Frequently asked questions
Who runs this site?
ReelVoic is an independent storefront for the ReelVoic TTS API. We operate separately from major tech brands and focus on providing a reliable text-to-speech solution for agencies and creators who need consistent audio generation at scale.
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. This ensures high-quality speech without the need for custom voice cloning.
Is my text used for training?
No. Input text is used only to produce the audio and is not used for training models. We respect your content privacy by ensuring your specific text inputs remain dedicated solely to the generation process.
Do you store generated audio?
Generated audio is returned in the response and not stored by our servers. Only request metadata, such as time, characters, and status, is kept for billing purposes to ensure accurate charge calculations for your account.
How can I contact support?
Support is available by email only. We do not offer live chat or phone support. Please reach out via the contact page if you have questions about your API key, billing, or technical issues with the endpoint.
Is there a phone number?
No, there is no phone number. All support communication is handled via email. This allows us to maintain a focused, asynchronous workflow that keeps operational costs low, resulting in predictable pricing for our agency clients.
Do you have an SLA?
We do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real time, but performance depends on current server load.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, so their SDKs work by changing the base_url. We are an independent provider offering a competitive alternative for text-to-speech generation.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons license that allows you to share and adapt the material, even commercially, as long as you give appropriate credit. Our voices are based on recordings under this license, ensuring legal clarity.
Can I use the voices commercially?
Yes, you can use the generated audio commercially. The underlying recordings are based on LibriVox public-domain readings and licensed under CC BY 4.0. You can integrate the audio into your content without additional fees.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer manual refunds for successful generations. Your balance does not expire, so you can use your credit whenever you need it.
How is data secured?
We use standard cloud security for our API endpoints. Input text is not stored long-term, and request metadata is kept for billing. We do not hold specific certifications like SOC 2 or HIPAA.
What is the editorial team?
We are a small, independent team focused on maintaining the ReelVoic API and storefront. We handle documentation and support directly. There is no large corporate hierarchy; our team ensures the product remains honest and specific to your needs.
Do you have a privacy policy?
Yes, we respect your privacy. We only keep request metadata for billing. Input text is used only for generation and not for training. Generated audio is not stored. You can review our full privacy details on our contact or about pages.
Who We Are
ReelVoic is an independent storefront for a cloud text-to-speech API, designed specifically for agencies and creators producing TikTok, Reels, and Shorts. We operate separately from major tech brands, providing a dedicated interface for developers and content teams who need reliable, human-like voice-overs at scale.
We focus on delivering consistent audio quality with predictable costs, ensuring agencies can plan their content pipelines without unexpected API variability.
Independent Storefront
We are not affiliated with OpenAI, ElevenLabs, or any other voice technology brand. Our API endpoint is distinct, allowing you to use standard OpenAI SDKs by simply changing the base URL. This independence means you get direct access to our infrastructure without middlemen, with transparent billing and no hidden enterprise contracts.
Editorial Team
Our team consists of developers and content strategists who understand the nuances of short-form video. We maintain the documentation and support channels to ensure your integration with our TTS API remains smooth. We prioritize clarity in our pricing and technical specs so you can focus on creating engaging content rather than debugging voice generation.
Mission
Our mission is to provide agencies with a scalable, cost-effective text-to-speech solution. We aim to eliminate the guesswork in audio production by offering consistent quality and straightforward character-based pricing. By keeping our technology stack simple and our support direct, we help creators produce more videos with less friction.
Voice Licensing
ReelVoic’s voice models are built on licensed recordings from the LibriTTS-R dataset. This source provides high-quality audio samples that form the foundation of our synthetic voices, ensuring consistent and natural-sounding outputs for your TikTok and Reels content.
LibriTTS-R Source
We utilize the LibriTTS-R dataset, which contains clean speech data designed for training high-quality text-to-speech models. This ensures our voices maintain clarity and natural rhythm across the supported languages.
CC BY 4.0 License
The underlying audio data is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This allows us to legally process and synthesize these recordings into our voice presets.
Public Domain Content
Many recordings originate from LibriVox, featuring public-domain audiobook readings. This means the source material is free from restrictive copyright claims, allowing for flexible commercial use in your generated voice-overs.
Data Privacy
We use your input text solely to generate the audio file. Your source text is not used for training our models or improving the TTS engine. Once the audio is created, it is returned in the response and not stored on our servers. This ensures your scripts remain private and your intellectual property stays yours.
