Frequently asked questions
What is a realistic AI voice over?
Our API generates audio from licensed recordings of LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. The result is synthetic speech that sounds natural and consistent. Each file includes an inaudible watermark identifying it as synthetic, ensuring transparency for compliance audits without compromising the listening experience for end-users.
Is synthetic speech suitable for dyslexic audiences?
Yes. Our API supports dyslexia-friendly audio formats and allows precise control over speech speed (0.25–4.0). This enables product teams to optimize playback rates for better comprehension. The consistent, licensable voices reduce cognitive load compared to variable human recordings, supporting accessibility standards effectively for diverse user needs.
Which format is best for accessibility videos?
We support MP3, WAV, Opus, FLAC, and PCM. WAV or FLAC are recommended for lossless clarity. MP3 offers efficient compression suitable for web delivery. You can select the optimal format via the response_format parameter to match your specific video player requirements.
How many languages are supported?
We support 23 languages, including English, Spanish, German, French, Chinese, Japanese, Arabic, and Hindi. Any voice can speak any supported language. If the language field is omitted, the system guesses the language, defaulting to English for Latin script. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and all others not in the list.
Can I use the voices for commercial videos?
Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. This provides a clear licensing path for commercial use. Generated audio is returned in the response and not stored, allowing you to integrate the files directly into your commercial video production workflows.
Do you offer custom voice cloning?
No. We do not offer custom voice cloning, voice design, or uploading of your own voice. You choose from eight preset voices (e.g., Aria, Nova, Atlas). This ensures consistent, licensable synthetic voices optimized for accessibility standards without the variability of custom cloning processes.
How is the audio quality ensured?
Quality is derived from licensed LibriTTS-R and LibriVox source recordings. We offer two models: tts-1 and tts-1-hd, both using the same engine. You can select formats like WAV or FLAC for high fidelity. The API returns clean audio files directly, ensuring consistent output for your video projects.
What is the character limit per request?
Each API request accepts up to 4,096 characters of input text. For longer scripts, split your text into parts of this size and join the resulting audio files. Spaces and punctuation count toward the character limit, so plan your text segmentation accordingly for efficient batch processing.
How does speed affect comprehension?
You can adjust speech speed from 0.25 to 4.0. This allows precise tuning for accessibility, such as slowing down audio for dyslexic audiences. Standard speed generates roughly 25 characters per second (real-time on long texts). Adjusting speed helps balance production efficiency with listener comprehension requirements for your specific target audience.
Are the voices watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This feature aids in compliance tracking and content identification. The watermark does not affect audio quality or listener experience, providing a reliable method to verify synthetic origin for regulatory purposes.
Do you store my 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. We retain request metadata (time, characters, status) strictly for billing purposes, ensuring your content remains private and under your control.
Can I change my voice key instantly?
Yes. You can issue a new API key at any time. The old key stops working immediately upon issuance of the new one. This allows for instant rotation of credentials without downtime. You manage keys via the /get-api-key/ page, supporting secure access for your product teams.
Is there a minimum spend requirement?
No. There are no monthly plans, no seats, and no minimum spend. You pay $0.01 per 1,000 characters (including spaces and punctuation). Failed requests are free. You can top up with a minimum of $5 via USDT (TRC-20). This model suits variable usage patterns common in video production workflows.
How fast is the generation process?
Generation is roughly real-time for long texts (25 characters per second). Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. The rate limit is 60 requests per minute per key after top-up.
First request
curl
curl https://api.368g.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.mp3Enterprise Text-to-Speech for Video Production
VoiceCompliance delivers consistent synthetic narration for high-volume video voice-overs, ensuring uniform tone across all content. Our API generates clear audio from text inputs, optimized for accessibility standards and dyslexia-friendly playback, allowing product teams to maintain brand voice without human variability.
Consistent Synthetic Narration
Generate uniform audio for e-learning and compliance videos using eight licensed voice presets. Each voice maintains a steady cadence, reducing listener fatigue in long-form educational content.
Dyslexia-Friendly Audio Formats
Output audio in MP3, WAV, OPUS, FLAC, or PCM formats. These high-fidelity options support clear speech processing, aiding users with reading difficulties who rely on audio summaries.
Scalable Cloud API
Process requests via a standard cloud endpoint. Handle up to 4,096 characters per request, splitting longer texts automatically. The API scales with your production volume without requiring infrastructure management.
Voice Library for Professional Narration
The VoiceCompliance API provides eight distinct voice presets designed for consistent synthetic narration across high-volume video productions. Each voice is optimized for clarity and professional tone, ensuring that accessibility standards are met without compromising on audio quality.
Female Presets: Aria, Nova, Luna, Sage
Aria offers a warm, clear narrator style suitable for general content. Nova provides a bright, upbeat tone ideal for energetic segments. Luna delivers a soft, storytelling voice for narrative-driven videos. Sage presents a calm, instructional tone perfect for educational material.
