Frequently asked questions
How does the text-to-speech API work for Minecraft voices?
Send a POST request to https://api.vip0.info/v1/audio/speech with your text and voice selection. The API returns an audio file directly. You can use standard HTTP libraries or the OpenAI SDK by adjusting the base URL. This allows seamless integration into your game’s audio pipeline for dynamic NPC dialogue generation without complex setup.
Which voices are best for NPC dialogue?
Choose from eight presets based on licensed recordings. For NPCs, consider sage (calm, instructional), atlas (neutral, news), or milo (friendly, conversational). Each voice is distinct and optimized for clear speech. You can select any voice for any language, ensuring consistent tone across your game’s diverse cast of characters and environments.
What is the character limit per request?
Each API request supports up to 4096 characters of input text. This limit applies to the entire text payload sent in a single call. For longer dialogues, you must split the text into chunks of this size. The API processes these requests sequentially, so plan your batching strategy accordingly for optimal performance.
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.vip0.info/v1 and using your LingoCast API key. This ensures compatibility with existing codebases and simplifies integration for developers already familiar with the OpenAI SDK structure and authentication methods.
How are failed requests handled?
Failed requests are free. If synthesis fails, the charge is returned in full to your account balance. This ensures you only pay for successful audio generation. You do not need to manually request refunds; the system automatically credits your account when a request does not complete successfully due to server or input errors.
What audio formats are supported?
The API supports mp3, wav, opus, flac, and pcm response formats. Select the format that best fits your game engine’s requirements. MP3 and Opus are compressed formats, while WAV and FLAC offer lossless quality. PCM provides raw audio data. All formats include an inaudible watermark marking the file as synthetic speech.
Do I need to pay monthly for the API?
No, there are no monthly plans or subscriptions. You pay only for what you use at $0.01 per 1,000 characters. There is no minimum spend or seats required. Your balance does not expire, and you can top up as needed. This pay-as-you-go model fits variable game development cycles perfectly.
Are the voices licensed for commercial use?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This provides a solid foundation for commercial use in your games. Each generated file carries an inaudible watermark identifying it as synthetic speech, which is standard for TTS outputs and does not restrict commercial deployment.
How long does voice generation take?
Generation speed is roughly real-time, averaging 25 characters of text per second of audio. Short phrases may take a few seconds to process. Requests are handled sequentially, so under heavy load, a request might wait in a queue. Plan your audio pre-loading strategies accordingly to ensure smooth gameplay experiences for your users.
Can I generate long text in one request?
No, each request is limited to 4096 characters. For longer texts, you must split the content into parts within this limit. After generating each part, you can join the resulting audio files in your pipeline. This approach ensures consistent quality and allows you to manage memory usage effectively during bulk generation tasks.
Is there a free trial available?
Yes, signing in with Google provides a $0.50 trial credit, valid for 7 days, allowing about 50,000 characters of generation. Accounts created with email and password start without trial credit. This allows you to test the API’s quality and integration speed before committing to a top-up.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are automatically added to your account within minutes after the transfer is confirmed on the blockchain. There are no invoices, VAT, or manual processing steps. This method ensures fast, low-cost funding for your API usage needs.
What happens if my request fails?
If a request fails, the charge is returned in full to your account balance. You are not billed for unsuccessful synthesis attempts. This ensures you only pay for usable audio files. The system handles refunds automatically, so you do not need to contact support for credit restoration in case of technical failures.
Which languages are supported?
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script, defaulting to English for Latin text.
First request
curl
curl https://api.vip0.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.mp3API for Game Dialogue
LingoCast provides a standardized TTS API endpoint (POST /v1/audio/speech) designed for seamless integration into game audio pipelines. Send text and receive an audio file in a single request, supporting up to 4,096 characters per call. This structure mirrors the OpenAI speech endpoint, allowing you to drop it into existing workflows with minimal friction.
Standardized Endpoint
Use POST https://api.vip0.info/v1/audio/speech to submit JSON payloads containing your text, voice selection, and format preferences. The endpoint accepts standard parameters like model, voice, input, response_format, and speed. This consistency ensures reliable programmatic control over NPC dialogue generation without proprietary quirks.
- JSON request body with standard fields
- Supports
tts-1andtts-1-hdmodels - Max 4,096 characters per request
SDK Compatibility
Since the request shape matches the OpenAI speech endpoint, you can use official OpenAI SDKs by simply changing the base_url to https://api.vip0.info/v1. Pass your LingoCast API key (tts-...) via the Authorization: Bearer header. This allows developers to reuse existing codebases without rewriting HTTP clients.
Instant Generation
Text is processed sequentially, with typical generation speed reaching roughly real-time (25 characters per second). Short phrases generate in a few seconds, while longer texts may queue under load. Failed requests incur no charge, ensuring you only pay for successful audio synthesis.
