Frequently asked questions
What does TTS stand for?
TTS stands for Text-to-Speech. It is a technology that converts written text into audible audio files. Our API accepts your story text and returns an audio file, allowing you to create narrated content without recording human voices.
Is TTS better than human narrators?
Neither is objectively better; they serve different needs. TTS offers instant generation and consistent quality without scheduling conflicts. Human narrators provide unique emotional nuance. Our voices are based on licensed recordings, offering a reliable, copyright-safe alternative for consistent story delivery.
Can I use TTS for commercial projects?
Yes. You pay for the characters processed, and the generated audio is yours to use. Input text is not used for training. We do not claim ownership over your specific story recordings, allowing you to distribute them commercially without additional licensing fees.
How natural are the voices?
Voices are based on licensed recordings from LibriTTS-R and LibriVox. They avoid sounding overly robotic, offering clear, distinct tones like Aria’s warm narration or Felix’s energetic promo style. Every file carries an inaudible watermark marking it as synthetic speech.
What is the difference between tts-1 and tts-1-hd?
Both models use the same engine and price. The distinction is purely in the model identifier sent in the request. Both deliver identical audio quality and speed, allowing you to switch between them without changing your workflow or budget.
Can I control the speed of the voice?
Yes. You can adjust the speed parameter between 0.25 and 4.0. This allows you to slow down complex stories for clarity or speed up simpler tales. The default speed provides a natural pacing suitable for most children’s narratives.
Do the voices sound robotic?
No. The voices are derived from licensed human recordings, providing natural intonation and rhythm. While they are synthetic and carry an inaudible watermark, they avoid the flat, monotone quality often associated with older TTS systems, offering clear, engaging narration.
Is there a limit to the story length?
Each API request accepts up to 4,096 characters. For longer stories, you split the text into parts and join the resulting audio files. There is no overall limit to total story length, only per-request constraints. Processing takes roughly real-time duration.
Can I mix different voices in one story?
Yes. You can generate separate audio files for each character using different voice presets like Luna or Milo. You then combine these files in your audio editor. This allows distinct vocal personalities for various characters within a single narrative.
What is an API?
An Application Programming Interface (API) allows your software to communicate with our TTS service. You send a POST request with your text and receive an audio file. It works similarly to the OpenAI SDK, enabling automated story generation.
Do I need to know code?
No. While the API uses JSON requests, you can use tools like Postman or curl to generate audio directly. We provide ready curl examples and documentation. You can also use the API with no-code tools that support HTTP requests to generate audio.
How is the audio delivered?
Audio is returned directly in the API response. You can choose formats like MP3, WAV, Opus, FLAC, or PCM. The file is delivered immediately upon successful synthesis, allowing you to save it locally or stream it to your application.
Can I download the audio files?
Yes. Once the synthesis is complete, the audio file is included in the response. You can save it to your device or server. Failed requests are free, so you only pay for successfully generated and downloadable audio files.
Is the audio high quality?
Yes. We offer high-quality formats like WAV and FLAC alongside standard MP3. The voices are based on licensed recordings, ensuring clear audio. Speed is roughly real-time, and failed requests incur no charge, ensuring you only pay for quality output.
Understanding TTS Technology
FableSonic converts your manuscript into broadcast-ready audio using a cloud API. You send text, and the service returns an audio file. This straightforward pipeline removes the need for recording studios, allowing you to produce audiobooks and animated stories at scale without managing complex hardware or software environments.
How text becomes audio
The process begins when you submit text via a simple API request. The system processes the input and returns a downloadable audio file in formats like MP3 or WAV. Each request handles up to 4,096 characters, ensuring consistent quality without requiring manual segmentation for shorter stories.
Neural voice synthesis
Our engine uses neural models trained on licensed recordings from LibriTTS-R and LibriVox. This technology captures natural intonation and pacing, essential for keeping young listeners engaged. The result is synthetic speech that sounds polished and professional, suitable for children’s audiobooks.
Latency and speed
Generation typically takes about one second per 25 characters of text, matching real-time narration speed for long texts; short phrases may take a few seconds. Short phrases may take a few seconds due to processing queues. For longer texts, you split the text into parts of up to 4,096 characters and join the resulting audio files.
