Frequently asked questions
Can the API generate Spanish audio from English text?
Yes. Any of the eight preset voices can speak any of the 23 supported languages, including Spanish. You may specify the language code in the request; if not set, the language is guessed from the script (Latin text defaults to English).
Which voices support both English and Spanish?
All eight voices support both languages. The available presets are aria, nova, luna, and sage (female); and felix, milo, atlas, and orion (male). Each voice maintains its specific tonal characteristics across all supported languages.
How much does it cost to generate 1,000 characters?
The cost is $0.01. Pricing is $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward the character total. Failed requests are free, with the charge returned in full.
Is there a free trial available for new users?
Yes, if you sign in with Google. New accounts receive $0.50 of credit, valid for 7 days, allowing approximately 50,000 characters. Accounts created with email and password start without trial credit and require a top-up.
What audio formats are supported?
The API supports mp3, wav, opus, flac, and pcm. You specify the desired format in the response_format field of the JSON request body. The audio is returned directly in the response payload.
How long can the input text be per request?
Each request supports up to 4,096 characters. For longer texts, you must split the content into parts of this size, generate audio for each part, and join the resulting audio files manually.
Does the API support SSML tags?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You can only adjust the speed parameter between 0.25 and 4.0. Complex prosody control is not available.
Are the voices customizable or cloned?
No. The API provides eight fixed presets based on licensed recordings. There is no custom voice cloning, no uploading of your own voice, and no voice design options available for customers.
How is the API billed?
Billing is character-based at $10 per 1 million characters. Payments are made via USDT on the TRON network (TRC-20). There are no monthly plans, subscriptions, or invoices. Balance does not expire.
Can I use the OpenAI SDK with this API?
Yes. The request shape matches the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base_url to https://api.godbet.info/v1 and using your site-specific API key for authentication.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or adjust parameters such as speed or text length.
Is there a rate limit on requests?
Yes. The limit is 60 requests per minute per key (10 per minute before the first top-up). Requests are processed sequentially.
Do the generated audio files contain watermarks?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded automatically during the synthesis process and cannot be removed.
How do I top up my account balance?
Send USDT on the TRON network (TRC-20) with a minimum of $5. Credits are added automatically within minutes after the transfer. There are no other payment methods like cards or PayPal.
First request
curl
curl https://api.godbet.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.mp3Multilingual Synthesis Capabilities
LingoTale delivers precise multilingual text-to-speech synthesis, enabling content creators to generate high-quality audio for language learning platforms. Our API processes text through a reliable cloud infrastructure, ensuring consistent output quality across diverse linguistic contexts without requiring complex backend configurations.
The system supports 23 languages, including English, Spanish, Chinese, and Arabic. Any voice preset can speak any supported language, with automatic language detection for Latin-script text or explicit language code specification for accuracy.
High-Fidelity Audio Output
Each synthesis request returns a clean audio file in your chosen format. The infrastructure handles character limits and formatting automatically, allowing you to focus on content creation rather than audio engineering.
23 Supported Languages
We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Not supported are Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali.
- Arabic
- Chinese
- Danish
- Dutch
- English
- Spanish
Voice Selection Guide
Choose from eight licensed presets based on LibriTTS-R recordings. Female voices include Aria (narrator), Nova (upbeat), Luna (storytelling), and Sage (instructional). Male voices include Felix (promo), Milo (conversational), Atlas (news), and Orion (documentary).
Each voice is distinct, allowing you to match the tone to your specific educational or content needs. All generated audio carries an inaudible synthetic watermark.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
Developer Integration
LingoTale’s API mirrors the OpenAI speech endpoint structure, allowing developers to integrate using official OpenAI SDKs by simply adjusting the base_url to https://api.godbet.info/v1. This compatibility ensures seamless adoption for existing workflows without requiring custom client libraries or complex adaptation layers.
