Frequently asked questions
What is automatic voice over?
Automatic voice over uses our cloud text-to-speech API to convert text into audio files. You send a POST request with your script, and receive an audio file in formats like MP3 or WAV. This infrastructure handles the synthesis so your team can focus on creating accessible content for video without managing voice recording logistics.
Is automatic voice over good for accessibility?
Yes, it provides reliable synthetic speech for accessible materials. Every generated file carries an inaudible watermark marking it as synthetic. The API supports 23 languages and offers clear voices like Aria or Nova. This ensures consistent, compliant messaging for dyslexic and neurodivergent audiences without the variability of human recording sessions.
Which voice is best for dyslexic audiences?
We offer eight presets, including Aria (warm, clear narrator) and Nova (bright, upbeat). Aria’s clear narration style is suitable for accessible content. You can test any voice with your specific text to determine which clarity level works for your audience.
How many characters can I process in one request?
Each request accepts up to 4096 characters of input text. For longer scripts, split the text into parts of this size and join the resulting audio files. Spaces and punctuation count toward this limit. This ensures manageable processing times and consistent audio quality for each segment of your video content.
Does the API support multiple languages?
Yes, we support 23 languages including English, Spanish, German, French, and Japanese. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses from the script, defaulting to English for Latin text. Explicitly setting the language ensures accurate pronunciation for non-English content.
Can I use the OpenAI SDK with this API?
Yes, the request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base URL to https://api.rk66.info/v1 and using your VoxEase API key. This allows your existing code to work with minimal configuration changes, leveraging familiar tools for your accessibility workflows.
What audio formats are available?
You can choose from MP3, WAV, OPUS, FLAC, and PCM formats. Select the format that best fits your video production pipeline. MP3 is efficient for web delivery, while WAV or FLAC offer high fidelity. The format is specified in the request body alongside your text, voice, and speed parameters.
How long does it take to generate audio?
Generation is roughly real-time, producing about 25 characters of text per second of audio. Short phrases take a few seconds. Under load, requests may wait in a queue since they are processed sequentially. This predictable speed helps you estimate processing times for large video projects accurately.
Is my input text used for training?
No, your input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. We keep request metadata like time and character count for billing purposes, ensuring your content remains private and secure for your team.
Do I need to pay for failed requests?
No, failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generation. This protects your budget when testing different voices or formats. The cost is $0.01 per 1,000 characters for successful requests, making it easy to track expenses.
What is the minimum top-up amount?
The minimum top-up amount is $5. Payments are made via USDT on the TRON network (TRC-20). Credits are added automatically within minutes of transfer. There are no monthly plans or subscriptions, so you only pay for what you use. Balance does not expire, allowing flexible usage for your team.
Can I issue a new API key immediately?
Yes, you can issue a new key at any time from your account page. When a new key is issued, the old one stops working immediately. Each account has one active key. This allows you to rotate keys securely without downtime, ensuring your accessibility tools remain protected against unauthorized access.
Are there any hidden fees?
No, there are no hidden fees. The price is $10 per 1 million characters. Failed requests are free. There are no monthly plans, seats, or minimum spends. You pay only for the characters you successfully generate. Support is by email only, with no additional charges for standard assistance.
How do I contact support?
Support is available by email only. There is no phone number, live chat, or SLA guarantee. You can reach out for assistance with your API usage or billing.
First request
curl
curl https://api.rk66.info/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Automatic Voice Over Matters for Accessibility
Automatic voice overs remove the barrier between text and comprehension for neurodivergent audiences. By converting scripts into clear audio, you ensure your video content is accessible to dyslexic viewers who may struggle with reading dense captions or subtitles.
Support for Dyslexic Readers
Consistent pacing and clear articulation help reduce cognitive load. Our TTS engine delivers steady rhythm, allowing viewers to follow complex narratives without the strain of rapid visual decoding.
- Reduces reading fatigue for dyslexic users
- Supports multimodal learning styles
- Ensures compliance with accessibility standards
Consistent Brand Voice
Every video uses the same calibrated voice presets, from Aria’s clear narration to Atlas’s neutral tone. This uniformity reinforces brand identity across all your accessible content, ensuring a professional and recognizable auditory experience.
