Frequently asked questions
Can I use AI voiceovers for monetized YouTube videos?
Yes. The generated audio files are returned directly in the API response and are not stored by us. Input text is used only to produce audio and is not used for training. You can use the generated audio for monetized videos.
How many characters can I send in one request?
You can send up to 4096 characters per request. For longer scripts, you should split the text into parts of this size and join the resulting audio files. This ensures consistent processing and avoids exceeding the single-request character limit for the synthesis engine.
Which voice is best for educational content?
Sage is designed for calm, instructional content, making it ideal for educational videos. Atlas offers a neutral, news-style delivery suitable for tutorials. Both voices provide clear, professional narration that helps maintain viewer focus without distracting vocal quirks or excessive emotional inflection.
Do I need coding skills to use this API?
No coding skills are required. The API follows the standard OpenAI request shape, so you can use the official OpenAI SDKs by simply changing the base URL. You can also use ready-made curl examples provided on the dashboard, or integrate via no-code tools that support HTTP requests.
Are the voices copyrighted or licensed?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. You do not need to worry about traditional copyright claims for the voice synthesis itself.
Can I change the speed of the voice?
Yes, you can adjust the speed between 0.25 and 4.0. This allows you to slow down complex explanations or speed up quick updates. The speed parameter is sent directly in the JSON body of your request alongside the text and voice selection.
What happens if my internet drops during generation?
Requests are processed sequentially. If your connection drops, you may need to retry the request. Failed requests are free, so you are not charged if synthesis fails. You can check your balance and usage on the dashboard to confirm whether a charge was applied.
Do you support long-form video narration?
Yes. You can split long texts into parts of up to 4096 characters and join the audio files. Typical speed is roughly real-time, generating about 25 characters per second. Under load, requests may wait in a queue, but the system handles the volume.
Is there a limit to how many videos I can create?
There is no limit to the number of videos you can create. You are limited by your account balance and rate limits of 60 requests per minute. You can top up with USDT on the TRON network (TRC-20) anytime, and there are no monthly plans or minimum spend requirements.
Can I use the audio commercially?
Yes. The API provides the audio file directly in the response. You can use the generated audio for commercial projects like YouTube videos, podcasts, or advertisements.
How accurate is the language detection?
If the language is not set, it is guessed from the script, with Latin text defaulting to English. For non-English Latin-script text, we recommend setting the language parameter explicitly. This ensures accurate pronunciation for the 23 supported languages, avoiding misinterpretation of the input text.
Do I need to credit the AI voice?
The generated audio carries an inaudible watermark marking it as synthetic speech. However, you may choose to credit the voice name or source in your video description.
What if the audio quality isn't what I expected?
You can adjust parameters like speed and voice selection to better match your needs. If synthesis fails, the charge is returned in full. You can test different voices and formats (mp3, wav, opus, flac, pcm) to find the best quality for your specific use case.
Can I mix different voices in one video?
Yes. You can generate separate audio files for each voice using different requests and then join them using your preferred editing tool. The API returns the audio file directly, allowing you to combine multiple voices seamlessly in your final video production workflow.
First request
curl
curl https://api.je1688.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 Creators Use API Voiceovers
Automated narration lets you produce daily video content without hiring voice actors or managing complex editing timelines. By integrating the TTS API into your workflow, you turn scripts into audio files ready for your editor, freeing you to focus on storytelling and visuals.
Scale Your Content Output
Split long scripts into parts of up to 4096 characters and join the resulting audio files. Requests are processed sequentially, so under load a request may wait in a queue.
Maintain Consistent Brand Voice
Use the same voice across all your videos to build recognition. Choose from eight preset voices, from warm narrators to energetic promo styles, ensuring a professional tone for every script.
Reduce Production Costs
Pay only for what you use. At $0.01 per 1,000 characters, you avoid monthly subscriptions or minimum spend requirements. Failed requests are free, so you only pay for successful audio generation.
Choose Your Narrator
Select the perfect narrator to match your video's tone. Our eight preset voices are built from licensed recordings, ensuring high-quality audio that fits any style, from casual vlogs to professional documentaries.