The core functionality is delivered via a single REST endpoint, simplifying implementation for content creators and language learning platforms. Authentication is handled through a standard Bearer token, ensuring secure access to synthesis services while maintaining straightforward error handling and response formats.
OpenAI SDK Compatibility
The API request shape matches the OpenAI speech endpoint exactly. Developers can use the official OpenAI SDKs for Python, Node.js, or other languages by configuring the client to point to our base URL. This reduces boilerplate code and leverages established community tools for retries and pagination.
Simple REST Endpoint
Send a POST request to /v1/audio/speech with a JSON body containing model, input, voice, and response_format. The service returns the audio file directly in the response stream. This minimal structure supports rapid prototyping and easy integration into web applications or backend services.
Request Limits and Rates
New accounts are limited to 10 requests per minute. After the first top-up, the limit increases to 60 requests per minute per key. This rate limit ensures fair usage during peak times while allowing scalable generation for language learning platforms with moderate traffic.
- Standard limit: 60 requests/minute per key
- Initial limit: 10 requests/minute
- Rate limits reset every 60 seconds
- Exceeding limits returns HTTP 429
Pricing and Billing
Billing is calculated strictly on character count, including spaces and punctuation. The rate is $10 per one million characters, equating to $0.01 per 1,000 characters. Failed requests incur no charge, with credits returned in full if synthesis fails.
Per-Character Pricing
Each request processes up to 4,096 characters. Longer texts must be split and joined by the client. There are no minimum spend requirements or monthly base fees.
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free
USDT Payment Only
Payments are accepted exclusively via USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are credited automatically within minutes of transfer confirmation.
- USDT (TRC-20) only
- Minimum top-up: $5
- No cards or PayPal
No Hidden Fees
Balance does not expire. There are no subscriptions, seats, or VAT invoices. A free trial of $0.50 credit is available for new Google sign-ins.
Use Cases for Language Learning
LingoTale’s API enables precise multilingual synthesis, allowing educational platforms to convert text into audio for 23 languages, including English and Spanish. Content creators can generate high-quality audio files for language learning materials, ensuring accurate pronunciation and consistent tone across diverse linguistic contexts.
Educational Content Generation
Language learning platforms utilize the API to transform written lessons into spoken audio, supporting students in developing listening skills. With support for 23 languages, educators can produce multilingual content that adapts to various learner needs without requiring multiple voice actors.
- Supports 23 languages for diverse learner bases
- Generates audio from text up to 4096 characters per request
- Ensures consistent voice quality across all lessons
Podcast Localization
Content creators can localize podcasts by converting scripts into natural-sounding audio in multiple languages. The API’s character-based billing ensures cost-effective scaling, allowing creators to expand their reach to international audiences without significant production overhead.
- Cost-effective scaling with transparent billing
- Supports various audio formats including MP3 and WAV
- Maintains consistent tone across localized episodes
Audiobook Production
The API facilitates the production of audiobooks by converting text into high-fidelity audio. With options for different voices and speeds, publishers can create engaging listening experiences that cater to various preferences and accessibility needs.
- Offers 8 distinct voice presets for varied narration styles
- Adjustable speed from 0.25 to 4.0 for customizable pacing
- Generates audio files ready for distribution on major platforms
Technical Specifications
LingoTale’s API supports five standard audio formats: mp3, wav, opus, flac, and pcm. Each format is optimized for different bandwidth and playback requirements, ensuring compatibility with most language learning platforms and content creation tools.
Audio Formats Available
MP3 offers efficient compression for web delivery, while WAV and FLAC provide lossless quality for archival or high-fidelity playback. Opus and PCM are available as response formats; the API does not support streaming or WebSocket connections.
- mp3, wav, opus, flac, pcm
Input Text Limits
Each API request accepts up to 4,096 characters, including spaces and punctuation. For longer texts, clients should split the input into chunks and join the resulting audio files sequentially to maintain continuity.