Voice Library for NPCs
LingoCast provides eight distinct voice presets engineered for consistent NPC dialogue generation. Each voice offers a unique tonal profile, from the warm clarity of Aria to the deep documentary tone of Orion, ensuring your game characters sound distinct without requiring manual tuning.
All voices are derived from licensed recordings and public-domain audiobook readings, providing a reliable foundation for in-game audio pipelines. This approach balances legal safety with high-quality synthetic output suitable for immediate integration into your project.
Every generated audio file contains an inaudible watermark, clearly marking the content as synthetic speech. This allows for easy identification of AI-generated assets within your audio library or during post-production reviews.
8 Distinct Presets
Select from four female and four male voices, each optimized for specific narrative roles. Options range from the bright, upbeat Nova for energetic promos to the calm, instructional Sage for tutorial dialogue.
The library includes Felix (energetic), Milo (friendly), Luna (soft storytelling), and Atlas (neutral news), giving you a full spectrum of emotional tones for diverse character archetypes without needing multiple audio files.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Licensed Source Audio
The voice models are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This ensures a legally sound foundation for your commercial or personal game projects.
By leveraging these established sources, we provide consistent voice quality across all generations. The underlying audio characteristics are preserved in the synthetic output, maintaining natural prosody and rhythm.
Inaudible Watermarking
Each audio file generated via the API includes an inaudible watermark. This digital signature identifies the file as synthetic speech without affecting the listening experience for your players.
This feature helps maintain transparency in your audio assets, allowing you to distinguish between recorded voice acting and API-generated dialogue during content audits or distribution.
Language Support
LingoCast supports 23 languages, enabling global NPC dialogue without needing separate voice assets for each region. This covers major markets including English, Spanish, French, German, Japanese, and Chinese, ensuring your game reaches a wider audience with consistent audio quality.
The API automatically detects the language from the input script, defaulting to English for Latin characters. This reduces boilerplate in your dialogue manager, but explicit codes are available when needed for clarity or edge cases.
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. Any voice preset can speak any of these languages, allowing you to mix voices and languages freely within a single scene.
- Full support for 23 distinct languages
- Any voice can speak any supported language
- No language-specific voice models required
Automatic Detection
If you do not specify a language, the API guesses it from the script. Latin-script text defaults to English. This works well for standard English dialogue but may misidentify other Latin-based languages.
Explicit Language Code
For non-English Latin text or to ensure accuracy, set the language parameter with the ISO code. This prevents incorrect pronunciation or accent issues in your NPC dialogue.
- Set
languageparameter for precision - Recommended for non-English Latin text
- Ensures correct accent and pronunciation
Audio Formats
Select the output format that fits your pipeline. MP3 delivers compressed audio for immediate distribution, while WAV preserves uncompressed quality for development. PCM provides raw data for direct processing.
MP3 for Distribution
Use MP3 for final NPC dialogue lines ready for integration. It offers a small file size suitable for network transmission.
WAV for Development
WAV is ideal for debugging audio quality. It preserves the full fidelity of the generated speech without compression artifacts.
PCM for Raw Data
PCM returns uncompressed raw audio data. This format is useful for low-level audio engines that handle their own encoding.
Performance
Text-to-speech synthesis typically operates at roughly real-time speed, processing approximately 25 characters of input per second of generated audio. Short phrases require a few seconds to complete, while longer dialogues scale linearly with text length.
Real-time Speed
Generation latency is primarily driven by the length of the input string. For standard NPC dialogue lines, expect near-instant feedback. Longer narrative passages may take slightly longer but remain efficient for background audio pipelines.
- Approx. 25 chars per second of audio
- Short phrases complete in a few seconds
- Linear scaling for longer texts
Queue Management
Requests are processed sequentially. Under high load, your synthesis job may wait in a queue before beginning generation. This ensures stability but may introduce slight delays during peak usage periods.
- Sequential processing model
- Queueing under high load
- No guaranteed instant response during spikes
Character Limits
Each API request accepts a maximum of 4,096 characters. For dialogue exceeding this limit, split your text into smaller chunks and join the resulting audio files in your game engine.
- Max 4,096 characters per request
- Split longer texts manually or via client
- Join output files for continuous audio

Pricing Model
Our pricing is strictly pay-per-character at $0.01 per 1,000 characters, including spaces and punctuation. You only pay for what you generate, making it easy to predict costs for NPC dialogue pipelines.
Pay Per Character
Billed at $0.01 per 1,000 characters. Failed requests are free, with charges returned in full if synthesis fails. A free trial provides $0.50 credit (approx. 50,000 characters) for 7 days upon Google sign-in.
