Text-to-Speech API for Voice Assistants and Bots

By BotVoice editorial team · Updated 2026-11-18

This page explains how BotVoice helps product teams integrate reliable text-to-speech into voice assistants and chatbots without managing infrastructure. You will find concrete examples of our straightforward API, clear pricing, and standard formats designed to speed up your voice UX development. We focus on practical integration steps rather than hype.

Whether you are building a conversational agent or a customer service bot, you need consistent audio quality and predictable costs. Here you will learn how to select voices, handle language nuances, and understand the technical limits that affect your deployment. Use this guide to set up your first request and start testing immediately.

Text-to-Speech API for Voice Assistants and Bots

Frequently asked questions

What is a TTS API for voice assistants?

A TTS API converts text into audio files via a simple POST request. You send JSON with text, voice, and format, then receive an audio file. This allows product teams to integrate speech into bots without managing infrastructure. The endpoint accepts standard formats like mp3 or wav, making it easy to connect to existing voice assistant workflows.

Which voice is best for a chatbot?

The voice depends on your bot’s personality. Milo offers a friendly, conversational tone suitable for general assistance. For news or updates, Atlas provides a neutral delivery. If your bot handles customer service, Sage’s calm instructional style works well. You can test all eight presets, including Aria, Nova, Luna, Felix, and Orion, to match your brand voice.

How does BotVoice compare to Amazon Polly?

BotVoice offers a straightforward API with clear pricing at $0.01 per 1,000 characters. Unlike many competitors, we do not require complex SSML or custom lexicons for basic use. Our voices are based on licensed recordings, and we support standard formats like mp3 and wav. We provide a simple integration using standard HTTP requests.

Do you support SSML for bots?

No, we do not support SSML. Our API uses simple JSON bodies with fields for text, voice, speed, and language. This simplifies integration for product teams who want to avoid complex markup. If you need specific pronunciation or pauses, you can adjust the text directly or use the speed parameter to control pacing between sentences.

Can I use this API for real-time voice calls?

We do not offer streaming or WebSocket endpoints for real-time partial audio. Requests are processed sequentially, so longer texts may take time proportional to their length. For voice calls, you can generate the full audio file first and then play it. Short phrases generate quickly, but under load, requests may queue before processing begins.

How many languages are supported?

We support 23 languages, including English, Spanish, German, French, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. If you do not specify a language, we guess it from the script, defaulting to English for Latin text. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, or other languages outside this list.

What happens if the API request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry requests or adjust parameters like speed or voice if the initial attempt fails due to temporary issues or invalid input data.

Is the audio quality suitable for voice assistants?

Yes, our voices are based on licensed recordings from LibriTTS-R and LibriVox. Each file includes an inaudible watermark marking it as synthetic. The quality is designed for clear communication in voice assistants and chatbots. You can choose from eight distinct presets to ensure the tone matches your application’s user experience requirements.

Do I need a specific SDK to use this API?

No, you do not need a specific SDK. You can use the official OpenAI SDK by changing the base URL to our API endpoint. Alternatively, use any standard HTTP client to send POST requests. We do not provide our own SDK, mobile SDK, or WordPress plugin, keeping integration simple and flexible for any development environment.

How is the price calculated per character?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free. There are no monthly plans, seats, or minimum spends. You pay only for the characters you successfully generate, making it cost-effective for both small prototypes and large-scale voice assistant deployments.

Can I stream the audio in real-time?

No, we do not support streaming or WebSocket connections. The API returns the complete audio file in the response. For real-time needs, you can generate the file and stream it from your server. Short phrases generate quickly, but the entire file is delivered at once, not in chunks, which simplifies playback logic for bots.

Do you offer voice cloning for my brand?

No, we do not offer custom voice cloning. You choose from eight preset voices based on licensed recordings. These voices are based on licensed recordings, and we do not upload your own voice. If you need a specific brand voice, you must select the preset that matches your desired tone and style.

How do I top up my balance?

Top up using USDT on the TRON network (TRC-20). The minimum amount is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or subscriptions. Your balance does not expire. You can issue a new API key at any time, and the old one stops immediately, ensuring secure access control.

Is there a free trial for voice assistant development?

Yes, signing in with Google gives you $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 test the API, generate audio files, and evaluate voice quality before committing to a top-up via USDT on the TRON network.

First request

curl

curl https://api.playfk9.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.mp3

Why BotVoice for Voice UX?

Sound wave illustration for: Why BotVoice for Voice UX?

BotVoice provides a straightforward API designed for voice assistants and chatbots. By matching the OpenAI speech endpoint structure, you can integrate reliable text-to-speech into your existing workflows using standard SDKs, simply by adjusting the base URL.