Scalable Content Production
Generate audio for dozens of videos without hiring multiple voice actors. Our API handles bulk requests efficiently, allowing your team to produce scalable, consistent content for large audiences without logistical bottlenecks.
How Our TTS API Works for Video Teams
VoxEase streamlines the voice-over process for video teams by accepting plain text and returning ready-to-use audio files. This eliminates the need for recording studios, allowing creators to produce accessible, dyslexia-friendly content at scale with consistent quality and tone.
Simple Text-to-Audio Workflow
Send your script via a standard HTTP POST request. The API processes the text and returns the audio file directly in the response, ready for integration into your video editing timeline or playback system.
- POST request to /v1/audio/speech
- JSON body with script and voice selection
- Immediate audio file return
23 Languages for Global Reach
Support your diverse audience with voices in 23 languages, including English, Spanish, German, French, Arabic, and Japanese. Any voice can speak any supported language, ensuring linguistic accuracy without needing multiple voice actors.
Specify the language code to ensure correct pronunciation, especially for non-English texts in Latin script. The system also auto-detects language from the script if not explicitly set.
- 23 supported languages
- Cross-lingual voice capability
- Auto-detection or explicit language setting
Standard Audio Formats (MP3, WAV, FLAC)
Choose the audio format that fits your production workflow. MP3 is ideal for web delivery, offering a balance of quality and file size.
WAV provides uncompressed, high-quality audio perfect for editing and post-production. FLAC offers lossless compression for archival purposes, preserving the highest fidelity.
PCM and OPUS formats are also available for specific technical requirements.
- MP3 for web and streaming
- WAV for editing and post-production
- FLAC for lossless archival storage
- PCM and OPUS for specific needs
Voices Designed for Clarity
Clear voice selection is critical for reducing cognitive load in accessible video content. Our eight presets are designed for distinct listening experiences, ensuring your materials remain engaging for dyslexic and neurodivergent audiences without sacrificing clarity.
Clear Female Narrators (Aria, Nova, Luna, Sage)
Aria provides a warm, clear narration ideal for standard content. Nova offers a bright, upbeat tone for energetic updates. Luna delivers a soft, storytelling style, while Sage presents a calm, instructional voice perfect for educational materials.
Calm Male Voices (Felix, Milo, Atlas, Orion)
Felix brings an energetic, promo-ready voice. Milo is friendly and conversational for direct address. Atlas provides a neutral, news-style delivery, and Orion offers a deep, documentary tone for serious topics.
Linguistically Accurate Pronunciation
Each voice supports 23 languages, ensuring consistent pronunciation across your global content. The system detects language automatically, though you can explicitly set the ISO code for non-English Latin text to guarantee accuracy.
Note: We do not offer custom voice cloning or emotion tags. All audio includes an inaudible synthetic watermark.
- Supports 23 languages including English, Spanish, German, and Japanese.
- Voices are based on licensed LibriTTS-R recordings (CC BY 4.0).
Technical Integration for Developers
VoxEase simplifies integration for video teams using familiar tools. By aligning with the OpenAI speech endpoint structure, your existing SDKs work immediately with a simple base URL change.
OpenAI SDK Compatible
Use the official OpenAI SDKs by setting the base URL to https://api.rk66.info/v1. This allows your team to leverage standard libraries without rewriting integration code.
RESTful API Endpoint
Send text via a standard POST request to https://api.rk66.info/v1/audio/speech. The endpoint accepts JSON bodies and returns audio files directly in the response.
JSON Body Requests
Include parameters like model (tts-1 or tts-1-hd), voice, and input text in the JSON payload. Authentication is handled via the Bearer token in the Authorization header.
Pricing Model for Video Productions
VoxEase charges $10 per million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests receive a full refund, ensuring you only pay for successful audio generation.
Pay Per Character
The cost is strictly usage-based. At $0.01 per 1,000 characters, producing a 40,000-character script costs approximately $0.40. This linear model scales directly with your content volume without hidden tiers.
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You can top up with USDT (TRC-20) as needed. Balances do not expire, allowing you to pause production without losing funds.
Free Failed Requests
If synthesis fails due to technical issues, the character count is not deducted. This protects your budget during high-volume production runs, ensuring you pay only for delivered audio files.