API vs. Web Platform
For children's content creators, an API offers direct programmatic access to the TTS engine, bypassing manual dashboard uploads. You send text and receive audio files, enabling seamless integration into existing storytelling workflows without switching contexts.
This approach supports automation, allowing you to batch-process entire storybooks or generate educational videos programmatically. Direct API integration ensures consistent voice quality and predictable costs, fitting the technical needs of modern content production.
Programmatic access
Unlike web platforms that require manual entry, our API lets you send text via HTTP requests. This gives you full control over parameters like voice selection and speed, ensuring every story segment matches your creative vision precisely.
- Send text via JSON POST requests
- Receive MP3, WAV, or OPUS files directly
- Control voice, speed, and format programmatically
Automation benefits
Automation reduces repetitive tasks, allowing you to generate hundreds of story pages in minutes. You can trigger audio generation based on content updates or schedule releases for educational series without manual intervention.
This efficiency is crucial for creators producing serialized content. By automating the synthesis step, you focus on writing and illustration while the API handles the audio production at scale.
- Batch process entire books
- Trigger generation via content updates
- Reduce manual entry errors
Direct API integration
Direct integration connects your content management system directly to the TTS engine. You can embed audio generation into your publishing pipeline, ensuring that text is converted to speech upon publication.
This method supports complex workflows, such as generating interactive story elements where audio responds to user actions. The API handles the heavy lifting, delivering audio files ready for immediate use.
- Connect directly to CMS platforms
- Generate audio upon publication
- Support interactive story workflows
Use Cases in Children's Content
Text-to-speech APIs transform written manuscripts into ready-to-use audio files, allowing creators to produce audiobooks, educational content, and interactive stories at scale. By sending text via a simple HTTP request, you receive an audio file without managing studio equipment or hiring voice actors for every project.
This programmatic approach eliminates the scheduling bottlenecks of traditional recording sessions. You can generate hours of narration in minutes, ensuring consistent voice quality across entire series while maintaining full control over the production workflow.
Audiobook production
Generate complete children's audiobooks by splitting long texts into 4,096-character chunks and stitching the resulting audio files. This method supports full-length stories, allowing you to publish serialized content efficiently.
The ability to choose from eight distinct voices ensures you can match the tone of your narrative, whether it is a gentle bedtime story or an adventurous tale, all produced from a single text source.
- Split large manuscripts automatically for seamless audio joining
- Consistent voice quality across multi-chapter series
- No studio booking delays
Educational videos
Sync generated audio with visual assets for educational content. Since the API returns standard audio formats like MP3 or WAV, you can easily integrate the voiceovers into your video editing software alongside animations or illustrations.
Use different voices for different characters or educational segments to keep young audiences engaged. The clear, neutral delivery of voices like Aria or Luna works well for instructional material where clarity is paramount.
- Easy integration with video editing workflows
- Support for multiple languages for diverse classrooms
- Consistent pacing for learning materials
Interactive stories
Create dynamic content where audio responds to user choices. By triggering API calls based on user input, you can branch narratives without pre-recording every possible path, saving storage and production time.
The ability to generate audio on demand makes this ideal for apps or web-based interactive books.
- On-demand audio generation for branching narratives
- Low latency for short interactive prompts
- Scalable for user-driven content
Voice Selection for Kids
Choosing the right voice is critical for children's content. The API offers eight distinct presets, each tailored to specific storytelling needs. Selecting the appropriate voice ensures the narrative tone matches the story's mood, from gentle lullabies to adventurous tales.
Each voice is based on licensed recordings, providing a professional quality that engages young listeners without requiring extensive editing.
Warm and clear voices
Aria and Luna are ideal for gentle reading. Aria offers a warm, clear narrator style perfect for straightforward stories. Luna provides a soft, storytelling tone that works well for bedtime tales or emotional narratives.
