Frequently asked questions
What is the character limit per request?
Each API request accepts up to 4096 characters of input text. For longer content, you can split the text into smaller parts and join the resulting audio files. This ensures consistent processing and allows you to handle extensive e-learning modules or training scripts without exceeding the single-request boundary.
Which voices are available?
We offer eight presets: Aria, Nova, Luna, and Sage for female voices; Felix, Milo, Atlas, and Orion for male voices. These range from warm narrators to energetic promo voices. All voices are based on licensed recordings from LibriTTS-R and LibriVox, ensuring consistent quality across your corporate training modules.
Can I use the OpenAI SDK?
Yes, our endpoint matches the OpenAI speech endpoint shape. You can use official OpenAI SDKs by changing the base URL to https://api.yanyabet.net/v1 and providing your VocalGuide API key. This allows seamless integration into your existing development workflows.
What audio formats are supported?
The API supports MP3, WAV, Opus, FLAC, and PCM formats. You can specify the desired response format in your request. This flexibility allows you to choose the optimal balance between file size and quality for your specific e-learning platform or internal corporate training distribution channels.
How fast is the generation?
Generation is roughly real-time, processing about 25 characters of text per second. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. This predictable timing helps you plan your automated training content generation pipelines effectively.
What languages are supported?
We support 23 languages, including English, Spanish, German, French, Chinese, Japanese, and Arabic. Any voice can speak any supported language. If the language is not specified, it is guessed from the script, with Latin text defaulting to English. Ensure you set the language parameter for non-English Latin text.
Does the API support SSML?
No, the API does not support SSML. It accepts plain text input up to 4096 characters. You cannot use phoneme dictionaries or custom pronunciation lexicons. For precise control, you must manage pacing and emphasis by splitting text into smaller segments and adjusting the speed parameter in your requests.
Is there a free trial?
Yes, signing in with Google provides a $0.50 credit, valid for 7 days, allowing approximately 50,000 characters. Accounts created with email and password start without trial credit. This allows HR teams to test voice quality and integration before committing to a paid top-up via USDT on the TRON network.
How much does it cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. There are no monthly plans, seats, or minimum spends. Failed requests are free, with the charge returned in full. This pay-as-you-go model scales directly with your training volume.
What payment methods are accepted?
We accept USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and credits are automatically added within minutes. We do not accept credit cards, PayPal, or issue invoices with VAT. Your balance does not expire, allowing you to top up as needed for ongoing training projects.
Are failed requests charged?
No, failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successfully generated audio files. You can monitor your usage and balance directly on the dashboard, which also provides a ready curl example for quick integration testing.
Is my text used for training?
No, your 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. We keep request metadata, such as time, characters, and status, strictly for billing purposes, ensuring your corporate content remains private and secure.
Do you offer voice cloning?
No, we do not offer custom voice cloning or uploading of your own voice. You must choose from the eight available presets. We do not offer voice design or emotion tags. This ensures consistent, licensed voice quality across all your training modules without the variability of custom cloned voices.
How do I get support?
Support is available via email only. We do not offer a phone number, live chat, or an SLA. There is no uptime guarantee. For technical issues or billing questions, please contact us through the email address provided on our contact page.
First request
curl
curl https://api.yanyabet.net/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 HR teams choose synthetic voices
Corporate training teams require audio that remains consistent across hundreds of modules. Synthetic voices eliminate the variability of human recording sessions, ensuring a uniform brand tone for every e-learning unit regardless of when or where it is produced.
This consistency is critical for global teams needing rapid localization. With support for 23 languages, you can distribute the same instructional content in Arabic, Japanese, or Spanish without hiring new talent for each market.
Consistent brand voice across modules
Human narrators vary in tone, pace, and clarity from day to day. VocalGuide’s eight preset voices, from the calm instructional tone of Sage to the warm narrative style of Aria, provide a stable auditory identity for your curriculum.
- Uniform delivery across all training modules
- No variability between recording sessions
- Professional presets designed for clarity
Rapid localization for global teams
Expanding training to new regions no longer requires coordinating complex recording schedules. The API supports 23 languages, allowing you to generate localized versions of your e-learning content quickly and efficiently.
- Support for 23 languages including Hindi, German, and Portuguese
- Automatic language detection or explicit ISO code setting
- Scalable generation for large content libraries
Cost-effective content updates
Updating training material with human voiceovers is expensive and slow. With VocalGuide, you pay only for characters used. Failed requests are refunded, ensuring you never pay for unusable audio.
- Pay per character at $0.01 per 1,000 characters
- No monthly minimums or subscriptions
- Refunds for failed synthesis requests
How the VocalGuide API works
The VocalGuide API follows a straightforward request-response pattern: you send a JSON payload containing your training script and receive an audio file. Each request accepts up to 4,096 characters, allowing you to process standard e-learning modules efficiently.