Billing metadata, including the timestamp, character count, and request status, is retained exclusively for accurate charge calculation and account management. This data helps us verify usage against your balance and ensures you are charged correctly for every synthesis request.
Input Text Usage
Your input text is processed only to produce the requested audio file. It is never used to train the underlying models or improve the service. This means your scripts, ideas, and content remain yours and are not ingested into our training datasets.
Audio Storage Policy
The generated audio is returned directly in the API response. We do not store the audio files on our servers after delivery. You are responsible for saving and managing your generated audio files locally or in your own cloud storage.
Billing Metadata
We retain request metadata, including the timestamp, character count, and status, solely for billing purposes. This data allows us to accurately calculate charges and provide you with transparent usage records. It is not used for marketing or profiling.
Honest Limits
ReelVoic is an independent storefront, not a corporate giant. We keep our infrastructure lean to offer predictable costs for agencies scaling content. This means we skip the enterprise overhead while delivering consistent, human-like voice-overs.
No SLA
We do not offer a Service Level Agreement guaranteeing specific uptime percentages. Our infrastructure is optimized for cost-efficiency rather than redundant enterprise-grade redundancy.
No Uptime Guarantee
No Enterprise Contract
We operate on a transparent, pay-as-you-go model. There are no custom enterprise contracts, minimum spend requirements, or dedicated account managers. Support is handled via email for all users.

Contact and Support
We keep it simple. Support is handled entirely via email, ensuring your queries are logged and addressed without the noise of live chat queues or hold music. You can reach our team via email.
Email Support Only
Send your questions to [email protected]. Whether it’s a billing discrepancy or an API integration question, our team reviews every message directly.
No Live Chat
We don’t offer live chat widgets or phone lines. This choice allows us to maintain deep focus on API reliability and account management rather than juggling multiple simultaneous conversations. It also ensures that every support ticket has a permanent record for easy reference.
Response Time
We aim to respond to emails within 24 hours. During high-volume periods, response times may vary slightly, but we prioritize clearing the queue efficiently. For urgent API key issues, please mention ‘Urgent’ in your subject line.
- Standard response: within 24 hours
- Urgent key issues: prioritized
- No phone number available
Technology Stack
ReelVoic is built on standard, well-understood technology to ensure reliable, predictable performance for agencies scaling voice-over production. We don't reinvent the wheel; we optimize the existing tools that already power millions of applications worldwide.
Our architecture prioritizes simplicity and compatibility, allowing your team to integrate quickly without learning a proprietary protocol or managing complex infrastructure. This approach keeps costs low and development cycles short.
OpenAI SDK Compatible
The API mimics the OpenAI speech endpoint structure exactly. You can use the official OpenAI SDKs by simply changing the base_url to https://api.playhs55.com/v1 and swapping in your ReelVoic key. This means no custom client libraries or steep learning curves for your developers.
This compatibility extends to standard request shapes, allowing you to leverage existing codebases. Your team can switch between providers or test different models with minimal code changes, reducing integration friction significantly.
- - Drop-in compatibility with official OpenAI SDKs
- - Standard JSON request/response format
- - No custom client libraries required
Standard Endpoints
We provide straightforward RESTful endpoints that are easy to debug and monitor. The core POST /v1/audio/speech endpoint handles synthesis, while GET /v1/voices and GET /v1/models allow you to programmatically list available options. These endpoints return clean JSON responses, making automation simple.
Each endpoint is designed for clarity and consistency. You send a POST request with parameters like model, input, voice, and response_format, and receive an audio file directly in the response body. This simplicity reduces the chance of integration errors during high-volume generation.
- - POST /v1/audio/speech for synthesis
- - GET /v1/voices for voice listing
- - GET /v1/models for model details
Simple Integration
Integration is straightforward because we use standard HTTP requests and JSON payloads. You can generate audio with a single curl command or a few lines of Python code. This simplicity allows agencies to prototype quickly and deploy to production without extensive engineering overhead.
The lack of complex features like streaming or SSML keeps the integration lightweight. You send text, receive audio, and move on. This linear workflow is perfect for automated pipelines where consistency and predictability matter more than interactive features.
- - Works with any HTTP client
- - Supports standard formats: mp3, wav, opus, flac, pcm
- - No custom dependencies needed
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. We create vertical video content optimized for short-form platforms like TikTok, Reels, and Shorts.
23 languages
Any voice speaks any of these languages.