Female Voices: Aria, Nova, Luna, Sage
Aria offers a warm, clear narration style ideal for explainer videos. Nova brings a bright, upbeat energy perfect for dynamic shorts. Luna provides a soft, storytelling tone for narrative content, while Sage delivers a calm, instructional voice for tutorials.
Male Voices: Felix, Milo, Atlas, Orion
Felix is energetic and great for promotional content. Milo sounds friendly and conversational for relatable storytelling. Atlas provides a neutral, news-style delivery, and Orion offers a deep, documentary voice for serious topics.
Voice Styles: From Storytelling to News
Each voice is designed for specific use cases. You can switch between personalities instantly by changing the voice parameter in your API request. All voices support 23 languages, allowing you to localize content. If the language is not set, it is guessed from the script (Latin text defaults to English), so for non-English Latin-script text you should set the language parameter explicitly.
Supported Languages & Formats
Support your global audience with 23 languages, from English and Spanish to German and Japanese. Any voice can speak any of these languages, and the system guesses the language from the text script if you don’t specify one.
Receive audio in MP3, WAV, OPUS, FLAC, or PCM formats, ensuring compatibility with any video editor. Generation takes roughly one second per 25 characters for long texts, keeping your production workflow fast and predictable.
23 Languages Including English, Spanish, German
Choose from Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. If your text uses Latin script but isn’t English, set the language parameter explicitly to ensure accurate pronunciation.
- Arabic, Chinese, Danish, Dutch, English, Finnish
- French, German, Greek, Hebrew, Hindi, Italian
- Japanese, Korean, Malay, Norwegian, Polish, Portuguese
- Russian, Spanish, Swahili, Swedish, Turkish
Audio Formats: MP3, WAV, OPUS, FLAC, PCM
Select the format that fits your editing pipeline. MP3 is ideal for web delivery, while WAV and FLAC offer lossless quality for professional post-production. PCM provides raw audio data, and OPUS offers efficient compression.
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 queueing. For texts over 4096 characters, split them into parts and join the resulting audio files seamlessly.
How It Works
We help you automate narration by sending your script directly to our API. You can use the same workflow as popular tools, simply adjusting the base URL to https://api.je1688.com/v1. This makes integration smooth for no-code creators who want to turn text into audio without complex setup.
Once you POST your text, the engine processes it and returns an audio file. You do not need special hardware or complex editing tools to get started. The process is designed to fit directly into your existing video production pipeline, allowing you to scale your content output efficiently.
Send Text via API
Structure your request with the required fields: model, input, voice, and response_format. You can specify up to 4096 characters per request. If your script is longer, split it into parts and join the resulting audio files later.
- Use standard JSON format for requests.
- Supports all 23 languages with optional ISO code.
- Adjustable speed from 0.25 to 4.0.
Receive Audio File
The API returns the generated audio file in your chosen format (mp3, wav, opus, flac, or pcm). Processing time is roughly real-time for long texts, though short phrases may take a few seconds due to queueing under load.
Download and Edit
Save the returned file directly into your video editing software. Since the audio is returned in the response, you can automate the download process using scripts or no-code tools like Zapier or Make, keeping your workflow entirely digital.
Pricing for Creators
You pay only for what you generate: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. If a synthesis fails, the charge is returned in full, so you never pay for errors.
Pay Per Character Used
Our pricing is straightforward and transparent. At $0.01 per 1,000 characters, creating a minute of narration typically costs just a few cents. You can estimate your budget based on script length before sending the request.
- Rate: $10 per 1 million characters
No Monthly Subscriptions
There are no recurring bills, seats, or minimum spends. You keep your balance and use it whenever you need it. Top-ups via USDT on the TRON network (TRC-20) are credited automatically within minutes after the transfer. Balance does not expire.
Free Trial Available
Start testing immediately with $0.50 in free credit, valid for 7 days. This provides about 50,000 characters to experiment with different voices and formats. Sign up with Google to receive the trial credit instantly.
- Trial: $0.50 credit (7 days)

Technical Requirements
Our API endpoint mirrors the standard OpenAI speech structure, allowing you to reuse existing client libraries with minimal configuration. By simply updating the base URL to https://api.je1688.com/v1, you can leverage official OpenAI SDKs for Python or Node.js without learning a new interface.
