Frequently asked questions
What is a voice over creator API?
It is a cloud text-to-speech API where you send text and receive an audio file. You can use the official OpenAI SDKs by changing the base URL to https://api.playtk8.com/v1. The endpoint POST /v1/audio/speech accepts JSON bodies with model, input, voice, and other parameters, allowing seamless integration into your existing workflows.
How does AI voice generation compare to human voice actors?
AI generates audio in minutes rather than days, with typical speed of roughly real time for long texts. Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. Every file carries an inaudible watermark marking it as synthetic speech, ensuring clear distinction from human recordings without hiring talent.
Which voices are best for corporate training?
For corporate training, Sage offers a calm, instructional tone, while Milo provides a friendly, conversational style. Aria serves as a warm, clear narrator, and Felix brings an energetic, promo-focused energy. These eight presets cover various needs, allowing you to select the perfect voice for your specific e-learning modules or internal communications.
Can the AI handle technical HR terminology?
Yes, the API processes any text up to 4096 characters per request. While it does not support custom pronunciation lexicons or phoneme dictionaries, the models are trained on diverse datasets. If specific terms need emphasis, you can adjust the speed between 0.25 and 4.0 to control the delivery pace of your technical content.
What languages are supported for global training?
We support 23 languages: 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. If the language is not set, it is guessed, so specify it for non-English Latin-script text.
How long does it take to generate audio?
Typical speed is roughly real time for long texts, about 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts are split into parts of up to 4096 characters and joined automatically.
Do I need technical skills to use the API?
You can use the official OpenAI SDKs by changing the base URL to https://api.playtk8.com/v1. Alternatively, use plain HTTP with a POST request to /v1/audio/speech. The page at /get-api-key/ provides a ready curl example, making it easy for developers to integrate quickly without needing deep technical expertise.
Is there a free trial available?
Yes, signing in with Google gives you $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, with a minimum of $5, credited automatically within minutes.
How are characters counted in the API?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. This transparent counting ensures you only pay for successful audio generation, with no hidden fees for metadata or processing time.
Can I change voices mid-project?
Yes, you can specify any of the 8 voice presets in each request. There are no restrictions on switching voices between different API calls. This flexibility allows you to maintain consistent branding while varying tones for different sections of your training modules or internal communications without needing to regenerate previous audio.
What formats are supported for audio files?
You can choose from mp3, wav, opus, flac, and pcm formats. These options ensure compatibility with various learning management systems and playback devices. Simply include the desired response_format in your JSON body when calling the POST /v1/audio/speech endpoint to receive the audio file in your preferred standard format.
How secure is the API key?
Each account has one active key, authenticated via the Authorization: Bearer header. You can issue a new key at any time, and the old one stops immediately. Request metadata is kept for billing, but input text is used only for production and not stored, ensuring your training content remains private.
Do I need to attribute the voices?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Each file carries an inaudible watermark marking it as synthetic speech for clear identification.
What happens if a request fails?
If synthesis fails, the charge is returned in full, making failed requests free. You can retry with adjusted parameters like speed or voice. The API returns an error status, allowing you to handle the failure in your application logic without incurring any cost for the unsuccessful audio generation attempt.
First request
curl
curl https://api.playtk8.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 HR Agencies Choose AI Voice Generation
HR agencies and training departments face the challenge of producing high-quality voice-overs for e-learning modules and internal communications at scale. Traditional methods require hiring talent, scheduling sessions, and waiting days for delivery. Clarispeak’s API lets you turn any text into professional audio in minutes, not days.
Scale training content across departments
Generate voice-overs for onboarding, compliance, and product training instantly. Whether you need one module or hundreds, our API processes requests efficiently, allowing you to distribute consistent audio content to diverse teams without logistical bottlenecks.
Reduce voice talent costs
By switching to AI generation, agencies significantly lower production expenses. With pricing at $0.01 per 1,000 characters, you pay only for what you use. There are no monthly minimums, no seats, and no hidden fees, making it economical for high-volume training needs.
Maintain consistent brand voice
Ensure every piece of training content sounds uniform across your organization. Choose from eight distinct voices, such as Aria for clear narration or Milo for conversational onboarding. This consistency strengthens your brand identity without relying on varying human performers.