Speed Control Options
The speed parameter accepts values between 0.25 and 4.0, allowing precise adjustment of playback rate. This enables educators to slow down speech for learners or accelerate narration for quick content reviews.

Voice Catalog Overview
LingoTale provides eight distinct voice presets engineered for precise multilingual synthesis. Each voice is derived from licensed recordings, ensuring consistent audio quality across all 23 supported languages.
Female Voice Options
Four female voices cover diverse tonal requirements. Aria offers a warm, clear narrator style suitable for educational content. Nova provides a bright, upbeat tone ideal for dynamic presentations. Luna delivers a soft, storytelling voice for narrative applications. Sage ensures calm, instructional clarity for technical or training materials.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male Voice Options
Four male voices address specific content genres. Felix delivers energetic, promo-style delivery. Milo provides a friendly, conversational tone for engaging narratives. Atlas offers neutral, news-style clarity for factual reporting. Orion supplies a deep, documentary voice for serious, long-form content.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Narrative Styles
All voices support any of the 23 languages, allowing consistent branding across localized content. Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Generated audio includes an inaudible watermark to identify synthetic speech.
Data Privacy and Security
LingoTale ensures that input text is utilized exclusively for the purpose of generating the requested audio file. We do not use your source text to train our models or improve the synthetic voice algorithms, preserving the integrity of your proprietary content.
Input Text Usage
Your text is processed in real-time to create the audio output. It is not stored long-term or repurposed for other clients, ensuring that your educational or podcast scripts remain private and distinct from our training data.
Audio Storage Policy
The generated audio file is returned directly in the API response and is not stored on our servers after delivery. This ephemeral handling minimizes data retention, ensuring that your final audio assets reside solely on your infrastructure or client devices.
Metadata Retention
We retain request metadata, including timestamp, character count, and status, strictly for billing and usage verification purposes. This data supports transparent invoicing and helps monitor API limits without retaining the actual content you processed.
- Text used only for generation, not training.
- Audio is not stored post-delivery.
- Metadata kept for billing accuracy only.
Getting Started
Access your unique API key directly from the /get-api-key/ dashboard. The interface displays your current balance, trial status, and character usage. Generate a new key instantly if needed; the previous key becomes invalid immediately upon creation.
API Key Generation
Sign in using Google or your email credentials. The dashboard provides a ready-to-use cURL example for immediate testing. Keys are tied to your account balance and rate limits.
- Google or email authentication
- Instant key rotation
- Visible balance and usage stats
First Request Example
Send a POST request to https://api.godbet.info/v1/audio/speech. Include your API key in the Authorization header. The system returns an audio file in your chosen format, such as MP3 or WAV.
Documentation Access
Visit the /docs/ page for complete endpoint details. Review the /pricing/ page to understand character-based billing. All integration guides reference the standard OpenAI SDK compatibility for ease of use.
Support and Contact
Support is handled exclusively via email. We do not offer phone lines, live chat, or on-site assistance. All inquiries, including billing questions and technical issues, are routed to our support team for resolution.
Email Support
Send your questions to our support address. Response times vary based on volume, but we prioritize clear, documented issues. Please include your API key and relevant request IDs to help us investigate efficiently.
Documentation Links
Refer to /docs/ for complete endpoint details, including the /v1/audio/speech request shape and voice parameters. The /get-api-key/ page provides ready-to-use curl examples for immediate integration.
Status Information
Service status and any planned maintenance windows are communicated via our email support channel. There is no dedicated status page currently.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. There are no monthly plans, no minimum spend requirements, and no per-seat fees.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriTTS-R corpus (OpenSLR 141)
- OpenAI API reference: create speech
- IETF RFC 7845: Ogg Opus
- Node.js documentation
- LibriVox public-domain audiobooks
- MDN: Web Speech API
- LibriTTS-R paper (arXiv 2305.18802)
- openai-node on GitHub
- W3C WAI: making audio and video accessible
- openai-python on GitHub
- TRON developer hub: TRC-20
