Frequently asked questions
What is this API?
It is a cloud text-to-speech API where you send text and receive an audio file. The endpoint is POST https://api.playf65.com/v1/audio/speech with a JSON body. It supports models tts-1 and tts-1-hd, eight voice presets, and adjustable speed between 0.25 and 4.0.
Is it compatible with OpenAI SDKs?
Yes. The request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.playf65.com/v1 and using your Lexiconet API key for authentication.
How many languages are supported?
The API supports 23 languages, including English, Spanish, German, French, Japanese, and Arabic. Any voice can speak any of these languages. If the language parameter is omitted, the system guesses the language based on the script.
What voices are available?
There are eight presets: aria, nova, luna, and sage (female); felix, milo, atlas, and orion (male). These voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings.
How fast is the speech generation?
Generation is roughly real time, processing about 25 characters per second for long texts. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins.
Do I need to install software?
No. It is a cloud API accessed via HTTP requests. You can use the official OpenAI SDKs or plain HTTP to send text and receive audio files directly from your application without installing any local software.
Can I use it for commercial projects?
Yes. The API is designed for indie developers and product teams to turn written content into audio. Generated audio files carry an inaudible watermark marking them as synthetic speech, suitable for commercial use in your applications.
What formats does it output?
You can choose from mp3, wav, opus, flac, or pcm using the response_format field. The API returns the audio file directly in the response, allowing you to integrate it immediately into your workflow.
Is there a free trial?
Yes. Signing in with Google provides $0.50 of credit, valid for 7 days, allowing about 50,000 characters. Accounts created with email and password start without trial credit. Balance does not expire.
How do I pay?
Pricing is $10 per 1 million characters. Top-ups are made via USDT on the TRON network (TRC-20), with a minimum of $5. Credits are credited automatically within minutes. There are no monthly plans or subscriptions.
Are there rate limits?
Yes, there is a limit of 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. You can issue a new key at any time; the old one stops working instantly.
What happens if a request fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generation. Input text is used only to produce the audio and is not stored.
Is my text data stored?
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. Only request metadata (time, characters, status) is kept for billing.
Can I clone my own voice?
No. Custom voice cloning is not offered. You cannot upload your own voice or design custom voices. The API uses eight fixed presets based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings.
First request
curl
curl https://api.playf65.com/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 choose our API?
Turn written content into natural-sounding audio without building complex infrastructure. Our API is designed specifically for indie developers and product teams who need reliable speech synthesis without the overhead of managing servers or hiring specialized voice talent.
Simple integration for indie teams
We offer a straightforward HTTP API that integrates easily into your existing workflow. You can use the official OpenAI SDKs by simply changing the base URL, making migration or adoption seamless for your development team.
- Standard JSON request body
- Compatible with OpenAI SDKs
- No custom client libraries required
No complex infrastructure needed
Focus on building your product, not maintaining speech engines. We handle the processing queue and audio generation, delivering ready-to-use audio files directly to your application via simple API calls.
Transparent pricing model
Pay only for what you use. Our pricing is based on character count, with no monthly subscriptions or hidden fees. Failed requests are free, ensuring you only pay for successful synthesis.
- $0.01 per 1,000 characters
- No monthly plans
- Failed requests are free
How it works
Integration is straightforward: send a POST request to our endpoint with your text and preferences. The API processes your input and returns the generated audio file directly in the response, eliminating the need for polling or complex webhook setups.
Send text via HTTP request
Use standard JSON bodies with fields like model, input, and voice. You can send up to 4096 characters per request. For longer content, split the text into parts and join the resulting audio files afterward.
- POST to
https://api.playf65.com/v1/audio/speech - JSON body with
input,voice, andmodel - Max 4096 characters per request
Receive audio files
The API returns the audio file directly in the response. You receive the binary data immediately after synthesis completes, allowing you to save or stream the file to your users without additional storage steps.
Support for multiple formats
Choose from mp3, wav, opus, flac, or pcm formats. Select the one that best fits your app’s performance needs or user device capabilities. All formats are generated from the same high-quality engine.