Audio Quality and Format Options
Audio formats determine how your voice-over files are processed in your editing workflow and delivered to end-users. Choosing the right format ensures compatibility with your video pipeline while balancing file size and fidelity.
Our API supports multiple output types, allowing you to select the optimal balance between compression and quality for each project stage.
MP3 for Web Delivery
MP3 is the standard for web video due to its efficient compression. Files are small enough for quick streaming and compatible with all major video players without requiring large bandwidth.
This format is ideal for final published content where file size matters for load times and user experience.
WAV for Editing
WAV provides uncompressed, lossless audio, preserving the full fidelity of the generated speech. It is the preferred format for post-production, allowing editors to apply effects, adjust levels, or sync audio without generational loss.
Use WAV when you need the highest quality source material for your editing timeline.
FLAC for Archival Quality
FLAC offers lossless compression, retaining all audio data while reducing file size compared to WAV. It is suitable for long-term archival where storage efficiency matters but quality must remain pristine.
This format ensures your voice-over assets remain pristine for future re-use or remastering.
Speed and Generation Time
VoxEase processes text at approximately 25 characters per second, delivering audio in near real-time for long scripts. Short phrases may take a few seconds.
Requests are processed sequentially, meaning bulk loads may experience brief queues during high demand. This linear processing guarantees reliability.
Real-Time Generation for Long Texts
Long texts are synthesized at a pace of roughly 25 characters per second of generation. This standard speed ensures that audio output remains synchronized with typical reading times, making it ideal for accessible video content where timing matters for dyslexic audiences.
Queue Handling for Bulk Loads
Requests are processed one after another, so under heavy load a request may wait in a queue before generation begins. This sequential handling prevents system overload and ensures every character is processed accurately, maintaining consistent audio quality across your entire library.
Split Logic for Long Scripts
For texts exceeding 4096 characters, the system automatically splits the input into manageable parts. Each segment is synthesized individually, and the resulting audio files are joined.
Data Privacy and Usage
VoxEase processes your input text solely to generate the audio file. We do not use your scripts for training our models or improving the engine, ensuring your content remains private and proprietary to your team.
No Training on Input Text
Your text is used exclusively for synthesis. Unlike some services that retain data for model improvement, we do not analyze or store your script content beyond the immediate generation process.
Temporary Audio Storage
Generated audio is returned directly in the API response and is not stored on our servers after delivery. This minimizes data retention risks for your specific video productions.
Secure API Keys
Each account holds one active API key. You can issue a new key at any time, which instantly invalidates the previous one, ensuring tight control over access without complex rotation workflows.
- One active key per account
- Instant invalidation of old keys
- Bearer token authentication
Getting Started with VoxEase
To begin, sign up on /get-api-key/ using your Google account to receive $0.50 in trial credit, valid for 7 days. This allows you to test the service with approximately 50,000 characters without immediate payment setup.
Once registered, generate your single active API key from the dashboard. You can issue a new key at any time, which instantly invalidates the previous one, ensuring secure access for your team’s video production workflows.
Sign Up for Trial Credit
Create an account via Google sign-in to instantly receive $0.50 of credit. This trial is valid for 7 days and covers roughly 50,000 characters, allowing you to verify audio quality before committing to long-form video scripts.
Generate Your API Key
Navigate to the dashboard to generate your API key. Each account holds one active key; issuing a new one immediately deactivates the old one, providing a simple security model for distributed video teams.
Use this key with the Authorization: Bearer header in your requests. No complex OAuth flows or subscription management are required.
- Keys are issued instantly upon creation
- Old keys stop immediately upon new issuance
- Support via email only
First API Call Example
Send a POST request to https://api.rk66.info/v1/audio/speech with your API key. Include the text, a voice preset like 'aria', and your desired format. The API returns the audio file directly, ready for embedding in your accessible video content.
Remember that the free trial covers about 50,000 characters. For larger volumes, top up with USDT (TRC-20) directly from the dashboard.
- Endpoint: POST /v1/audio/speech
- Format: JSON body
- Auth: Bearer tts-...
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This combination supports better retention of information in video content.
23 languages
Any voice speaks any of these languages.
