Frequently asked questions
What is a text to speech reader API?
It is a cloud service where you send text via a POST request and receive an audio file. TaleTTS API uses standard JSON bodies compatible with OpenAI SDKs. You send your script, specify a voice and format, and get back synthesized speech ready for playback in your children’s book app or educational platform without managing audio servers.
How does TTS work for children's stories?
You send text up to 4096 characters to the /v1/audio/speech endpoint. The system synthesizes the audio using licensed recordings from LibriVox. You receive an audio file in formats like mp3 or wav. For longer stories, split the text into parts and join the resulting audio files. This allows seamless integration into your digital storytelling workflow.
Which voices are best for fairy tales?
Q: Which voices are suitable for fairy tales? A: Luna offers a soft, storytelling tone, while Aria provides a warm, clear narrator style. Sage is calm and instructional, suitable for educational content. For energetic promo-style stories, Felix works well. All voices support 23 languages, allowing you to maintain consistent character voices across different linguistic versions of your children’s books.
Can I use the API for commercial projects?
Yes, the API is designed for startups and commercial applications. Input text is not used for training, and generated audio is returned in the response without being stored. You pay per character used, with no monthly plans or minimum spend. This model supports scalable commercial deployment for apps and web platforms creating educational audio content.
What languages are supported for storytelling?
The API supports 23 languages including English, Spanish, French, German, Japanese, Korean, Arabic, Hindi, and Portuguese. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses it from the script, defaulting to English for Latin text. Explicitly set the language for non-English Latin-script text.
How accurate is the pronunciation in other languages?
Voices are based on licensed recordings from LibriVox public-domain audiobook readings. The system supports 23 specific languages including Chinese, Russian, and Turkish. If the language parameter is omitted, Latin text defaults to English. For other languages, explicitly setting the ISO code ensures accurate pronunciation. Vietnamese, Indonesian, and Thai are not supported.
Is the API suitable for real-time reading?
It is not suitable for real-time streaming. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time for long texts, but short phrases take a few seconds. You receive the complete audio file after synthesis, not partial streaming audio, making it ideal for pre-generated content.
How do I handle long stories with multiple chapters?
Split your text into parts of up to 4096 characters per request. Send each part to the API and receive individual audio files. Then, join these audio files to create the full story. This approach handles texts longer than the character limit efficiently. Ensure your application manages the concatenation of these audio segments.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry the request or adjust parameters like voice or format. The system guarantees that no credit is lost for unsuccessful synthesis attempts.
Do I need to credit the voice actors?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. While the base recordings are public domain, each generated file carries an inaudible watermark marking it as synthetic speech. Check the specific license terms for LibriVox content if required by your distribution platform, but no direct actor credit is mandated by the API.
Can I control the speed of the narration?
Yes, you can control the speed using the speed parameter in your request. The allowed range is 0.25 to 4.0. This allows you to adjust the narration pace for children’s stories, making it slower for younger audiences or faster for older readers. The default speed is typically 1.0, but you can customize it per request.
Is there a limit to how many characters I can send?
Each request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer stories, you must split the text into multiple requests. Each request generates one audio file. You can then concatenate these files to create the complete audio narrative for your application or educational content.
How is the API billed?
Billing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. You can start with a $0.50 free trial valid for 7 days. Top-ups are made via USDT on the TRON network (TRC-20), with a minimum of $5. Balance does not expire, and there are no monthly plans.
Do I need a developer to use this API?
You need basic developer skills to integrate the API. You send JSON POST requests to the endpoint and handle the audio response. The API is compatible with OpenAI SDKs by changing the base URL. While you can use the provided curl example, implementing it in your app requires coding. No custom SDK or mobile app is provided.
First request
curl
curl https://api.playpg699.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.mp3How it works
The TaleTTS API converts written text into natural-sounding narration with a single API call. You send a POST request with your script, and receive an audio file ready for playback in your children's book app or educational platform.
Send text, get audio
Input plain text up to 4096 characters and receive high-quality audio in formats like MP3 or WAV. Failed requests incur no charge, ensuring you only pay for successful narration.
OpenAI-compatible endpoints
Use the standard POST https://api.playpg699.com/v1/audio/speech endpoint. The request shape matches OpenAI’s API, allowing you to use official OpenAI SDKs by simply changing the base_url.
Easy integration with existing stacks
Integrate seamlessly with your current tech stack using standard HTTP requests. Authenticate with a Bearer token and handle responses directly in your application code without managing complex audio infrastructure.
Voices for storytelling
Select from eight distinct voice presets designed to match the tone of your content. Each voice offers a unique character, allowing you to differentiate between story segments and educational explanations without needing multiple voice actors.