Available Voices
We offer eight distinct voice presets designed to suit various content styles, from warm narration to energetic promos. Each voice is based on licensed recordings, ensuring your audio content is clear and natural.
Female voices: Aria, Nova, Luna, Sage
Aria provides a warm, clear narrator tone ideal for books. Nova brings a bright, upbeat energy perfect for modern apps. Luna offers a soft, storytelling voice for immersive content, while Sage delivers a calm, instructional tone for tutorials.
Male voices: Felix, Milo, Atlas, Orion
Felix is energetic and great for promos. Milo sounds friendly and conversational. Atlas provides a neutral, news-style delivery, and Orion offers a deep, documentary voice for serious content.
Licensing from LibriTTS and LibriVox
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file includes an inaudible watermark to mark it as synthetic speech.
Supported Languages
Our API supports 23 languages, ensuring your content reaches a global audience without language barriers. Every voice can speak any of the supported languages, allowing you to mix voices and languages freely within a single project. If you do not specify a language, the system guesses it from the script, but for non-English Latin text, we recommend setting the language field explicitly for accuracy.
The list is specific and finite. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, or any other languages outside this set. This clarity helps you plan your localization strategy without unexpected compatibility issues.
Major languages: English, Spanish, French
These widely spoken languages are fully supported across all eight voice presets. Whether you are creating tutorials in English or marketing copy in Spanish, the synthesis engine delivers consistent, natural-sounding audio.
The system defaults to English for Latin-script text if no language is specified. For other Latin-based languages like French or Spanish, explicitly passing the ISO code ensures the correct accent and pronunciation.
- English
- Spanish
- French
Asian languages: Chinese, Japanese, Korean
We support Simplified Chinese, Japanese, and Korean, allowing indie developers to localize apps for major Asian markets. Each voice renders these languages with appropriate intonation and rhythm.
You can use any of the eight voices for these languages, giving you flexibility in tone while maintaining high linguistic accuracy.
- Chinese
- Japanese
- Korean
Other: Arabic, Hindi, Russian, Turkish
Beyond the major markets, we support Arabic, Hindi, Russian, and Turkish, among other languages. This covers a significant portion of the global web audience.
All 23 supported languages include Arabic, Danish, Dutch, Finnish, Greek, Hebrew, Italian, Malay, Norwegian, Polish, Portuguese, Swahili, Swedish, and Turkish. Each voice adapts to the linguistic nuances of the selected language.
- Arabic
- Hindi
- Russian
- Turkish
Technical Specs
Lexiconet provides a straightforward integration path for indie developers who need reliable audio generation without managing complex infrastructure. Our API mirrors the structure of major cloud providers, allowing you to swap in our service with minimal code changes.
OpenAI SDK compatible
Use the official OpenAI SDKs by simply changing the base_url to https://api.playf65.com/v1. Pass your API key via the standard Authorization: Bearer header, and all existing logic remains intact.
- Drop-in replacement for OpenAI's speech endpoint
- Standard JSON request and response shapes
- Works with existing SDKs without custom wrappers
Standard JSON endpoints
Send text to POST https://api.playf65.com/v1/audio/speech with a simple JSON body. Specify your model, input text, voice, response_format, and optional speed (0.25–4.0). Retrieve available voices and models via GET /v1/voices and GET /v1/models.
- Single endpoint for audio synthesis
- Clear JSON structure with standard fields
- Easy retrieval of voice and model metadata
Generation speed
Generation is roughly real-time, processing about 25 characters of text per second. Short phrases may take a few seconds, while longer texts are split into 4096-character chunks and joined seamlessly. Requests are processed sequentially, so under heavy load, a request may wait in a queue.

Use Cases for Indie Devs
Turn written content into natural-sounding audio without building complex infrastructure. Our API lets indie teams convert text to speech quickly, supporting formats like MP3, WAV, and OPUS. You send text via a simple HTTP request and receive audio files instantly, handling up to 4096 characters per call with automatic splitting for longer documents.