- Aria: warm, clear narrator
- Luna: soft, storytelling
Energetic narrators
For action-packed adventures, Nova and Felix bring energy. Nova is bright and upbeat, suitable for lively characters. Felix is energetic and promo-style, ideal for dynamic scenes or interactive story elements that require engagement.
- Nova: bright, upbeat
- Felix: energetic, promo
Calming tones
Sage and Milo offer conversational ease. Sage is calm and instructional, great for educational content. Milo is friendly and conversational, creating a relatable voice for dialogue-heavy stories. Orion provides a deep, documentary tone for serious tales.
- Sage: calm, instructional
- Milo: friendly, conversational
- Orion: deep, documentary
Language Support
FableVoice supports 23 languages, including Arabic, Chinese, French, German, Japanese, Korean, Spanish, and Swahili. Any voice can speak any supported language, making it easy to produce consistent audio across diverse story collections.
For non-English Latin-script text, explicitly set the language parameter to ensure accurate pronunciation. If omitted, the system guesses the language, defaulting to English for Latin script.
23 languages available
Our API covers major global markets with 23 supported languages. This range allows creators to reach international audiences without managing multiple voice engines or inconsistent quality standards across different platforms.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
- Any voice works with any language
- Optional ISO code for precise control
Multi-story series
Maintain consistent character voices across a series by selecting the same preset (e.g., Luna for soft storytelling or Felix for energetic promos). The 4096-character limit per request requires you to split longer chapters and join the audio files.
- 8 distinct voice presets
- Consistent tone across episodes
- Split long texts into parts
Localization
Translate your stories and generate new audio files quickly using the same voice profile. This ensures brand consistency while adapting content for specific linguistic markets without re-recording with new talent.
Cost Efficiency
Billing is straightforward: you pay $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. This model ensures you only fund actual narration, avoiding the overhead of unused studio time.
Per-character billing
Each request processes up to 4,096 characters. Longer stories are split and joined seamlessly. You are charged only for completed synthesis, and failed requests are free.
No subscription waste
There are no monthly plans or minimum spends. You top up via USDT (TRC-20) when needed, with no expiration on your balance. This fits irregular production schedules perfectly.
Trial credit usage
Signing in with Google grants $0.50 in trial credit (approx. 50,000 characters) valid for 7 days. This allows you to test voice quality and API integration before committing funds.

Technical Requirements
Integration requires only basic coding skills. You send a POST request to the speech endpoint with your text and preferred voice. The API returns an audio file, typically in MP3 or WAV format, which you can store or play directly in your application.
Basic coding skills
You do not need advanced engineering knowledge. Standard HTTP clients in Python, JavaScript, or Go are sufficient. The request structure mirrors common TTS APIs, making it straightforward for developers familiar with RESTful services.
- Standard HTTP POST requests
- JSON payload support
- Compatible with OpenAI SDKs
API integration
Connect your storytelling platform by setting the base URL to https://api.123h.info/v1. Use your API key for authentication. For longer stories, split the text into segments of up to 4,096 characters, generate audio for each, and join them into a single file manually.
- Base URL: https://api.123h.info/v1
- Bearer token authentication
- Split and join workflow
Audio file management
The API returns audio files directly in the response. You are responsible for storing these files and managing their lifecycle. Formats like MP3, WAV, OPUS, FLAC, and PCM are available. Choose the format that best suits your distribution channel, balancing quality and file size.
- Multiple format support
- Direct file download
- Manual storage management
Content Ownership
When you generate audio through the FableSonic API, you retain full rights to the resulting files. This clarity allows content creators to use the generated speech in children's audiobooks, educational videos, or interactive stories without worrying about complex licensing tiers or hidden restrictions on commercial use.
Rights to generated audio
The audio files you receive are yours to distribute. Unlike traditional studio recordings where rights might be shared or limited, our API model ensures that once the synthesis is complete, the output is integrated into your project freely.
Inaudible watermarking
Every generated file carries an inaudible watermark that marks it as synthetic speech. This helps identify the origin of the audio as AI-generated, which is increasingly important for transparency in children's media, yet it remains undetectable to the end listener.
No training data usage
Your input text is used only to produce the audio and is not used for training. This means your unique story scripts or educational content remain private and are not ingested into the model’s future learning set, protecting your creative IP.