Standard OpenAI-Compatible SDK

Standard OpenAI-Compatible SDK

Use the official OpenAI SDKs with minimal code changes. Send a POST request to the speech endpoint and receive an audio file in seconds, keeping your integration simple and predictable.

Low Latency for Conversations

Requests are processed sequentially, typically generating audio at roughly real-time speed (25 characters per second). While short phrases may take a few seconds, this ensures consistent, queue-managed delivery for conversational UX without complex streaming infrastructure.

Transparent Character Pricing

Pay only for what you use: $10 per 1 million characters. Failed requests are free, and there are no monthly fees or hidden costs. This model scales naturally with your bot's usage volume.

Voice Selection for Bots

Sound wave illustration for: Voice Selection for Bots

Choosing the right voice profile is critical for maintaining user engagement in voice assistants and chatbots. BotVoice provides eight distinct presets, each engineered for specific conversational contexts. Selecting a voice that matches your bot’s personality ensures consistent audio identity across interactions.

Warm Narrator (Aria)

Aria is a warm, clear narrator. Her tone remains steady and clear, making complex instructions easy to follow without sounding robotic.

Energetic Promo (Felix)

Felix is energetic and suited for promos. His upbeat delivery captures attention effectively in short bursts, keeping users engaged during brief interjections.

Neutral News (Atlas)

Atlas is neutral and suited for news. His consistent pace and lack of emotional bias ensure information is delivered objectively and clearly.

Supported Languages

Sound wave illustration for: Supported Languages

BotVoice supports 23 languages, ensuring your voice assistant or chatbot can communicate naturally with a global user base. Our API handles language detection automatically for Latin-script texts, defaulting to English if unspecified, though explicitly setting the language code is recommended for non-English content.

This flexibility allows product teams to deploy multilingual bots without managing separate voice models for each region. The synthetic speech remains clear and consistent across supported languages.

English and Spanish

English and Spanish are fully supported with all eight voice presets available. These languages cover a significant portion of global voice assistant interactions and require no special configuration beyond standard API calls.

  • Full voice preset compatibility
  • Automatic language detection for Latin scripts
  • Default English fallback for ambiguous input

European Languages

We support 11 European languages including German, French, Italian, Portuguese, Russian, and Turkish, among others. Each language benefits from the same high-quality synthesis engine, ensuring consistent audio quality regardless of the target market.

  • Arabic, Danish, Dutch, Finnish, Greek, Hebrew, Polish, Swedish
  • Consistent tone across all European presets
  • No additional fees for multi-language support

Asian Languages

Our Asian language support includes Chinese, Japanese, Korean, and Malay. These languages utilize the same text-to-speech engine, allowing your bot to handle diverse linguistic requirements without needing specialized infrastructure or third-party integrations.

  • Chinese, Japanese, Korean, Malay
  • Unified pricing and character limits
  • Standard API integration for all supported scripts

Audio Formats for Integration

Sound wave illustration for: Audio Formats for Integration

BotVoice lets you choose the exact audio container your voice assistant or chatbot requires. Selecting the right format ensures seamless playback across different devices and reduces unnecessary processing steps in your pipeline.

MP3 Compatibility

MP3 is the universal standard for web and mobile playback. Most voice assistants and chat interfaces expect this format, making it the safest default for general user interactions.

WAV for Processing

Use WAV when your backend needs uncompressed audio for further analysis or mixing. Its raw structure preserves full fidelity, ensuring no data loss during intermediate processing steps.

OPUS for Efficiency

OPUS offers superior compression for low-bandwidth environments. It reduces data transfer costs while maintaining high speech quality, ideal for apps with strict data limits.

Pricing Model

Sound wave illustration for: Pricing Model

BotVoice charges $0.01 per 1,000 characters, covering spaces and punctuation. This flat rate applies to all models, with no hidden fees for format conversion or voice selection.

There are no monthly subscriptions or minimum spend requirements. You only pay for what you use, making it easy to budget for voice assistant projects of any scale.

Pay Per Character

The cost is $10 per million characters. This straightforward metric ensures predictable expenses for your bot's audio generation needs.

No Monthly Fees

Unlike traditional services, there are no recurring subscription costs. Start small and scale up as your product grows without locking into long-term contracts.

Failed Requests Free

If synthesis fails, you are not charged. The full amount is returned to your balance, ensuring you only pay for successful audio outputs.

Pricing Model

Technical Limits

Sound wave illustration for: Technical Limits

BotVoice is engineered for predictable voice UX, but your integration must respect specific technical boundaries. Understanding these limits ensures smooth playback in your voice assistants and chatbots without unexpected interruptions or delays during peak usage.

4096 Character Limit

Each API request accepts a maximum of 4096 characters, including spaces and punctuation. For longer scripts, split the text into chunks and concatenate the resulting audio files. This ensures consistent latency and avoids processing timeouts.

