Frequently asked questions
What is an online voice over maker?
It is a cloud API that converts text into audio files via a POST request. You send JSON with your script and receive an audio file. This infrastructure allows language learning creators to generate thousands of practice tracks consistently without hiring voice actors, using standard HTTP requests.
How many languages are supported?
We support 23 languages including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and Russian. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, defaulting to English for Latin text. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Can I change the speed of the voice?
Yes, you can adjust the speed between 0.25 and 4.0 using the speed field in your request. This allows you to create slower practice tracks for beginners or faster audio for advanced learners. The API accepts this parameter alongside the text, voice, and model specifications.
Do I need to install software?
No software installation is required. The service is a cloud API accessible via HTTP. You can use the official OpenAI SDKs by changing the base URL or send standard POST requests. It works with any programming language or tool that can make API calls.
Is the voice realistic for learners?
Voices are based on licensed recordings from LibriTTS-R and LibriVox. They are clear synthetic voices suitable for educational content. Each file carries an inaudible watermark marking it as synthetic speech. They are not celebrity clones but consistent, high-quality presets designed for clarity in language instruction.
How much does it cost per lesson?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free. You pay only for the text length generated. There are no monthly plans, seats, or minimum spend requirements.
Can I use it for commercial courses?
Yes, you can use the generated audio for commercial language learning courses. The API provides the infrastructure to generate thousands of tracks. Generated audio is returned in the response and not stored by us. Input text is used only to produce the audio and is not used for training.
What happens if generation fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures you only pay for successfully generated audio files. You can retry the request with the same parameters after addressing any errors returned by the API.
Are there limits on character count?
Each request supports up to 4096 characters of input text. For longer lessons, you must split the text into parts and join the resulting audio files. This limit applies per API call, allowing you to manage audio generation efficiently within your workflow.
How do I pay with cryptocurrency?
Top-ups are made via USDT on the TRON network (TRC-20). The minimum top-up is $5. Credits are added automatically within minutes after the transfer. We do not accept cards, PayPal, or subscriptions. Balance does not expire, and no invoices with VAT are issued.
Is there a free trial available?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can issue a new API key at any time if needed.
Do I own the generated audio?
Generated audio is returned in the response and not stored by us. You receive the file directly. Input text is used only to produce the audio and is not used for training. You retain control over the generated files for your courses.
Can I use multiple voices?
Yes, you can choose from 8 presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Each voice has a distinct tone, from warm narrators to energetic promos. You specify the voice parameter in each request to switch between them as needed.
How long does generation take?
Typical speed is roughly real-time, 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. Longer texts take time proportional to their length.
First request
curl
curl https://api.hajee.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.mp3Why Language Creators Choose API Voice-Over
Language learning creators need audio that sounds identical across hundreds of lessons. Manual recording introduces variations in tone and pace that distract learners. Our API ensures every practice track uses the exact same voice parameters, maintaining a consistent educational experience.
Consistency Across Thousands of Lessons
Manual voice-over work often results in subtle shifts in emotion or pacing. By using a synthetic voice, you guarantee that a beginner hears the same clear instruction in lesson one as in lesson fifty. This uniformity helps students focus on the language, not the narrator.
- Uniform voice tone across all video content
- No vocal fatigue or variation between sessions
- Predictable audio quality for learners
Instant Updates for New Vocabulary
When you correct a mispronunciation or add new vocabulary to your curriculum, you do not need to re-record entire video series. Send the updated text to the API, receive the new audio file, and replace the asset in your video editor. This reduces update time from days to minutes.
- Regenerate specific tracks without re-recording
- Fix errors in seconds, not hours
- Adapt content for new lesson editions instantly
Cost-Effective Scaling for Video Content
Hiring voice actors for thousands of short practice phrases incurs significant per-minute costs and scheduling delays. Our API charges $0.01 per 1,000 characters, allowing you to generate unlimited practice tracks for a fraction of the cost. Scale your library from 10 to 10,000 lessons without increasing your production team.
- $0.01 per 1,000 characters
- No hourly voice actor rates
- Predictable costs based on text length
Support for 23 Languages in Education
SonicLingo supports 23 languages, including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, ensuring consistent audio quality across your entire curriculum.