Comparison with Traditional Studios
Traditional studios require booking voice actors, scheduling recording sessions, and waiting days or weeks for final audio files. You also pay for studio time, engineer fees, and potential re-recording rounds. With FableSonic, you send text and receive an MP3 or WAV file in seconds, eliminating the logistical delay.
Speed and cost
Studio rates vary, but typically involve booking fees and engineer costs. Our API charges $0.01 per 1,000 characters, making it significantly cheaper for high-volume content like children’s series. Generation takes seconds per request, allowing instant iteration.
- No hourly studio rates
- Pay only for characters used
- Instant generation vs. days for recording
Scalability
Producing 100 stories with a human voice actor means coordinating schedules and managing consistent quality across sessions. The API handles 60 requests per minute, ensuring consistent voice quality for every chapter without human fatigue or scheduling conflicts.
- Consistent voice across hundreds of episodes
- No booking conflicts
- Handle large series effortlessly
Ease of use
You do not need to manage microphones, soundproof booths, or audio engineers. Simply paste your text into the API, select a voice like Aria or Luna, and download the file. The process fits into a standard content workflow without specialized audio equipment.
Getting Started
Creating your first audiobook starts with a simple registration. Visit /get-api-key/ to sign in with Google or create an account with email and password. You will receive a unique API key and $0.50 in trial credit, valid for seven days, which covers approximately 50,000 characters of text.
Sign up process
After signing up, navigate to your dashboard to view your API key, current balance, and usage statistics. The interface provides a ready-to-use cURL example, allowing you to copy the command directly into your terminal without manual configuration. Your key is active immediately upon creation.
- Google or email/password authentication
- Instant API key generation
- $0.50 trial credit included
- Dashboard shows balance and usage
First API call
Send a POST request to https://api.123h.info/v1/audio/speech with your JSON payload. Include the model (tts-1 or tts-1-hd), your input text, and the desired voice preset. The endpoint returns an audio file directly in the response, ready for download or playback.
- Endpoint: POST /v1/audio/speech
- Models: tts-1 or tts-1-hd
- Input: up to 4096 characters
- Output: direct audio file
Testing voices
Use the /v1/voices endpoint to list all eight available presets, from warm narrators like Aria to energetic options like Felix. Test short phrases with each voice to match the tone of your children's stories. Remember that requests are processed sequentially, so longer texts may take time.
- 8 voice presets available
- List voices via GET /v1/voices
- Test tone before full production
- Sequential processing may cause delays
Common Questions
FableSonic simplifies the technical side of text-to-speech so you can focus on narration. Our API accepts standard JSON requests, meaning you can generate audio files with minimal code or even via simple command-line tools.
The platform handles character splitting and audio joining automatically, allowing you to produce long audiobooks without managing complex infrastructure or worrying about file sizes.
Is it hard to use?
If you can send a POST request, you can use FableSonic. The endpoint matches the OpenAI speech format, so existing SDKs work by simply changing the base URL to https://api.123h.info/v1.
You start with a $0.50 trial credit valid for 7 days, giving you about 50,000 characters to test voices and formats before spending anything.
- Support via email only; no phone or live chat.
- No complex SSML or phoneme dictionaries to learn.
Can I edit the audio?
The API returns complete audio files in formats like mp3, wav, or opus. It does not stream partial audio or offer real-time editing.
Since voices are synthetic, you cannot adjust emotion tags or pause mid-sentence via the API. You must regenerate the segment if you need a different tone.
Do I need a developer?
Basic coding skills help for automation, but the API is accessible to non-developers using tools like Postman or curl.
The dashboard shows ready-to-use curl examples and usage stats, making it easy to integrate without building a full application from scratch.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. These voices maintain engagement without sounding overly dramatic.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Python documentation
- Node.js documentation
- W3C WAI: making audio and video accessible
- openai-node on GitHub
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- FFmpeg documentation
- IETF RFC 7845: Ogg Opus
- LibriTTS-R paper (arXiv 2305.18802)
- curl documentation
- openai-python on GitHub