The library includes warm narrators for engaging stories, energetic voices for promotional content, and calm tones ideal for instructional material. All voices support any of the 23 available languages, ensuring consistent quality across global audiences.
Warm narrators like Aria and Luna
Aria provides a warm, clear narration style perfect for reading classic fairy tales. Luna offers a soft, storytelling tone that creates an intimate atmosphere for bedtime stories or gentle educational content.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling voice
Energetic characters like Felix
Felix delivers an energetic, promo-style delivery suitable for interactive apps or dynamic story segments. His tone keeps young listeners engaged during fast-paced narrative sections or game-like interactions.
Note: Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings.
- Felix: Energetic, promo style
Calm voices for educational content
Sage offers a calm, instructional tone ideal for teaching concepts or reading textbooks. Milo provides a friendly, conversational style that feels natural for dialogue-heavy educational tools.
Milos and Atlases ensure neutral, clear delivery for news-style or informational content.
- Sage: Calm, instructional
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary

Languages and accessibility
The TaleTTS API supports 23 languages, enabling developers to narrate children's stories in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This broad coverage ensures that educational audio content reaches diverse global audiences without requiring separate voice talent for each market.
Each voice can speak any of the supported languages, providing consistent character personality across different linguistic contexts. This flexibility allows startups to maintain narrative continuity even when localizing stories for multiple regions, ensuring that the emotional tone remains intact regardless of the language used.
Support for 23 major languages
We cover the most widely spoken languages for children's literature and education. If a language is not in this list, such as Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali, it is not supported. You can verify the exact list via the /v1/voices endpoint.
This selection focuses on high-demand markets for digital storybooks and language learning apps. By supporting these 23 languages, we reduce the need for complex multi-voice management systems, simplifying your audio infrastructure.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Clear pronunciation for non-native speakers
The voices are trained on licensed recordings from LibriTTS-R and LibriVox, ensuring clear and natural pronunciation. This clarity is essential for language learning tools where accurate phonetic delivery helps children and learners grasp new sounds correctly.
This consistency helps maintain the integrity of the story while aiding listeners in developing accurate listening skills in their target language.
Automated language detection
If you do not specify a language, the API guesses it from the script. Latin script text defaults to English, so you must set the language for non-English Latin text to avoid mispronunciation. For example, French text sent without the language parameter will be read as English.
This feature simplifies your integration by reducing the number of parameters you need to manage. However, for optimal results, explicitly setting the language code ensures the correct accent and intonation are applied to your children's stories.
Technical specifications
The API supports five standard audio formats: mp3, wav, opus, flac, and pcm. This flexibility ensures compatibility with various web players and mobile app audio engines without requiring additional conversion steps.
Each request accepts one format choice, allowing you to optimize file size or quality based on your specific delivery needs.
MP3, WAV, OPUS, FLAC formats
Choose from mp3, wav, opus, flac, or pcm based on your platform's requirements.
Wav and flac offer lossless quality for archival or high-fidelity playback, while mp3 and opus reduce bandwidth usage.
- mp3: widely compatible, smaller file size
- wav: uncompressed, high fidelity
- opus: efficient compression
- flac: lossless compression
- pcm: raw audio data
Speed control from 0.25x to 4.0x
Adjust speech rate between 0.25x and 4.0x to match the pacing of your content. Slower speeds aid comprehension for young listeners or language learners, while faster speeds suit quick reviews.
Speed is applied uniformly across the entire generated segment.
4096 character limit per request
Each API call accepts up to 4096 characters of input text. For longer stories, split the text into chunks and join the resulting audio files.
Spaces and punctuation count toward the character limit.
Pricing for startups
Startups can launch immediately with a $0.50 free trial (about 50,000 characters) valid for 7 days when signing in with Google. This allows you to validate your audio integration without upfront commitment.
Pay per character usage
Chargebacks are straightforward: you pay $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full if synthesis fails.
$10 per million characters
The cost is consistent regardless of voice or model. Both tts-1 and tts-1-hd use the same engine and price structure, allowing you to experiment with quality without changing your budget model.
No monthly fees or minimum spend
There are no subscriptions, seats, or minimum spend requirements. Balance does not expire. Top-ups via USDT (TRC-20) are credited automatically within minutes, with a minimum deposit of $5. No cards or invoices needed.

Data privacy and rights
Your input text is used exclusively to generate the audio file and is never used for training our voice models. This ensures that your unique story content remains proprietary to your startup.