Send text, receive audio
Submit your text via POST to the speech endpoint and receive the generated audio in your preferred format. Failed requests are free: if synthesis fails, the charge is returned in full.
- Up to 4,096 characters per request
- Supports mp3, wav, opus, flac, and pcm
OpenAI SDK compatibility
Leverage existing infrastructure by using official OpenAI SDKs. Simply update the base URL to https://api.yanyabet.net/v1 and use your VocalGuide key for immediate integration.
Simple JSON integration
The API accepts standard JSON bodies with fields for model, input, voice, and speed. This standardized structure simplifies development for HR tech teams familiar with common REST patterns.
Voices designed for learning
The VocalGuide API offers eight distinct voice presets, each calibrated for specific training contexts. Whether you need a warm narrator for soft skills or a neutral anchor for technical manuals, the voice selection directly influences learner engagement and information retention.
Every generated file carries an inaudible watermark that marks it as synthetic speech. They carry an inaudible watermark to identify synthetic speech, providing transparency for compliance teams without affecting the listening experience.
Clear instructional tones
Sage provides a calm, instructional voice ideal for step-by-step tutorials and compliance training. Nova offers a bright, upbeat tone suitable for engaging onboarding sequences or interactive quizzes.
These voices maintain clarity at various speeds (0.25–4.0x), allowing trainers to adjust pacing for complex material without losing intelligibility.
- Sage: Calm, instructional voice for tutorials
- Nova: Bright, upbeat tone for onboarding
Warm narrative styles
Aria delivers a warm, clear narration perfect for storytelling-based learning or case studies. Luna adds a soft, storytelling quality, ideal for emotional intelligence modules or leadership development scenarios.
Both voices support natural phrasing and pacing, reducing listener fatigue during longer e-learning sessions.
- Aria: Warm, clear narrator for case studies
- Luna: Soft, storytelling voice for leadership training
Neutral news-style delivery
Atlas provides a neutral, news-style delivery for factual updates, policy changes, or technical documentation. Orion offers a deep, documentary tone, suitable for historical context or in-depth industry analysis.
These voices ensure objective delivery, minimizing bias in corporate communications and training materials.
- Atlas: Neutral, news-style for policies
- Orion: Deep, documentary tone for analysis
Supported languages for training
VocalGuide supports 23 languages, including English, Spanish, French, German, Japanese, and Arabic. This range covers the primary markets for global corporate training, allowing HR teams to produce localized e-learning modules without hiring separate voice talent for each region. Every voice can speak any of these languages, ensuring consistent quality across your curriculum.
We recommend setting the language explicitly for non-English Latin-script text to ensure accurate pronunciation, as the API guesses the language by default based on the script.
23 languages available
Our API handles major global languages, including Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This selection targets the most common needs for multinational training programs.
Automatic language detection
The API guesses the language from the input text if you do not specify one. Latin script defaults to English. For non-English Latin-script content, we recommend explicitly setting the language parameter to avoid mispronunciation.
ISO code support
You can pass an optional ISO language code to the request. This ensures the synthetic voice uses the correct accent and phonetic rules for your target audience, which is critical for clear instructional content.
Free trial for agencies
The VocalGuide free trial gives agencies $0.50 in credit, providing approximately 50,000 characters of synthetic speech. This allows training teams to evaluate voice quality and integration speed without financial commitment. Accounts created via Google sign-in receive this credit automatically upon verification.
The trial credit is valid for 7 days, offering ample time to test multiple voices and formats. There is no credit card required to start, removing friction from the initial evaluation phase. Once the trial expires or credit is exhausted, agencies can top up via USDT to continue production.
$0.50 credit on sign-in
New accounts verified via Google receive $0.50 in instant credit. This amount covers roughly 50,000 characters, sufficient for testing several training modules or voice presets. The credit applies to all request types, allowing teams to assess audio quality across different formats like MP3 or WAV.
Failed requests are refunded, ensuring you only pay for successful audio generation. This trial credit serves as a risk-free environment to validate the API’s performance against your specific e-learning content requirements before committing to a paid plan.
- Covers ~50,000 characters of text
- Applies to all voice models
- Refunds applied to failed requests
7-day validity
The trial credit remains active for 7 days from the moment of account creation. This window is designed to give agencies enough time to integrate the API, generate sample audio, and share results with stakeholders. The balance does not expire after the trial period if you upgrade to a paid account.
If the trial credit is not used within 7 days, it expires. However, the account remains active, allowing for immediate top-up and production start. This structure encourages thorough testing without the pressure of a ticking clock affecting long-term budgeting.
- Valid for 7 days from sign-in
- Balance rolls over if upgraded
- No expiration on paid funds
No credit card required
Signing up for the trial does not require a credit card or payment method on file. This reduces friction for HR teams and training coordinators who want to evaluate the service quickly. You can start generating audio immediately after verifying your identity via Google.
