Text-to-Speech API for Children’s Stories and Fairy Tales

By FableVoice editorial team · Updated 2026-11-19

FableSonic is a specialized text-to-speech API designed for creators producing children’s audiobooks and animated stories. We provide a reliable, copyright-safe alternative to complex web studios, offering eight distinct narrator voices derived from licensed LibriVox recordings. Our platform simplifies the technical workflow, allowing you to focus on storytelling while we handle the synthesis.

This page outlines how to integrate our API into your content pipeline. You will find details on our eight voice presets, support for 23 languages, and transparent pricing based on character count. We also compare our approach to Murf AI Studio, explaining why our OpenAI SDK compatibility and simple USDT payments suit independent creators who need volume and clarity without monthly subscriptions.

Text-to-Speech API for Children’s Stories and Fairy Tales

Frequently asked questions

What is the FableSonic?

FableSonic is a specialized storefront for the FableVoice TTS API, designed for content creators who need reliable, copyright-safe synthetic voices for children's audiobooks and animated stories. We simplify the technical side of text-to-speech so you can focus on narration.

Is FableVoice a Murf AI Studio alternative?

FableVoice is not affiliated with Murf AI. It is a cloud text-to-speech API where you send text and receive an audio file via a POST request. It offers 8 voice presets and supports 23 languages, providing a distinct alternative for generating synthetic speech without relying on other brands.

Which voices are best for children's stories?

You can choose from eight presets. Female voices include Aria (warm, clear narrator), Nova (bright, upbeat), and Luna (soft, storytelling). Male options are Felix (energetic, promo), Milo (friendly, conversational), Atlas (neutral, news), and Orion (deep, documentary). Each voice can speak any of the 23 supported languages.

How much does it cost per character?

The price is $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and the charge is returned in full if synthesis fails. There are no monthly plans or minimum spend requirements.

Can I use FableVoice for commercial audiobooks?

Yes, the API is available for commercial use. 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. You can generate up to 4,096 characters per request and join files for longer texts.

Does FableVoice support SSML?

No, FableVoice does not support SSML. It is a simple cloud API where you send text and receive an audio file. The request body includes fields like model, input, voice, response_format, and speed, but does not include SSML tags for markup or pronunciation control.

Are the voices based on real people?

Yes, the voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech, ensuring transparency about the origin of the audio content.

How many characters can I send in one request?

You can send up to 4,096 characters per request. For longer texts, you should split them into parts of up to 4,096 characters and join the resulting audio files. This limit applies to each individual API call you make.

What audio formats are supported?

The API supports mp3, wav, opus, flac, and pcm as response formats. You can specify the desired format in your request body. This allows you to choose the best balance between file size and quality for your specific children's story project.

Is there a free trial available?

Yes, signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up with USDT on the TRON network for ongoing use.

How long does generation take?

Generation takes roughly real time on long texts, about 25 characters per second of generation. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue before being synthesized.

Can I clone a voice with FableVoice?

No, FableVoice does not offer custom voice cloning. It provides eight preset voices based on licensed recordings. You cannot upload your own voice or design custom voices. The service focuses on reliable, pre-defined synthetic voices for consistent narration.

Does the API support streaming audio?

No, the API does not support streaming. It is a standard REST endpoint where you send a POST request and receive the complete audio file in the response. There is no WebSocket support or real-time partial audio generation available.

What happens if a request fails?

If synthesis fails, the charge is returned in full. Failed requests are free, so you are not billed for audio that was not successfully generated. This ensures you only pay for the audio files that are successfully delivered.

First request

curl

curl https://api.123h.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.mp3

Why creators choose FableVoice

Sound wave illustration for: Why creators choose FableVoice

FableSonic powers the FableVoice TTS API, offering a specialized path for creators of children's audiobooks and animated stories. We remove the technical friction of voice synthesis, allowing you to focus entirely on narration and storytelling.

Our infrastructure is built for reliability and clarity, ensuring that your synthetic voices remain distinct and legally clear for commercial use.

Copyright-safe voices from LibriVox

Copyright-safe voices from LibriVox

Every voice in our library is derived from licensed recordings of LibriVox public-domain audiobook readings. This foundation provides a clean copyright baseline for your productions, distinguishing our approach from platforms that rely on proprietary or ambiguous voice models.

Simple API, no complex studio

Forget complex drag-and-drop editors. We provide a direct cloud API endpoint where you send text and receive an audio file. It works with the OpenAI SDK by simply changing the base URL, making integration straightforward for developers who prefer code over canvas.

  • JSON body requests with standard fields
  • No need to manage audio tracks manually
  • Works with existing OpenAI SDKs

No monthly subscriptions

You pay only for the characters you actually synthesize. There are no recurring seat fees or minimum monthly spends. If a request fails, you are not charged, ensuring you only pay for successful audio generation.