Each generated audio file contains an inaudible watermark that clearly marks it as synthetic speech, providing transparency for your end users and helping maintain trust in your educational products.
Input text not used for training
We process your text solely to create the audio response. Unlike some competitors, we do not ingest your story text into our general training data, keeping your intellectual property secure.
Inaudible synthetic watermarks
Every audio file generated by TaleTTS API carries a unique, inaudible watermark. This digital signature identifies the content as AI-generated narration, which is increasingly important for transparency in children's media.
Generated audio not stored
The audio output is returned directly in the API response and is not retained on our servers after delivery. We keep only request metadata (time, characters, status) for billing purposes.
Use cases for education
Turn static text into engaging audio experiences. By converting storybooks into natural narration, developers can create interactive e-books that keep young readers engaged through voice.
Support language acquisition with clear, consistent pronunciation. Educational tools can offer audio guides in multiple languages, helping students practice listening skills with accurate, synthetic voices.
Make content accessible to visually impaired readers. High-quality narration ensures that educational materials are inclusive, allowing users to consume stories and lessons without relying solely on text.
Interactive e-books
Convert written stories into audio files with a single API call. Developers can integrate narration directly into apps, allowing children to listen to fairy tales while reading along.
Use different voices for different characters. This adds depth to interactive stories, making the reading experience more immersive and entertaining for young audiences without complex audio engineering.
- Dynamic narration for digital books
- Character-specific voice assignment
- Instant audio generation
Language learning tools
Provide clear audio examples for pronunciation practice. Students can hear accurate accents in 23 languages, supporting diverse learning needs without requiring native speaker availability.
Automatically detect language from input text. This reduces configuration overhead for developers building multilingual educational platforms that serve students from various linguistic backgrounds.
- Multi-language support
- Consistent pronunciation
- Automated language detection
Accessibility for visually impaired readers
Deliver high-quality audio narration for blind or low-vision users. Natural-sounding speech improves comprehension, making educational content more enjoyable.
Ensure inclusive access to digital libraries. By converting text to speech, you remove barriers for readers who struggle with traditional text-based formats.
- Natural voice synthesis
- Improved comprehension
- Inclusive design
Developer experience
The TaleTTS API uses a straightforward JSON request body, compatible with standard HTTP clients. You send your text payload alongside voice and format settings, receiving a direct audio response. This simplicity allows rapid integration into existing backend services without complex middleware.
Authentication relies on standard Bearer tokens, ensuring secure access to your generated audio files. The API returns standard HTTP error codes, making debugging intuitive for developers familiar with common RESTful patterns.
JSON request body
Send text up to 4096 characters in a simple JSON payload. Include the model, voice, and desired output format. The API processes this synchronously, returning the audio file directly in the response.
- Supports mp3, wav, opus, flac, and pcm formats
- Optional speed parameter (0.25–4.0) for pacing control
- Single JSON object per request for easy parsing
Bearer token authentication
Include your API key in the Authorization header as Bearer <your_key>. This single active key authenticates all requests from your application, simplifying credential management for small development teams.
- Standard HTTP header format
- One active key per account
- Instant revocation upon key renewal
Standard error codes
The API returns standard HTTP status codes (400, 401, 429, 500) to indicate success or failure. Failed requests incur no charge, and the response body provides clear error messages to help you adjust your integration quickly.

Getting started
To start narrating children's stories, sign up at /get-api-key/ using Google or email. Google sign-ups include a $0.50 free trial (50,000 characters) valid for 7 days.
Once registered, access your dashboard to view your unique API key and current balance. You can issue a new key at any time, instantly invalidating the old one.
Sign up for free trial
Visit the /get-api-key/ page and choose Google or email registration. Google accounts receive $0.50 credit (50,000 characters) valid for 7 days immediately. Email accounts start with zero balance.
- Google sign-up includes $0.50 trial credit
- Email sign-up requires initial top-up
- Trial valid for 7 days
Generate your API key
After signing in, your dashboard displays your active API key, starting with 'tts-'. Use this key in the Authorization header for all requests.
You can generate a new key at any time. The previous key stops working immediately upon creation of the new one.
- Key format: tts-...
- Instant invalidation of old keys
- Available in dashboard
First curl example
Use this command to test the API. Replace 'YOUR_API_KEY' with your key and 'text' with your story snippet.
curl -X POST https://api.playpg699.com/v1/audio/speech \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{"model": "tts-1", "input": "Once upon a time...", "voice": "aria", "response_format": "mp3"}'
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Craft enchanting digital fairy tales that ignite imaginations and inspire the next generation of dreamers.
23 languages
Any voice speaks any of these languages.