The API detects the language from the script if not explicitly set, defaulting to English for Latin text. For non-English Latin-script text, you should set the language parameter to ensure accurate pronunciation. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Native-Sounding Pronunciation
Our voices are based on licensed recordings from LibriTTS-R and LibriVox, providing clear and natural speech patterns. Each generated file carries an inaudible watermark, marking it as synthetic speech while maintaining high fidelity for educational content.
- Support for 23 specific languages
- Any voice can speak any language
- Licensed LibriTTS-R and LibriVox base
Accents and Regional Variations
Since any voice can speak any supported language, you can maintain a consistent character voice across different language tracks. This allows learners to associate specific characters with specific linguistic patterns, enhancing retention and engagement in your video lessons.
- Consistent character voices across languages
- No regional locking per voice
- Flexible language assignment
Clear Articulation for Beginners
The API processes requests sequentially, ensuring stable output. With a typical speed of roughly 25 characters per second, the audio is generated at a pace suitable for language practice. You can adjust the speed between 0.25 and 4.0 to suit different proficiency levels.
- Adjustable speed (0.25–4.0)
- Clear, synthetic speech
- Suitable for practice listening
Voice Selection for Educational Tone
SonicLingo offers distinct voice presets optimized for educational clarity. Selecting the right voice ensures your language lessons maintain a consistent, professional tone across thousands of tracks.
Sage: Calm Instructional Narration
Sage provides a calm, instructional delivery ideal for grammar explanations and vocabulary drills. Her clear articulation helps learners distinguish subtle phonetic differences without distraction.
Luna: Soft Storytelling Style
Luna’s soft, storytelling approach brings reading passages to life. This preset is particularly effective for narrative-based lessons where emotional context aids memory retention.
Atlas: Neutral News-Style Clarity (or Orion: Deep, Documentary)
Atlas delivers neutral, news-style clarity for objective content. Orion offers a deep, documentary tone for more immersive listening exercises. Both ensure consistent audio quality.
Technical Specs for Video Integration
The API returns audio in MP3, WAV, OPUS, FLAC, or PCM formats, ensuring seamless integration with standard video editing software. Each file includes an inaudible watermark marking it as synthetic speech.
Speed ranges from 0.25 to 4.0, allowing you to adjust playback rate for beginner practice or natural conversation speed. This control helps learners adjust to different pacing levels without re-generating the audio file.
MP3 and WAV Format Support
Choose MP3 for efficient video file sizes or WAV for lossless quality in editing workflows. The API supports OPUS, FLAC, and PCM as well, giving you flexibility based on your production pipeline.
Speed Control for Practice Listening
Adjust the speed parameter between 0.25 and 4.0 to create practice tracks tailored to learner proficiency. Slower speeds aid pronunciation drilling, while faster rates simulate natural conversational flow.
Character Limit Optimization
Each request handles up to 4096 characters. For longer lessons, split text into parts, generate each segment, and join the audio files. This ensures consistent quality and manageable processing times.
How It Works: From Text to Audio
To generate audio for your language lessons, you send a POST request to the speech endpoint with your text and voice selection. The API processes the input and returns the synthesized audio file directly in the response body.
Send Text via JSON Request
Construct a JSON payload containing the text to be spoken, up to 4096 characters, along with your chosen voice preset and audio format. Include your API key in the Authorization header to authenticate the request.
Receive Audio File Instantly
The API returns the audio file immediately in the requested format (mp3, wav, opus, flac, or pcm). Failed requests incur no charge, ensuring you only pay for successfully generated practice tracks.
Download and Embed in Video
Save the returned audio file and integrate it into your video editing timeline. The synthetic speech provides consistent narration for your educational content without the need for manual recording sessions.

Pricing Model for Content Creators
SonicLingo’s API charges $0.01 per 1,000 characters, making it ideal for high-volume language lesson production. Failed requests are free, ensuring you only pay for successful audio generation.
Pay Per Character Usage
Each request processes up to 4,096 characters. At $10 per million characters, costs remain predictable for flashcard sets or dialogue tracks. Spaces and punctuation count toward the limit.