Professional Voices for Professional Content
Clarispeak offers eight distinct voice presets designed for professional corporate environments. Each voice is derived from licensed recordings, ensuring high-quality narration that maintains consistency across your e-learning modules and internal communications without the variability of human talent.
Our voices handle everything from strict compliance scripts to friendly onboarding guides. With support for 23 languages and automatic detection, you can deploy scalable content for global teams while maintaining a cohesive brand tone.
Aria: Clear narrator for compliance
Aria provides a warm, clear narration style ideal for compliance training and educational content. Her steady delivery ensures that complex regulatory information is absorbed clearly by learners, reducing cognitive load and improving retention rates in dense textual modules.
Atlas: Neutral tone for news updates
Atlas delivers a neutral, professional tone perfect for corporate news updates and policy announcements. His consistent pacing and lack of emotional bias make him an excellent choice for delivering factual information where clarity and neutrality are prioritized over personality.
Milo: Conversational for onboarding
Milo brings a friendly, conversational tone to onboarding materials and employee guides. His approachable style helps new hires feel welcomed and engaged, transforming dry procedural texts into engaging audio experiences that encourage active learning and better information retention.
Support for Global Teams
Global teams require clear, consistent communication across borders. Clarispeak supports 23 languages, enabling HR agencies to distribute training content to diverse employee bases without hiring local voice talent for every region.
23 languages supported
Our API handles Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Every voice preset can speak any of these languages, ensuring consistent quality across your entire global workforce.
Accents for diverse audiences
Select from eight distinct voice presets to match your brand’s tone, regardless of language. Whether you need the warm clarity of Aria for compliance modules or the neutral authority of Atlas for news updates, each voice delivers professional-grade audio suitable for corporate environments.
Language detection technology
The API automatically detects the language based on the script’s script (e.g., Latin script defaults to English). For non-English Latin-script text, simply set the optional language field to ensure accurate pronunciation. Languages like Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Simple Integration for Dev Teams
Our API endpoint mirrors the familiar OpenAI structure, allowing your development team to integrate voice generation without learning a new system. Simply update your base URL to https://api.playtk8.com/v1 and use your existing OpenAI SDKs. This compatibility means you can leverage standard libraries and tools you already know, reducing onboarding time for your engineers.
The integration is straightforward: send a POST request with your JSON payload, and receive an audio file in return. You authenticate with a single Bearer token, ensuring secure access for your team. This simplicity lets developers focus on building features rather than wrestling with complex API quirks.
OpenAI-compatible endpoint
The endpoint https://api.playtk8.com/v1 accepts standard requests, making it easy to swap in Clarispeak as your TTS engine. Your team can use the same code structure they are already familiar with, ensuring a smooth transition for existing projects.
- Standard
POST /v1/audio/speechendpoint - Compatible with official OpenAI SDKs
- Easy base URL configuration
REST API with JSON body
Send your text, voice selection, and language preferences in a simple JSON body. The API handles the synthesis and returns the audio data directly. Fields like model, input, and voice are clearly defined, making integration predictable and reliable for your automated workflows.
- JSON request body
- Standard HTTP methods
- Clear field definitions
Multiple audio formats
Choose from mp3, wav, opus, flac, or pcm based on your platform's needs. Whether you need compressed files for web delivery or uncompressed audio for high-quality e-learning modules, the API supports your requirements. This flexibility ensures compatibility with any learning management system or video editor.
- mp3, wav, opus, flac, pcm
- Format selection via
response_format - Optimized for various platforms
Pricing Built for Agencies
Clarispeak’s pricing model is designed for agencies that need predictable costs without overpaying for unused capacity. You only pay for what you generate, making it easy to budget for large-scale training projects.
With no monthly minimums or subscription fees, your costs scale directly with your output. This structure eliminates the risk of paying for idle capacity when your training calendar is light.
Pay per character used
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful audio generation.
- $0.01 per 1,000 characters
No monthly minimums
There are no monthly plans, no seats, and no minimum spend. You can use the API for a single onboarding script or for a global rollout of compliance modules without penalty.