Male Presets: Felix, Milo, Atlas, Orion
Felix is energetic and suited for promotional content. Milo offers a friendly, conversational style for direct address. Atlas provides a neutral, news-like delivery for factual reporting. Orion delivers a deep, documentary-style voice for authoritative content.
Licensed Base Recordings
All voices are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This ensures clear usage rights for commercial applications. Every generated audio file includes an inaudible watermark to identify synthetic speech.
Global Language Support
VoiceCompliance delivers synthetic narration in 23 languages, covering major global markets including Arabic, Chinese, English, French, German, Hindi, Japanese, Korean, and Spanish. This range supports diverse audience bases without requiring separate voice talent contracts for each region.
23 Supported Languages
Our API supports 23 languages, ensuring broad coverage for international video content. Supported languages include Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
- Arabic, Chinese, Danish, Dutch, English
- Finnish, French, German, Greek, Hebrew
- Hindi, Italian, Japanese, Korean, Malay
- Norwegian, Polish, Portuguese, Russian, Spanish
- Swahili, Swedish, Turkish
Automatic Language Detection
The API automatically detects the language based on the input script. For text in Latin script, English is the default if no language is specified. This reduces configuration overhead for English-dominant content.
Manual Language Override
For non-English Latin-script text, you must explicitly set the language parameter to ensure correct pronunciation and intonation. This prevents the system from defaulting to English, ensuring accurate delivery for languages like Dutch or German.
Technical Specifications
The API endpoint at https://api.368g.info/v1 follows the standard OpenAI speech schema, allowing teams to integrate using existing OpenAI SDKs by adjusting the base URL. This compatibility simplifies implementation for engineering teams already familiar with standard TTS patterns, requiring only an API key change and the correct endpoint configuration.
OpenAI SDK Compatibility
Requests use the same JSON structure as the official OpenAI speech endpoint, ensuring seamless integration with common client libraries. Authentication is handled via a Bearer token, and the base URL is set to https://api.368g.info/v1.
Multiple Output Formats
Audio is returned in mp3, wav, opus, flac, or pcm formats via the response_format parameter. For accessibility, uncompressed wav or flac provides high-fidelity output, while opus offers efficient bandwidth usage.
Speed Control 0.25x–4.0x
The speed parameter allows precise control over playback rate, ranging from 0.25 to 4.0. Slower speeds (0.5x–0.75x) enhance comprehension for users with cognitive disabilities, while faster rates support rapid prototyping and review cycles.
Data Privacy and Licensing
VoiceCompliance processes input text exclusively to generate the requested audio file. Once synthesis is complete, the source text is not retained for model training or future development. Request metadata, including timestamps, character counts, and status, is stored solely for billing accuracy and dispute resolution.
No Training on Input Data
Unlike many consumer-grade services, we do not use your specific voice-over scripts to improve our underlying engine. The text you submit is used strictly for the immediate production of the audio file and is discarded from any training dataset.
Synthetic Watermarking
Every generated audio file contains an inaudible watermark that explicitly marks the content as synthetic speech. This technical marker allows downstream platforms and content moderators to identify AI-generated narration without affecting the audio quality or listener experience.
Clear Usage Rights
Your generated audio files are free from additional licensing restrictions. The underlying voice models are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain LibriVox readings, providing a clean baseline for commercial and accessibility use without complex attribution requirements for the final audio asset.
- Audio files are returned in the response and not stored on our servers.
- Input text is not used for training or improving the TTS engine.

Pricing Structure
VoiceCompliance charges $0.01 per 1,000 characters, including spaces and punctuation. Failed requests incur no charge, ensuring you pay only for successful synthesis.
Pay-Per-Character Model
The rate is $10 per million characters. This flat rate applies to both tts-1 and tts-1-hd models, which use the same underlying engine.
No Monthly Minimums
There are no monthly plans, seats, or minimum spend requirements. You can top up as needed without commitment.
- No subscriptions or recurring fees.
- Balance does not expire.
Transparent Billing
Requests are processed sequentially, and usage data is retained for accurate billing. New API keys invalidate old ones immediately (the old key stops at once).
- Top-ups via USDT (TRC-20) only.
- Minimum top-up is $5.
Integration Workflow
Access your API key via the /get-api-key/ dashboard to begin integration immediately. The key enables standard JSON requests to the speech endpoint, ensuring consistent delivery for high-volume video narration.
Use the provided curl example or OpenAI SDK with a custom base URL. Requests are processed sequentially, so under load, queuing may occur. Failed requests incur no charge, simplifying billing logic for product teams.
Quick API Key Setup
Sign up via Google or email on the /get-api-key/ page. Your unique key appears instantly alongside your balance and character count.
Rotate keys anytime; the old key stops immediately. This ensures secure, auditable access for your development and production environments.
- Google or email authentication
- Instant key generation
- Immediate invalidation of old keys
Standard JSON Requests
Send a POST request to /v1/audio/speech with your text, voice selection, and format preferences. The endpoint accepts standard parameters compatible with OpenAI SDKs.
