Frequently asked questions
What makes Aria different from Nova?
Aria is described as a warm, clear narrator, while Nova is bright and upbeat. Both are female voices available in the API. You can test both via the /v1/voices endpoint to see which tone fits your chatbot’s personality best. The choice depends on whether you prefer a calm narration style or an energetic, upbeat delivery for your users.
Can I use Luna for a calming meditation app?
Yes, Luna is designed as a soft, storytelling voice, making it suitable for calming applications. It supports 23 languages, including English. You can generate audio using the tts-1 model with Luna as the voice parameter. It is based on licensed recordings from LibriVox and does not require custom cloning.
Does Sage work well for instructional videos?
Sage is described as calm and instructional, making it ideal for educational content or instructions. It supports 23 languages and can be used with the tts-1 or tts-1-hd models. You can set the speed between 0.25 and 4.0 to adjust the pacing for your video, ensuring clear and understandable delivery for your audience.
How many languages do the female voices support?
All eight voices, including the female options Aria, Nova, Luna, and Sage, support 23 languages. These include 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.
Is the API compatible with OpenAI SDKs?
Yes, the API uses the same request shape as the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.tam300.info/v1 and providing your API key. This allows you to integrate VoicePilot into existing workflows with minimal code changes, leveraging familiar tools for text-to-speech generation.
What is the character limit per request?
Each request supports up to 4096 characters of input text. If your text exceeds this limit, you should split it into parts of up to 4096 characters and join the resulting audio files. This ensures efficient processing and maintains audio quality across longer texts without overwhelming the API endpoint.
Are voices cloned from real people?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), which includes readings from LibriVox public-domain audiobooks. Custom voice cloning is not offered. Each generated file also contains an inaudible watermark to mark it as synthetic speech, ensuring transparency about the audio's origin.
Do I get a refund if a request fails?
Yes, if synthesis fails, the charge is returned in full. You only pay for successful audio generation. This applies to all requests, regardless of the model or voice used. Failed requests do not consume your character limit or balance, ensuring you are only charged for usable audio output.
How fast is the audio generation?
Generation is roughly real-time on long texts, processing about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. The rate limit is 60 requests per minute per key (10 per minute before the first top-up).
Can I mix male and female voices in one project?
Yes, you can use any of the eight voices, including male options like Felix, Milo, Atlas, and Orion, alongside female voices. Each voice is a separate preset you can select in your API requests. This flexibility allows you to create diverse audio projects by switching voices as needed for different sections or characters.
Is there a limit to how many characters I can process?
There is no hard limit on total characters processed, but each API request is capped at 4096 characters. For longer texts, you must split the input into chunks and join the audio files. This approach allows you to generate unlimited audio content, limited only by your account balance and rate limits.
Do I need to pay for every request?
You pay $0.01 per 1,000 characters for successful requests. Failed requests are free. The price is $10 per 1 million characters. You can start with a free trial credit of $0.50 if you sign in with Google; accounts created with email and password start without trial credit. Otherwise, you top up with USDT on the TRON network, with no minimum spend.
What formats are available for output?
The API supports mp3, wav, opus, flac, and pcm formats. You can specify the desired format in the response_format field of your request. This allows you to choose the best format for your application’s needs, whether you prioritize file size, quality, or compatibility with specific audio players or systems.
How do I track my API usage?
Track your API usage directly on the /get-api-key/ page, which displays your balance, trial status, characters left, and usage history. Request metadata—including time, character count, and status—is retained for billing purposes. This built-in dashboard allows you to monitor consumption and manage your account effectively without needing external tools or third-party integrations.
First request
curl
curl https://api.tam300.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 Voice Matters in Conversational AI
In conversational AI, tone defines trust. Users forgive minor latency but reject robotic monotony. Our eight licensed voices provide distinct tonal profiles, allowing product teams to align the assistant’s personality with brand values from day one.
Building Trust Through Tone
A warm, clear narrator like Aria creates immediate rapport, while Sage’s instructional style reduces confusion during complex tasks. Consistency in vocal identity prevents the 'uncanny valley' effect, making interactions feel intentional rather than generic.
- Distinct tonal profiles for every use case
- Licensed recordings ensure legal clarity and quality
- Consistent branding across all touchpoints
Consistency Across Languages
Our API supports 23 languages with any voice speaking any language. This allows a single voice identity to remain recognizable whether the user speaks English, Japanese, or Swahili, simplifying localization strategies for global teams.
- 23 languages supported with any voice
- Automatic detection or explicit language setting
- No need for multiple voice hires per region
Reducing User Fatigue with Natural Pacing
Robotic pacing causes cognitive load. Our synthesis engine generates audio at roughly real-time speed, with natural pauses and inflection. This reduces listener fatigue during longer interactions, such as customer support calls or audiobook narration.
