is derived from high-quality source material, ensuring natural intonation and clarity that product teams rely on for authentic voice assistant experiences.
LibriTTS-R Source
All eight voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are based on the LibriTTS-R dataset. This source provides consistent acoustic characteristics, allowing developers to integrate voices that sound cohesive across different languages and use cases without unpredictable variations.
CC BY 4.0 License
The underlying source recordings are released under the CC BY 4.0 license. This standard open license allows BotVoice to legally bundle these voices into our API product. You can integrate these voices into your applications without worrying about complex royalty structures or attribution errors in the audio output.
Public Domain Readings
Many of the source recordings originate from LibriVox public-domain audiobook readings. These are clean, well-enunciated narrations originally created by volunteers. By leveraging this public domain content, we provide stable, high-fidelity voices that have already been tested in real-world listening environments.
Data Policy
BotVoice processes input text solely to generate the requested audio file. We do not use your input data or generated audio for model training or improving our engine. The generated audio is returned in the response and is not stored on our servers after delivery.
We retain request metadata—including timestamp, character count, and status—strictly for billing purposes. This data ensures accurate usage tracking and supports the transparent pricing model. No personal information or voice characteristics are harvested from your usage patterns.
No Training Data Use
Your input text is used exclusively to produce the audio output. We do not ingest your data into our training datasets, ensuring your content remains private and distinct from our model development.
Generated audio files are returned in the API response and are not persisted in our storage systems. Once the audio is delivered, the content is effectively ephemeral.
No Audio Storage
Unlike many TTS providers, we do not archive your generated speech files. This minimizes data retention risks and ensures that your audio outputs are not available for later analysis or reuse by us without your explicit action.
The lack of long-term storage aligns with our focus on providing a straightforward, infrastructure-light API for product teams.
Metadata Retention
We keep request metadata (time, characters, status) only as long as necessary for billing verification and account management. This data supports the accurate calculation of usage-based charges.
No other metadata is retained for analytics or profiling purposes.

Contact Support
BotVoice is an independent storefront, so our editorial team handles the primary support channel for this API. We keep communication simple and direct to avoid unnecessary overhead.
All inquiries go through email. There is no phone line, no live chat widget, and no third-party ticketing portal cluttering the experience.
Email Support Only
Send your questions to [email protected]. Whether it is about billing, API keys, or voice selection, our team monitors this inbox directly.
No Live Chat
We intentionally do not offer live chat or a phone number. This allows our team to focus on resolving your specific technical or account issues without context switching.
Response Time
For urgent billing issues, please include your account email and a clear description of the problem to help us prioritize your request.
Technical Limits
BotVoice provides a reliable, standard REST API designed for straightforward integration. While powerful for generating audio files, the API does not support streaming responses, SSML markup for fine-grained control, or custom voice cloning for brand-specific voices.
No Streaming
The API returns complete audio files upon request completion. It does not support WebSocket or real-time partial audio streaming, meaning clients receive the full file only after synthesis finishes.
No SSML
The endpoint accepts plain text input without SSML tags. You cannot control pauses, emphasis, or pronunciation breaks via markup; the engine uses default prosody based on the input text.
No Custom Cloning
We do not offer custom voice cloning or uploading of your own voice recordings. The eight presets are fixed licensed voices based on LibriTTS-R recordings.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Build conversational flows that feel human to delight users and drive engagement.
23 languages
Any voice speaks any of these languages.