Top-ups are handled via USDT on the TRON network, offering a transparent and direct payment method without bank fees. This crypto-only approach keeps the billing process simple and avoids the complexities of subscription management or invoice processing typical in enterprise software.
- No payment method needed to start
- Instant access via Google sign-in
- Simple USDT top-ups later
Pricing for high-volume training
VocalGuide charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. This model eliminates unused license seats, allowing HR teams to scale voice generation directly alongside curriculum volume.
Pay per character
Every character, including spaces and punctuation, counts toward usage. Failed requests incur no charge, ensuring you only pay for successful audio synthesis. This precision helps agencies budget accurately for large-scale e-learning projects without worrying about hidden fees.
- Rate: $10 per 1 million characters
- Cost: $0.01 per 1,000 characters
- Failed requests are free
No monthly minimums
There are no monthly plans, seats, or minimum spend requirements. You can top up your balance via USDT on the TRON network (TRC-20) with a minimum deposit of $5. Credits do not expire, allowing you to pause and resume generation as training needs dictate.
Fair rate for long texts
Long texts are split into parts of up to 4,096 characters and joined. While synthesis takes roughly real-time duration, the consistent per-character rate ensures that extensive course materials remain cost-effective compared to traditional studio recordings.

Technical reliability
VocalGuide ensures consistent performance for training pipelines through standardized endpoints. The API follows the same request shape as the OpenAI speech endpoint, allowing teams to integrate quickly using the official OpenAI SDK by simply changing the base_url to https://api.yanyabet.net/v1. This compatibility means your existing code structures work immediately, reducing engineering overhead for HR tech teams.
Standardized endpoints
The core endpoint POST https://api.yanyabet.net/v1/audio/speech accepts a JSON body with model, input, voice, response_format, and optional speed or language fields. Supporting endpoints GET /v1/voices and GET /v1/models provide metadata on available voices and formats. Authentication is handled via a single active Bearer token, which can be rotated instantly if needed.
Predictable latency
Generation speed is roughly real-time, producing approximately 25 characters of text per second for long texts. Short phrases may take a few seconds to process. Requests are processed sequentially, so under high load, a request may wait in a queue before synthesis begins. This linear processing ensures stable, predictable output times for batch curriculum generation.
Failed request refunds
If synthesis fails for any reason, the charge is returned in full. You only pay for successful audio generations. This eliminates financial risk when testing new voices or formats during your curriculum development phase.
Data privacy for employee data
VocalGuide processes input text solely for the purpose of generating the requested audio file, ensuring that your training content remains private. Input text is used only to produce the audio and is not used for training.
Text not used for training
Your source text is processed in real-time and discarded after synthesis. It is not retained for future model training or analysis, ensuring that your internal training materials remain exclusive to your organization.
No audio storage
Generated audio files are returned directly in the API response and are not permanently stored on our servers. Once you receive the file, the temporary copy is removed, minimizing the risk of data leakage from our infrastructure.
Metadata only
We retain only request metadata—such as timestamp, character count, and status—for billing and usage verification purposes. This minimal data ensures accurate invoicing without storing the actual content of your training modules.
Get started with your first voiceover
Access your API key directly from the /get-api-key/ dashboard. This unique identifier authenticates your requests to the VocalGuide endpoint.
Generate API key
Sign in via Google or email to retrieve your key instantly. Each account holds one active key; issuing a new one immediately invalidates the previous one.
Use the curl example
Copy the ready-made curl command from your dashboard. It points to https://api.yanyabet.net/v1/audio/speech with your key in the Authorization header.
- Set model to tts-1 or tts-1-hd
- Select a voice like sage or atlas
Test with sample text
Paste up to 4096 characters of training content into the input field. Receive the audio file in mp3, wav, opus, flac, or pcm.
faq
Questions about VocalGuide’s technical limits and account specifics for training workflows.
Direct answers based on current API capabilities and pricing structures.
Can I use the API for internal employee training?
Yes. Input text is used solely to produce audio and is not used for model training. Generated audio is returned in the response and not stored, making it suitable for sensitive corporate content.
What happens if a request fails?
Failed requests are free. If synthesis fails, the charge is returned in full, so you only pay for successful audio generation.
Do you offer custom voice cloning?
No. We provide eight preset voices based on licensed recordings. We do not offer custom voice cloning, voice design, or uploading your own voice.
How do I handle texts longer than 4096 characters?
Split your text into parts of up to 4096 characters per request. Join the resulting audio files using standard media tools or our recommended workflow.
Is there a free trial for agencies?
Yes. Signing in with Google provides $0.50 of credit (about 50,000 characters) valid for 7 days. No credit card is required.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. His impartial tone ensures clarity and neutrality when delivering regulatory information.
23 languages
Any voice speaks any of these languages.