- Natural rhythm reduces cognitive load
- Real-time generation speeds for long texts
- Optimized for extended listening sessions
Our Female Voice Catalog
VoicePilot offers four distinct female voices, each engineered for specific conversational contexts in chatbots and voice assistants. These presets are based on licensed recordings from LibriTTS-R and LibriVox, ensuring high-quality, natural-sounding output without the need for custom voice cloning, which is not offered.
Each voice supports all 23 available languages, allowing your product team to maintain consistent tone across global deployments. You can select the preset that best matches your brand's personality, from warm narration to bright energy, and test them via our API.
Aria: Warm and Clear Narrator
Aria delivers a warm, clear tone ideal for general narration or welcoming users in a chatbot interface. Her clarity ensures high comprehension rates, making her suitable for long-form interactions or detailed instructions.
- Best for: General purpose chatbots, onboarding flows
- Style: Warm, clear narrator
Nova: Bright and Upbeat Energy
Nova brings a bright, upbeat energy that works well for promotional content or engaging user prompts. Her tone is energetic yet natural, helping to keep users engaged during brief interactions or feature highlights.
- Best for: Promotional bots, engagement prompts
- Style: Bright, upbeat energy
Luna: Soft Storytelling Tone
Luna offers a soft, storytelling tone perfect for audiobooks, interactive fiction, or calming customer support experiences. Her gentle delivery reduces user fatigue during longer listening sessions, providing a soothing auditory experience.
- Best for: Audiobooks, calming support
- Style: Soft, storytelling tone
Sage: Calm Instructional Style
Sage provides a calm, instructional style ideal for technical guides, step-by-step instructions, or educational bots. Her steady pace and neutral warmth help users focus on information without distraction, ensuring clarity in complex tasks.
- Best for: Technical guides, educational bots
- Style: Calm, instructional style
Technical Integration for Developers
VoicePilot’s API endpoint mirrors the OpenAI speech structure, allowing you to use official OpenAI SDKs by simply changing the base_url to https://api.tam300.info/v1. This minimizes code changes for teams already familiar with standard TTS integrations, ensuring a smooth transition from development to production without needing our own SDK.
OpenAI SDK Compatibility
You can leverage existing OpenAI SDKs for Python or Node.js by pointing them to our base URL. Authentication uses a standard Bearer token, ensuring seamless compatibility with your current infrastructure. This approach lets you swap the endpoint without rewriting your integration logic, saving development time for large teams.
Simple JSON API Structure
Send a POST request to /v1/audio/speech with a JSON body containing model, input, voice, and optional speed or language fields. The API returns the audio file directly, supporting texts up to 4096 characters per request. For longer scripts, split the text and join the resulting audio files programmatically.
Support for Multiple Audio Formats
Choose from mp3, wav, opus, flac, or pcm via the response_format field. Selecting opus or mp3 reduces bandwidth for chatbot deployments, while wav and flac provide lossless quality for voice assistants requiring high fidelity. This flexibility lets you optimize for either network efficiency or audio clarity based on your specific use case.
Language Support for Global Teams
VoicePilot supports 23 languages, enabling your chatbots and voice assistants to communicate naturally with global users. The system supports 23 languages including English, Spanish, German, Japanese, and Arabic, ensuring broad coverage for international deployments.
23 Languages Supported
Our engine 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. Each voice can speak any of these languages, allowing you to maintain a consistent character across your entire user base.
- English, Spanish, German, French, Italian, Portuguese, Russian, Chinese, Japanese, Korean, Arabic, Hindi, Turkish, Dutch, Swedish, Danish, Norwegian, Finnish, Polish, Greek, Hebrew, Swahili, Malay
Automatic Language Detection
If you do not specify a language, the API guesses it from the text script. Latin script text defaults to English, which works for many cases but may misinterpret other Latin-based languages.
Consistent Voice Across Regions
For non-English Latin-script text, set the language field explicitly to ensure accurate pronunciation. This ensures that a user in France hears the same voice tone as a user in Canada, regardless of the input text's origin.
Pricing for High-Volume Teams
VoicePilot charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward this limit. Failed requests are free, ensuring you only pay for successful synthesis. Balance never expires, and there are no monthly plans, seats, or minimum spend requirements.
Start with a free $0.50 trial (valid 7 days) when signing in with Google. Top-ups via USDT on the TRON network (TRC-20) are processed automatically within minutes. Payments are straightforward: no cards, no PayPal, no invoices with VAT.
Pay Per Character Model
Our pricing is simple: $10 per 1 million characters. This equals $0.01 per 1,000 characters, with spaces and punctuation counted. If synthesis fails, the charge is returned in full. There are no monthly plans, no seats, and no minimum spend.
- $10 per 1 million characters
- $0.01 per 1,000 characters (incl. spaces)
- Failed requests are free
- Balance does not expire
Free Trial for Evaluation
Sign in with Google to receive $0.50 of credit, covering approximately 50,000 characters for 7 days. Accounts created with email and password start without trial credit. This allows teams to evaluate voice quality and integration ease before committing to larger volumes.