The 8 Narrator Voices

Sound wave illustration for: The 8 Narrator Voices

Each voice is derived from licensed recordings in the LibriTTS-R dataset (CC BY 4.0) or public-domain LibriVox readings. Every generated audio file contains an inaudible watermark identifying it as synthetic speech.

Select from eight distinct presets to match the mood of your story, from gentle bedtime tales to energetic adventures. All voices support 23 languages, allowing you to localize your fairy tales without hiring new talent.

Warm narrators: Aria and Luna

Aria offers a warm, clear tone ideal for standard narration. Luna provides a soft, storytelling quality perfect for gentle bedtime stories.

bullets

Energetic storytellers: Felix and Nova

Felix brings an energetic, promotional vibe suitable for engaging young audiences. Nova delivers a bright, upbeat delivery that keeps listeners engaged.

bullets

Calm and deep: Sage, Milo, Atlas, Orion

Sage offers a calm, instructional tone. Milo is friendly and conversational. Atlas provides a neutral, news-style delivery, while Orion offers a deep, documentary voice.

bullets

Support for 23 Languages

Sound wave illustration for: Support for 23 Languages

FableSonic supports 23 languages, covering major global markets with both Latin and Cyrillic scripts. This ensures your children's stories and fairy tales can reach a diverse audience without needing separate voice models for each region.

Global reach with Latin and Cyrillic scripts

The API handles text in multiple scripts, allowing you to produce content in languages ranging from English and Spanish to Russian and Arabic. You can mix and match voices across these languages seamlessly within your narration workflow.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Automatic language detection

If you do not specify a language, the system guesses it from the text script. For Latin-script text that is not English, you should explicitly set the language code to ensure accurate pronunciation and intonation.

Explicit language code support

You can pass an optional ISO language code in the request to override detection. This guarantees consistent voice quality even for texts that might otherwise be misidentified, such as Spanish text that looks similar to English.

Technical Simplicity

Sound wave illustration for: Technical Simplicity

The API mirrors the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base_url to https://api.123h.info/v1. This compatibility means you can integrate TTS into your existing workflows with minimal code changes. You send a JSON payload with your text, voice selection, and format preference, receiving a direct audio file response.

This simplicity extends to format choices and speed control. You select from five audio formats and adjust generation speed between 0.25x and 4.0x to match your story’s pacing. The technical stack handles the rest, letting you focus on the narrative rather than audio engineering details.

OpenAI SDK compatible

Use standard OpenAI SDKs with a simple base_url change. Send model, input, voice, and response_format in a JSON body. The endpoint accepts the same request shape as OpenAI’s speech API, ensuring smooth integration for developers already familiar with that ecosystem.

  • Supports tts-1 and tts-1-hd models
  • Standard JSON request structure
  • Works with official OpenAI SDKs

Multiple audio formats

Choose from mp3, wav, opus, flac, or pcm based on your distribution needs. MP3 and OPUS are efficient for web delivery, while WAV and FLAC offer lossless quality for archival. PCM provides raw audio data for custom processing pipelines.

Fast generation speeds

Long texts generate at roughly real-time speed, processing about 25 characters per second. Short phrases may take a few seconds due to queue processing. Requests are handled sequentially, so under heavy load, generation time may increase slightly.

Transparent Pricing

Sound wave illustration for: Transparent Pricing

FableSonic uses a straightforward usage-based model: $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward the total. There are no monthly subscriptions, no per-seat fees, and no minimum spend requirements, making it easy to scale your narration projects without unexpected overhead.

$10 per million characters

Your cost scales directly with the length of your stories. Since texts are processed in requests up to 4096 characters, longer audiobooks are split into parts and joined by the client. This structure ensures you only pay for the actual content generated, keeping budgeting simple for indie creators and small studios alike.

Pay only for successful requests

If synthesis fails due to a server error, the charge is returned in full. You are not billed for failed attempts, ensuring that your balance reflects only usable audio files. This reliability protects your budget while you refine your scripts and voice selections.

USDT TRC-20 payments

We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits are added automatically within minutes of transfer. There are no credit cards, PayPal options, or VAT invoices to manage. Your balance never expires, allowing you to pause creation between seasons without losing funds.

  • Minimum top-up: $5 USD
  • Credited automatically within minutes
  • No monthly subscriptions or seats
Transparent Pricing

Demo & Quick Start

Sound wave illustration for: Demo & Quick Start

See how simple it is to turn your story text into audio. The API accepts standard JSON payloads, allowing you to use familiar tools like the OpenAI SDK by simply adjusting the base URL.