Transparent billing
Balance never expires, and you can top up with USDT (TRC-20) starting at $5. No invoices with VAT or hidden fees. View your exact usage, character counts, and balance directly in your dashboard.

Technical Reliability
Clarispeak’s infrastructure ensures your training content is generated reliably, with minimal downtime for HR teams rolling out global modules. Our system processes requests sequentially, maintaining stability even during peak usage periods.
Reliable infrastructure
We prioritize consistent delivery for your voice-over needs. While we don’t offer a formal SLA, our architecture is designed for steady performance, ensuring your e-learning projects proceed without unexpected interruptions.
Secure data handling
Your input text is used solely to produce the audio file and is not used for training models. Generated audio is returned in the response and not stored on our servers, keeping your proprietary training scripts private.
- Input text is not used for training
- Generated audio is not stored
- Request metadata kept only for billing
Fast processing speeds
Typical synthesis speed is roughly real-time (25 characters per second). Short phrases take a few seconds to generate, while longer texts are split into parts and joined seamlessly. Requests are processed sequentially, so under heavy load, a request may wait in a queue.
- ~25 characters per second generation speed
- Sequential processing with queueing under load
Use Cases for HR Professionals
Clarispeak transforms static text into engaging audio for e-learning modules, ensuring consistent narration across hundreds of courses without scheduling voice talent. HR teams can rapidly localize training content for global teams using our 23 supported languages.
Generate professional audio for video training scripts and internal announcements in minutes. Whether narrating compliance updates or onboarding guides, our API delivers clear, natural-sounding speech that maintains your company’s brand voice at scale.
E-learning module narration
Turn course outlines into ready-to-use audio files. Select a voice like Aria for clear instruction or Luna for storytelling, then generate MP3 or WAV files directly via API. This eliminates the back-and-forth of booking studio time.
- Support for 23 languages including English, Spanish, and German
- Choose from 8 distinct voice presets
- Export in MP3, WAV, or FLAC formats
Video training scripts
Synchronize generated audio with visual training materials seamlessly. Use the API to produce high-quality voice-overs for digital learning platforms, ensuring every module sounds professional and consistent without hiring multiple voice actors.
- Adjustable speed from 0.25x to 4.0x
- Adjustable speed from 0.25x to 4.0x
Internal announcement audio
Broadcast company updates instantly using voices like Atlas for neutral news or Milo for conversational tones. Distribute audio announcements via email or intranet, keeping employees engaged with clear, human-like speech without scheduling studio sessions.
- Ideal for compliance and policy updates
- Fast turnaround for urgent internal comms
Get Started in Minutes
Generate your secure API key instantly via Google sign-in or email on the /get-api-key/ page. You receive a Bearer token ready for immediate use with any OpenAI-compatible SDK or simple HTTP request.
Create your API key
Navigate to the dashboard to view your active key and balance. The system provides a ready-to-use cURL example, allowing your developers to test the endpoint with a single command.
- Instant Google or email registration
- Immediate access to API documentation
- OpenAI SDK compatibility
Upload your script
Send your text via POST request to the /v1/audio/speech endpoint. Select from eight professional voices like Aria or Atlas, and specify the desired language and audio format.
- Support for texts up to 4096 characters
- Automatic language detection
- Multiple format options
Download your audio
Receive your synthesized audio file directly in the response. Choose from MP3, WAV, Opus, FLAC, or PCM formats to suit your learning management system or video editing workflow.
Frequently Asked Questions
We answer the most common questions from HR teams integrating Clarispeak into their training workflows.
Is the audio royalty-free?
Yes. Generated audio is yours to use internally. Each file carries an inaudible synthetic watermark, but you retain full usage rights for your e-learning modules and comms without additional fees.
Can I use multiple voices?
Absolutely. You can switch between all 8 presets (like Aria or Atlas) within a single project or across different modules. This allows you to distinguish between narrator, character, or news update audio.
How do I handle long scripts?
Split your text into parts of up to 4,096 characters. Synthesize each part individually, then join the resulting audio files. This ensures consistent quality and avoids request limits.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This ensures that your training materials sound professional and engaging, regardless of the target demographic.
23 languages
Any voice speaks any of these languages.