No Monthly Subscription Fees
There are no seats, minimum spends, or recurring plans. You top up via USDT (TRC-20) on the TRON network, with a $5 minimum deposit. Balance never expires, allowing flexible scaling for seasonal content releases.
Free Trial for New Accounts
Signing in with Google grants $0.50 in trial credit, valid for seven days. This allows testing voice clarity and integration before committing funds. Email-based accounts start without trial credit.
Data Privacy and Training Policy
Your input text is used exclusively to produce the audio file and is never used to train our models. This ensures that your specific lesson content remains distinct from the training data used to refine the voice engines.
Generated audio files are returned directly in the response and are not stored on our servers. Only request metadata—such as timestamp, character count, and status—is retained, solely for accurate billing and usage tracking.
Text Not Used for Training Models
The text you submit via the API is processed to generate speech and is not ingested into the model's training dataset. This isolation protects your unique lesson scripts from being used to improve the voice engine for other users.
- Input text is isolated from training data.
- Your lesson scripts remain proprietary.
No Long-Term Audio Storage
Audio files are delivered in the API response and are not permanently stored in our database. Once you receive the file, the server does not retain a copy for long-term archiving, reducing data exposure.
Metadata Kept for Billing Only
We retain minimal metadata including the request time, character count, and status code. This information is used strictly to calculate your usage charges and verify the validity of your API key.
- Timestamp of request.
- Character count processed.
- Request status (success/failed).
Common Use Cases in Language Apps
Language creators leverage the TTS API to produce consistent audio assets at scale. By generating thousands of practice tracks without hiring voice actors, you maintain a uniform listening experience across your entire curriculum.
The API handles character limits up to 4096, allowing you to batch longer reading passages or split shorter phrases. This flexibility ensures that every audio file matches your pedagogical structure precisely.
Flashcard Audio Generation
Generate clear pronunciation audio for vocabulary lists instantly. With support for 23 languages, you can cover diverse learner needs without managing multiple voice contracts.
Each flashcard audio is generated via a simple JSON request. You can adjust the speed between 0.25x and 4.0x to help beginners grasp individual phonemes before moving to natural tempo.
- Support for 23 languages including Arabic, Hindi, and Korean
- Speed control from 0.25x to 4.0x for adjustable difficulty
- Instant generation via REST API for rapid content updates
Dialogue Practice Tracks
Create conversational audio using distinct voices like Felix (energetic, promo) or Milo (friendly, conversational). Assign different voices to different speakers within a single track to enhance listening comprehension.
Use the optional language parameter to ensure correct pronunciation even when the script uses Latin characters for non-English languages, preventing default English guessing errors.
- Distinct voice personalities for speaker differentiation
- Optional language code overrides for accurate pronunciation
- MP3 and WAV formats for easy video editing
Reading Comprehension Audio
Process longer texts by splitting them into 4096-character segments and joining the audio files. This allows you to upload full lessons or articles and receive cohesive audio tracks for your video lessons.
The API processes requests sequentially, so long texts may take a few seconds. However, the cost remains low at $0.01 per 1,000 characters, making it viable for high-volume content libraries.
- Text splitting and joining for long-form content
- Low cost: $0.01 per 1,000 characters
- Metadata kept only for billing, not training
Getting Started with the API
To begin, visit the /get-api-key/ page on hajee.info and sign up using your Google account or an email and password. This creates your independent account for the SonicLingo network.
Create Your Account
Visit the /get-api-key/ page on hajee.info. Sign up via Google or email/password. Your account is specific to this site.
Generate Your API Key
After signing in, your unique tts-... key appears immediately. This single key authenticates all requests. You can issue a new key anytime, which instantly invalidates the previous one.
- Key format:
tts-... - Send via
Authorization: Bearerheader - Revoke old keys instantly upon new issuance
Make Your First Request
Send a POST request to https://api.hajee.info/v1/audio/speech. Include your model, input text, voice, and format in the JSON body. The API returns the audio file directly. Use the OpenAI SDK by setting base_url to https://api.hajee.info/v1.
- Endpoint:
POST /v1/audio/speech - Supports OpenAI SDK with custom
base_url - Returns audio file in response body
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This is critical for beginners who are still developing their auditory processing skills for new sounds and rhythms.
23 languages
Any voice speaks any of these languages.