Try the curl command

Send a request to POST https://api.123h.info/v1/audio/speech with your tts-... key. Pass the text, voice (e.g., aria), and format. The endpoint returns the audio file directly.

Generate your first audio file

For texts under 4,096 characters, the response is immediate. For longer stories, split your text into parts and join the resulting audio files. Short phrases take a few seconds; long texts generate at roughly real-time speed.

Check voice samples

Browse the 8 preset voices to find the perfect tone. From Aria’s warm narration to Orion’s deep documentary style, each voice is licensed from LibriVox and ready for your children’s stories.

Data & Privacy

Sound wave illustration for: Data & Privacy

Content creators need to know how their stories are handled. When you send text for synthesis, it is processed solely to generate the audio file and is not used to train any underlying models.

After generation, the audio response is returned to you immediately and is not stored on our servers. We retain only request metadata—such as time, character count, and status—strictly for billing purposes.

Input text not used for training

Your source text remains yours. We use it exclusively for the single purpose of producing the requested audio file and do not incorporate it into our training datasets for future model improvements.

No storage of generated audio

The resulting audio files are returned in the response and are not stored on our infrastructure. This ensures that your unique story recordings remain in your possession, not in our cloud storage.

  • Audio is returned in the response, not stored.

Synthetic watermark included

Every generated audio file contains an inaudible watermark. This digital marker clearly identifies the content as synthetic speech, which is valuable for verifying authenticity when distributing children’s audiobooks or animated stories.

Comparison: Murf AI Studio

Sound wave illustration for: Comparison: Murf AI Studio

FableSonic (powered by the FableVoice API) offers a direct alternative to Murf AI Studio for creators who prefer programmatic control over a graphical editor. While Murf provides a web-based studio, our API integrates directly into your workflow, allowing you to generate audio files via simple HTTP requests without managing a complex interface.

We focus on simplicity and transparency, ensuring that every aspect of generation is predictable and auditable for children's content.

API vs. Web Interface

Murf AI Studio relies on a visual web editor where users drag and drop timelines and adjust settings manually. FableSonic exposes a standard REST API compatible with OpenAI SDKs, enabling you to send text and receive audio files programmatically. This approach is ideal for automating the production of serialized stories or bulk audiobook creation without manual clicks.

  • Web-based visual editing (Murf) vs. HTTP API (FableSonic)
  • Manual timeline adjustments vs. automated character-count billing
  • Single-user interface vs. scalable programmatic access

Cost efficiency for long texts

Murf often charges per minute of generated audio or per user seat. FableSonic charges $10 per million characters, regardless of audio duration. For a typical 50,000-character fairy tale, the cost is fixed at $0.50, providing predictable expenses for high-volume content creators.

  • $10 per million characters (FableSonic) vs. per-minute or per-seat models
  • Predictable costs for long-form audiobooks
  • No monthly subscription fees

Voice licensing clarity

Murf uses proprietary voices with varying licensing terms depending on your plan. FableSonic voices are derived from LibriTTS-R (CC BY 4.0) and LibriVox public-domain recordings, offering clear copyright-safe foundations for commercial content. Each generated file includes an inaudible synthetic watermark.

  • LibriTTS-R (CC BY 4.0) foundation vs. proprietary models
  • Inaudible synthetic watermark for provenance
  • Clear commercial licensing for children’s content

Get Started Today

Sound wave illustration for: Get Started Today

Create your account on the /get-api-key/ page using Google or a standard email and password. This step initializes your dashboard where you can monitor usage and balance in real time. Accounts are specific to this site, ensuring your credentials remain secure and isolated.

Once registered, you receive a unique Bearer token immediately. This key authenticates your requests to the API endpoint, allowing you to start generating audio files without waiting for manual approval or setup periods.

Sign up with Google or Email

Registration takes seconds. Choose Google for quick access or use your email to create a standard account. No credit card is required to begin, and you can issue a new key at any time if needed.

  • Google or email authentication
  • Instant account creation
  • No payment info required

Get your API key instantly

Your API key appears on the dashboard immediately after sign-up. Copy this key to use in your HTTP headers or SDK configuration. You can revoke and regenerate keys at any time to maintain security.

Start creating stories

Send your text to the speech endpoint and receive an audio file. With 60 requests per minute, you can batch-process chapters quickly. Use the OpenAI SDK by pointing it to our base URL for seamless integration.

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.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. openai-node on GitHub
  3. TRON developer hub: TRC-20
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. Creative Commons Attribution 4.0
  6. ISO 639 language codes
  7. LibriVox public-domain audiobooks
  8. LibriTTS-R corpus (OpenSLR 141)
  9. curl documentation
  10. IETF RFC 7845: Ogg Opus
  11. Python documentation
  12. OpenAI API reference: create speech

More on this site