- Rate: $0.01 per 1,000 characters
- Minimum top-up: $5 via USDT (TRC-20)
- Balance does not expire
No Monthly Fees
We offer no monthly plans, seats, or minimum spend requirements. There are no subscriptions or invoices with VAT. Your balance covers usage indefinitely without recurring charges.
Free Failed Requests
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful API calls, ensuring you only pay for successful audio generation.
Technical Specs
The API accepts standard JSON payloads with configurable parameters for model, input text, voice selection, and audio format. Text input is limited to 4096 characters per request.
Authentication relies on a single Bearer token issued per account, supporting immediate key rotation to invalidate previous credentials instantly.
JSON Request Body
Send a POST request to the speech endpoint with a JSON body containing the model ('tts-1' or 'tts-1-hd'), input text, voice preset, response format, and optional speed or language codes.
The request structure mirrors the OpenAI speech endpoint, allowing direct use of official OpenAI SDKs by adjusting the base URL to https://api.vip0.info/v1.
- model: tts-1 or tts-1-hd
- input: text string (max 4096 chars)
- voice: one of 8 presets
- response_format: mp3, wav, opus, flac, pcm
- speed: 0.25–4.0
- language: optional ISO code
Bearer Token Auth
Include the header Authorization: Bearer tts-... with your unique API key. Each account maintains one active key at a time.
Issuing a new key immediately stops the old one, ensuring secure access management without waiting for session timeouts.
60 RPM Limit
Requests are capped at 60 per minute per API key. New accounts start with a 10 RPM limit until the first top-up.
Requests process sequentially; under load, synthesis may queue, but failed requests incur no charge and do not consume the limit beyond the attempt.
Use Cases
We provide a standard-compliant TTS API optimized for NPC dialogue generation and in-game audio pipelines. Send text, receive an audio file, and integrate voice lines directly into your game engine without manual recording sessions.
Generate diverse character voices programmatically. Our API handles the audio synthesis, allowing you to focus on gameplay logic while ensuring consistent, high-quality audio output for every interaction.
NPC Dialogue
Programmatic NPC audio generation requires reliable, low-latency responses. Our API accepts JSON bodies with voice presets like Aria or Felix, enabling dynamic dialogue trees where characters speak immediately upon player interaction.
Support up to 23 languages with automatic detection. Set the language field explicitly for non-English scripts to ensure accurate pronunciation, or let the API guess based on the Latin script for English defaults.
- Dynamic dialogue trees with instant audio response
- 8 distinct voice presets for character differentiation
- Automatic language detection or explicit ISO code support
Audiobook Clips
Generate short audiobook segments efficiently. Split long texts into 4096-character chunks and join the resulting audio files. This method supports distributed reading experiences without needing a full voice actor for every chapter.
Use the tts-1 or tts-1-hd models for consistent quality. Each generated file carries an inaudible watermark, marking it as synthetic speech while maintaining a natural listening experience.
- Split long texts into 4096-character chunks
- Inaudible watermarking for synthetic speech identification
- Consistent quality with
tts-1ortts-1-hdmodels
Content Creation
Content creators can generate voiceovers on demand. Use the API to produce audio for videos, podcasts, or social media clips. The speed parameter allows fine-tuning the delivery pace from 0.25 to 4.0.
Supports multiple audio formats including MP3, WAV, FLAC, OPUS, and PCM. Choose the format that best fits your workflow, whether for distribution or further editing in a DAW.
- On-demand voiceovers for videos and podcasts
- Adjustable speed from 0.25 to 4.0
- Multiple output formats: MP3, WAV, FLAC
Integration
Connect your game engine or audio pipeline to LingoCast using standard HTTP requests. The API endpoint mirrors the OpenAI speech interface, allowing you to swap the base URL and inject your API key without rewriting your client logic.
Initialize the connection with your Bearer token and send JSON payloads containing text, voice selection, and audio format preferences. The system returns synthesized audio files ready for immediate integration into your game assets or content workflows.
OpenAI SDK Support
Use the official OpenAI SDK by updating the base_url to https://api.vip0.info/v1. This allows you to leverage existing client libraries for seamless integration with your preferred programming language and environment.
cURL Ready
Test the endpoint directly from the command line. Use the provided cURL examples on the /get-api-key/ page to verify authentication and audio generation before implementing the logic in your application code.
Simple Setup
Sign up for an account and retrieve your API key. Send a POST request with your text and voice parameters. Receive the audio file in your chosen format (MP3, WAV, OPUS, FLAC, or PCM) immediately.
- Supports JSON request bodies for easy parsing
- Standardized fields: model, input, voice, response_format
- No custom SDKs or proprietary drivers required
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Avoid these three frequent errors to ensure consistent voice generation and accurate billing.
23 languages
Any voice speaks any of these languages.