  • Max 4096 characters per request
  • Split and join for longer content

Rate Limits

Standard keys are limited to 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. Exceeding this results in a 429 error.

  • 60 requests/minute (standard)
  • 10 requests/minute (new accounts)

Request Queuing

Requests are processed sequentially. Under heavy load, your synthesis job may wait in a queue before generation begins. While typical speed is near real-time, queuing can add slight latency during high-demand periods.

  • Sequential processing model
  • Potential queuing under load

Data Privacy

Sound wave illustration for: Data Privacy

Input text is used exclusively to generate the requested audio file and is not repurposed for training our voice models. Once the synthesis is complete, the generated audio is returned in the response and is not permanently stored on our servers.

This ensures your dialogue scripts and conversation logs remain private, with no risk of your specific utterances being used to improve the base engine without your consent.

No Training Data Use

We do not use your input text to train or refine our TTS engine. Your data is strictly transactional, used only to produce the audio file for your immediate request.

No Audio Storage

Generated audio files are delivered directly in the API response and are not retained in our storage systems. Once your application receives the file, we have no copy of it.

Metadata for Billing

We retain minimal request metadata, including timestamp, character count, and status, solely to calculate accurate charges and verify billing integrity. This data is not used for analytics or marketing.

Getting Started

Sound wave illustration for: Getting Started

Start by creating an account on the /get-api-key/ page. You can sign in instantly using your Google account, which is the fastest way to begin testing the API.

New Google sign-ins receive $0.50 in free trial credit, valid for 7 days. This provides about 50,000 characters to test integration without requiring immediate payment setup.

Google Sign Up

Visit the sign-up page and select the Google login option. This creates an independent account for the site.

Free Trial Credit

Upon successful Google authentication, $0.50 is automatically added to your balance. This credit covers approximately 50,000 characters and expires in 7 days.

  • Valid for 7 days from sign-up
  • Covers ~50,000 characters
  • No credit card required

API Key Generation

After logging in, you can generate your API key. Use this key with the Authorization header in your requests.

  • One active key per account
  • Revoke old keys instantly

Comparison with Traditional Services

Sound wave illustration for: Comparison with Traditional Services

BotVoice offers a straightforward API with clear pricing and standard formats, designed specifically for product teams building voice assistants and chatbots. Unlike legacy providers that require complex configuration of SSML, phoneme dictionaries, and custom pronunciation lexicons, BotVoice lets you send plain text and receive audio immediately.

By removing the need to manage underlying infrastructure, BotVoice allows your team to focus on conversation design rather than server maintenance or volume scaling. You integrate using standard OpenAI-compatible SDKs, ensuring a smooth transition from prototyping to production without deep infrastructure expertise.

Simpler than Amazon Polly

Amazon Polly often requires detailed SSML markup for natural pacing and custom pronunciation rules, adding development overhead. BotVoice simplifies this by guessing the language from the script or accepting an optional ISO code, letting you pass simple strings and receive high-quality audio without manual tagging.

  • Plain text input without mandatory SSML
  • Automatic language detection or optional ISO code
  • No custom pronunciation lexicons required

No Infrastructure Management

Traditional TTS services often require you to provision servers, manage scaling policies, and handle uptime guarantees. BotVoice is a fully managed cloud API. You simply send a POST request with your text and voice selection, and receive an audio file. There are no servers to patch or scale during traffic spikes.

BotVoice handles the heavy lifting. You get consistent performance across 23 languages without worrying about data-center choices or certification compliance, letting your engineering team focus on the bot's logic.

  • Fully managed cloud API
  • No server provisioning or scaling needed
  • No SLA or uptime guarantees to manage

Developer Friendly

Integration takes minutes. Use the official OpenAI SDKs by changing the base_url to https://api.playfk9.com/v1. Pass your API key in the Authorization header, and you are ready to generate speech. The request shape mirrors the industry standard, so most existing code requires minimal changes.

We provide clear documentation and a ready-to-use cURL example. Whether you are building a voice assistant or a chatbot, the straightforward JSON body with model, input, and voice fields makes debugging and testing predictable.

  • OpenAI SDK compatible
  • Standard JSON request body
  • Ready cURL examples provided

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Build conversational flows that feel human to delight users and drive engagement.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. W3C WAI: making audio and video accessible
  3. LibriVox public-domain audiobooks
  4. Node.js documentation
  5. curl documentation
  6. TRON developer hub: TRC-20
  7. Creative Commons Attribution 4.0
  8. IETF RFC 7845: Ogg Opus
  9. openai-node on GitHub
  10. OpenAI API reference: create speech
  11. ISO 639 language codes
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site