Audiobook production
Generate audiobooks from raw text using voices based on licensed LibriVox recordings. Since input text is used only to produce audio and not for training, you retain full rights to the output. With voices like Luna for storytelling or Orion for documentary styles, indie creators can produce professional-grade content without hiring voice actors.
- Licensed voices from LibriTTS-R (CC BY 4.0) and LibriVox
- No training data retention for generated audio
- Support for long texts via automatic splitting and joining
E-learning content
Create engaging audio lessons for your courses using clear, instructional voices like Sage or energetic ones like Felix. Our API supports 23 languages, allowing you to localize content for global audiences. With a speed range of 0.25–4.0, you can adjust playback to match learning paces, ensuring clarity for diverse learners.
- 23 supported languages including English, Spanish, French, and Chinese
- Adjustable speed from 0.25x to 4.0x
- Simple JSON integration for existing course platforms
Accessibility features
Enhance app accessibility by converting text to speech for screen readers or auditory consumption. Use voices like Atlas for neutral news updates or Milo for conversational interfaces. The API returns audio in standard formats, making it easy to integrate into web and mobile apps without requiring custom audio pipelines.
- 8 distinct voice presets for different tones
- Standard audio formats (MP3, WAV, OPUS, FLAC, PCM)
- No custom voice cloning needed for standard accessibility needs
Pricing Overview
Lexiconet charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this total, ensuring transparent billing without hidden fees. Failed requests are free, with charges returned in full if synthesis fails.
Pay per character usage
Pricing scales directly with usage. At $0.01 per 1,000 characters, you only pay for what you generate. There are no minimum spends or wasted credits.
No monthly plans
We do not enforce monthly subscriptions or seat limits. Your balance never expires, allowing you to pause and resume generation at your own pace without losing access.
Free trial available
Sign in with Google to receive $0.50 in trial credit, valid for 7 days. This grants approximately 50,000 characters to test the API. Email-based accounts start without trial credit.
Integration Options
Integrating Lexiconet’s TTS API is straightforward for indie developers. You can send text via standard HTTP requests or leverage the official OpenAI SDK by adjusting the base URL. This approach keeps your implementation simple without requiring custom infrastructure or learning new protocols.
Direct API calls
Send a POST request to the speech endpoint with your JSON body containing the text, voice, and format. Receive the audio file directly in the response.
- Standard HTTP POST method
- JSON request body
- Audio response
OpenAI SDK support
Use the official OpenAI SDKs by simply changing the base URL to our API endpoint. This allows you to use familiar libraries and code structures without rewriting your integration logic.
- Compatible with OpenAI SDKs
- Easy base URL swap
- Familiar development workflow
Custom speed settings
Adjust the playback speed between 0.25 and 4.0 to fit your content’s pace. This flexibility ensures the audio matches your users’ listening preferences without post-processing.
- Speed range: 0.25–4.0
- Adjustable per request
- No post-processing needed
Get Started Today
Getting started takes less than a minute. Create your account using your Google credentials on the /get-api-key/ page, or sign up with an email and password if you prefer. This process is quick and requires no credit card upfront.
Once registered, you are immediately assigned a unique API key. This key authenticates your requests to the API base at https://api.playf65.com/v1. You can view your key, current balance, and usage statistics directly on your dashboard.
Sign up with Google
Click the sign-up button on the /get-api-key/ page and authorize Lexiconet to access your Google account. This method is the fastest way to create an account and instantly receive your $0.50 free trial credit.
- Instant account creation
- Automatic trial credit activation
- No credit card required
Get your API key
Your API key appears immediately after registration. Use this key in the Authorization: Bearer header for all requests. You can revoke and generate a new key at any time if needed; the old key stops working instantly.
- One active key per account
- Instant revocation support
- Compatible with standard HTTP headers
Try the free trial
Google-signed-up accounts receive $0.50 in credit, covering approximately 50,000 characters. The trial is valid for 7 days. Email-based accounts start without trial credit but can top up via USDT (TRC-20) immediately.
- 50,000 characters included
- Valid for 7 days
- Zero risk to test quality
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Use PCM if you need raw samples for further audio manipulation.
23 languages
Any voice speaks any of these languages.