Transparent USDT Payments
Top-up via USDT on the TRON network (TRC-20) only. Minimum top-up is $5, credited automatically within minutes after transfer. We do not accept cards, PayPal, or subscriptions. Support is by email only; there is no live chat or phone support.
- USDT on TRON (TRC-20) only
- Minimum $5 top-up
- No cards or PayPal
- No VAT invoices

Performance and Reliability
VoicePilot delivers audio at roughly real-time speed, generating approximately 25 characters of text per second. While short phrases require a few seconds, longer texts process efficiently, making it suitable for high-volume deployments where consistent throughput matters.
Real-Time Generation Speed
Requests are processed sequentially, ensuring predictable output. For texts exceeding 4096 characters, you must split the input and join the resulting audio files, maintaining narrative flow without manual intervention.
- ~25 characters generated per second
- Automatic splitting for long texts
- Predictable sequential processing
Queue Management Under Load
During high traffic, requests may wait in a queue before synthesis begins. This ensures every request is handled without data loss or format errors, though generation time may increase slightly compared to idle periods.
No Hidden Fees or Surprises
Failed requests are fully refunded, so you only pay for successful synthesis. With a flat rate of $10 per million characters and no monthly plans or minimum spends, your costs scale directly with your usage volume.
- Full refund for failed requests
- No monthly plans or subscriptions
- Transparent character-based billing
Data Privacy and Licensing
VoicePilot ensures your input text is used solely for audio synthesis and is never retained for model training. We store only the necessary metadata—time, character count, and status—for accurate billing and usage tracking, keeping your conversational data private and secure.
No Training on Your Data
Your text inputs are processed in real-time to generate the audio file and are not stored long-term. Only request metadata is kept for billing purposes, ensuring your conversational patterns remain proprietary to your organization.
Licensed Voice Recordings
Our eight voice presets are derived from high-quality recordings licensed under CC BY 4.0 from LibriTTS-R, with additional source material from LibriVox public-domain audiobook readings. This ensures clear legal standing for commercial use without complex royalty negotiations.
Synthetic Watermarking
Every generated audio file contains an inaudible digital watermark that explicitly marks the content as synthetic speech. This provides an additional layer of transparency and traceability for your voice assistant outputs, helping users distinguish AI-generated audio from human recordings.
Common Use Cases
VoicePilot’s 8 licensed voices deliver consistent, natural-sounding responses across 23 languages, ensuring your chatbots and IVR systems maintain a professional tone regardless of user location.
With clear pacing and distinct character traits, our API reduces user fatigue during long interactions while supporting high-volume deployments with straightforward JSON integration.
Customer Support Bots
Deploy agents like Felix for energetic, prompt-driven interactions or Sage for calm, instructional guidance. The API’s 4096-character limit per request allows for comprehensive, context-rich responses without splitting audio unnecessarily.
Use Luna’s soft storytelling tone for empathetic handling of customer issues, ensuring users feel heard. With automatic language detection, your bot can switch between languages, though Latin script defaults to English.
- Support for 23 languages with automatic detection
- Distinct personalities for varied customer scenarios
- No custom voice cloning required
Interactive Voice Response
Atlas provides a neutral, news-style delivery ideal for standard IVR menus, while Orion’s deep, documentary tone adds authority to system prompts. Both voices ensure clarity in noisy environments.
Generate audio files in MP3, WAV, or Opus formats for optimal compatibility with existing telephony infrastructure. The API’s straightforward JSON structure integrates easily with your current IVR logic.
- Multiple audio format support
- Neutral and authoritative voice options
- Seamless telephony integration
Audiobook Narration
Luna and Aria are optimized for long-form content, with Aria offering a warm, clear narration style. Users can adjust speed between 0.25x and 4.0x to suit different listening preferences.
Each generated file includes an inaudible synthetic watermark, marking it as AI-generated content. Since input text is not used for training, your unique scripts remain private and secure.
- Adjustable playback speed (0.25x–4.0x)
- Inaudible synthetic watermarking
- No data training on input text
Getting Started
Start by creating your VoicePilot account at /get-api-key/. You can sign in instantly with Google or use a standard email and password. This step initializes your workspace and prepares your billing profile.
Create Your Account
Visit the registration page and choose your preferred sign-in method. Google sign-ins automatically include a $0.50 trial credit valid for seven days, giving you immediate capacity to test the service.
- Supports Google OAuth or email/password registration
- Google sign-ins receive a $0.50 trial credit
- Accounts are specific to tam300.info
Generate Your API Key
Once logged in, navigate to the dashboard to view your unique API key. This key authenticates your requests to the endpoint. You can issue a new key at any time, which immediately invalidates the previous one.
- One active key per account
- New keys instantly revoke the old one
- Key format starts with tts-
Run Your First Test
Use the provided curl example on your dashboard to send a test request. Point your OpenAI SDK base_url to https://api.tam300.info/v1 and send a simple text input to receive an audio file.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your voice is often the first touchpoint for users, so it must align with your product’s personality while remaining intelligible across diverse contexts.
23 languages
Any voice speaks any of these languages.