Supports text up to 4096 characters. For longer scripts, split the input and concatenate the resulting audio files.
- POST /v1/audio/speech
- JSON body format
- OpenAI SDK compatible
Simple Error Handling
Failed synthesis requests are returned with a 4xx or 5xx status code and zero charge. This ensures your billing remains accurate even during transient issues.
Check the response body for specific error details. Retry logic should account for the 60 requests-per-minute rate limit per key.
- Zero charge on failure
- Standard HTTP status codes
- 60 req/min limit
Use Cases for Product Teams
Product teams in the accessibility sector require reliable synthetic narration to ensure e-learning content remains consistent and compliant with audio standards. Our API provides a scalable solution for generating high-quality voice-overs without the variability of human performers.
The system supports 23 languages and includes dyslexia-friendly audio formats, enabling teams to deliver clear, accessible content to diverse audiences. This ensures that educational materials meet regulatory requirements while maintaining high production value.
Rapid prototyping is essential for agile teams. With our API, teams can quickly generate audio variants for testing and iterate on content without waiting for studio availability. This speed allows for faster updates and more efficient workflows.
E-Learning Video Narration
Our API enables product teams to generate consistent synthetic narration for e-learning videos, ensuring that educational content remains accessible and compliant with audio standards. The system supports 23 languages and includes dyslexia-friendly audio formats, which helps in delivering clear and understandable content to diverse audiences. This consistency is crucial for maintaining high production value across large volumes of educational material.
By leveraging our text-to-speech API, teams can easily update their e-learning content without the need for re-recording with human voice actors. This not only reduces production costs but also ensures that the audio quality remains uniform across all modules, enhancing the overall learning experience for students.
- Supports 23 languages for global reach
- Dyslexia-friendly audio formats available
- Consistent voice quality across modules
Accessibility Compliance
Accessibility compliance is a critical requirement for many educational institutions and corporate training programs. Our API provides a reliable solution for generating synthetic voice-overs that meet these standards. The system's ability to handle multiple languages and formats ensures that content is accessible to a wide range of users, including those with visual or cognitive impairments.
The synthetic watermarks embedded in generated audio files help in identifying the content as AI-generated, which can be important for transparency and compliance purposes. This feature, combined with our clear usage rights, ensures that teams can confidently use the generated audio in their accessible content without worrying about licensing issues.
- Meets accessibility standards for diverse audiences
- Synthetic watermarks for transparency
- Clear usage rights for compliance
Rapid Prototyping
Rapid prototyping is essential for agile product teams that need to quickly test and iterate on their content. Our API allows teams to generate audio variants in seconds, enabling them to test different voices, languages, and formats without the delay of traditional recording processes. This speed is crucial for staying ahead in fast-paced development cycles.
The simplicity of our JSON-based API makes it easy to integrate into existing workflows. Teams can use the official OpenAI SDKs by changing the base URL, ensuring a seamless transition from planning to production. This ease of use reduces the time from concept to deployment, allowing teams to focus on delivering high-quality content.
- Generate audio variants (short phrases take a few seconds; long texts generate at roughly real-time speed).
- Easy integration with existing workflows
- Supports multiple languages and formats
Why Choose Synthetic Voice-Over
Synthetic voice-over ensures consistent audio quality across all your video content, eliminating the variability of human recording sessions. This reliability supports accessibility standards and maintains a uniform brand voice for product teams managing high-volume narrations.
Our API delivers licensable synthetic voices optimized for clarity, making content accessible to diverse audiences, including those with dyslexia or visual impairments. The consistent tone enhances user comprehension and engagement without the need for re-recording.
Consistent Brand Voice
Using a single synthetic voice for all narrations guarantees a uniform tone across your entire library. This consistency strengthens brand identity and ensures that accessibility features remain cohesive regardless of content volume or update frequency.
- Uniform tone across all video content
- Enhanced accessibility for diverse audiences
- Single voice for consistent branding
Reduced Production Costs
Our pay-per-character model at $0.01 per 1,000 characters eliminates monthly minimums and subscription fees. You only pay for the audio you generate, making it cost-effective for both small projects and high-volume enterprise needs.
- Pay only for characters generated
- No monthly minimums or subscriptions
- Cost-effective for high-volume use
Instant Content Updates
Update your video narration instantly by sending a new text request through the API. This eliminates the logistical delays of scheduling voice actors, studio time, and post-production editing, allowing for rapid content iteration and deployment.
- Instant narration updates via API
- No scheduling or studio delays
- Rapid content iteration and deployment
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. His natural pacing aids comprehension, particularly for accessibility-focused materials where clear, approachable speech is prioritized over formal narration.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- ISO 639 language codes
- LibriTTS-R corpus (OpenSLR 141)
- Python documentation
- IETF RFC 7845: Ogg Opus
- LibriVox public-domain audiobooks
- OpenAI API reference: create speech
- LibriTTS-R paper (arXiv 2305.18802)
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- openai-python on GitHub
- curl documentation