The service operates as a straightforward REST API, requiring only a standard HTTP POST request with a JSON body. Authentication is handled via a Bearer token in the header, ensuring secure access to your account's unique key.
OpenAI SDK Compatible
Leverage familiar tooling by pointing your OpenAI SDK to our base URL. This compatibility means you can integrate voice generation into your existing no-code workflows or custom scripts without rewriting your integration logic.
- Works with official OpenAI Python and Node.js SDKs
- Standard JSON request body structure
- Easy base URL configuration
Simple REST API
Send text via a standard POST request to /v1/audio/speech and receive an audio file directly in the response. The endpoint accepts standard parameters like model, voice, and speed, making it easy to automate narration generation.
- Single endpoint for all audio generation
- Supports MP3, WAV, OPUS, FLAC, and PCM formats
- JSON-based input and output
No Special Hardware Needed
Since all processing happens in the cloud, you do not need powerful GPUs or specialized audio hardware. Any device capable of running a modern web browser or making HTTP requests can trigger voice synthesis.
- Cloud-based processing
- Works on any computer or server
- No local dependencies required
Data Privacy & Usage
Your input text is used solely for generating the audio response and is never used to train our models. Once the synthesis is complete, the generated audio file is returned directly in the API response and is not stored on our servers.
We retain request metadata—such as timestamp, character count, and status—strictly for billing purposes. This ensures accurate tracking of your usage without retaining the actual content you create.
Text Not Used for Training
The text you send via the API is processed only to produce your specific audio file. It is not added to our training data sets, ensuring your scripts remain private and exclusive to your project.
No Audio Storage
Generated audio files are returned in the response stream and are not permanently stored on our infrastructure. You maintain full ownership and control over the resulting audio files immediately after generation.
Secure API Keys
Each account is secured with a single active API key. You can issue a new key at any time, and the old one stops immediately, ensuring tight control over access to your narration service.
Common Use Cases
Automate narration for high-volume content without hiring voice actors. Our API integrates directly into your editing workflow, turning scripts into polished audio files ready for YouTube, Shorts, and tutorials.
YouTube Shorts Narration
Generate quick, engaging voiceovers for short-form videos. With speeds up to 4x, you can produce multiple scripts per minute, keeping up with trending topics and maintaining a consistent brand voice across all your shorts.
- Ideal for fast-paced commentary
- Supports multiple languages for global reach
- Instant MP3/WAV output for easy editing
Educational Video Scripts
Create clear, instructional narration for tutorials and courses. Use calm voices like Sage or friendly tones like Milo to explain complex topics. The API handles up to 4,096 characters per request, perfect for standard lesson lengths.
- Consistent tone for series content
- No re-recording needed for minor script changes
- Supports technical and conversational styles
Documentary Voiceovers
Produce high-quality narration for documentaries and long-form videos. Use deep, neutral voices like Atlas or Orion for a professional, engaging feel. Each audio file includes a synthetic watermark, ensuring authenticity while maintaining production quality.
- High-fidelity audio formats (FLAC, WAV)
- Natural pacing and intonation
- Suitable for long-form content
Get Started Today
Start creating professional video narration without upfront costs. Sign up using your Google account on the /get-api-key/ page to instantly receive a $0.50 trial credit, valid for 7 days and covering approximately 50,000 characters.
Sign Up for Free Trial
Create an account in seconds. Your trial credit is active immediately, allowing you to test voice quality and API reliability before committing any funds.
Generate Your First Audio
Paste your script into the API endpoint or use the provided curl example. Select a voice like Aria or Felix, set your language, and receive a downloadable audio file in your preferred format.
Integrate Into Your Workflow
Use the standard OpenAI SDK by adjusting the base URL to https://api.je1688.com/v1. Automate narration for shorts, tutorials, or documentaries by connecting your script generator directly to our TTS endpoint.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Viewers expect factual delivery without emotional bias, making voice selection critical for trust.
23 languages
Any voice speaks any of these languages.
