Text-to-Speech API for E-Commerce Audio Generation

By ShopVoice editorial team · Updated 2026-11-18

This page shows how ShopVoice API helps no-code e-commerce stores turn text into natural-sounding audio for product pages, ads, and updates. You will see how to generate speech files, choose from eight distinct voices, and integrate the service directly into your store’s backend without hiring developers.

We provide a simple cloud API that sends text and returns audio in formats like MP3 or WAV. You can test the technology immediately with a free trial, then scale usage based on your actual needs. Everything is priced per character with no monthly subscriptions, making it easy to add accessible audio content to your online shop.

Text-to-Speech API for E-Commerce Audio Generation

Frequently asked questions

Is the free text to speech software truly free?

You receive $0.50 of free credit when you sign in with Google, valid for 7 days. This allows about 50,000 characters of generation. Accounts created with email and password start without this trial credit. Once the credit is used, you must top up to continue using the service.

How many characters can I convert at once?

Each API request accepts up to 4,096 characters of input text. Spaces and punctuation count toward this limit. If your content exceeds this length, you can split the text into smaller parts, generate audio for each, and join the resulting files together.

Which voices work best for product descriptions?

For product descriptions, Aria offers a warm, clear narrator style, while Felix provides an energetic, promo-focused tone. Nova is bright and upbeat, suitable for lively advertisements. Sage delivers a calm, instructional voice ideal for detailed explanations. All eight voices support 23 languages.

Can I use the generated audio in my online store?

Yes, the API generates audio files you can download and embed directly into your store’s product pages, ads, or updates. The audio files are standard formats like MP3, WAV, OPUS, FLAC, or PCM, making them compatible with most web platforms and e-commerce themes.

What happens if the synthesis fails?

If a synthesis request fails, the charge is returned in full. You are not billed for failed attempts. This ensures you only pay for successfully generated audio files, protecting your balance from errors during the conversion process.

Do I need to install any software?

No software installation is required. The service is a cloud API accessible via standard HTTP requests. You can use the official OpenAI SDKs by changing the base URL, or send simple POST requests with your API key to generate audio from any device.

How do I pay with cryptocurrency?

Top-ups are accepted via USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Funds are credited automatically within minutes after your transfer is confirmed. There are no other payment methods like cards or PayPal available.

Is my customer data safe when I use this API?

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. Request metadata like time and status is kept for billing purposes. We do not claim specific certifications like SOC 2 or HIPAA.

Can I change the speed of the speech?

Yes, you can adjust the speech speed between 0.25 and 4.0. This allows you to make the narration faster for quick updates or slower for clearer pronunciation. The speed parameter is part of the standard request body sent to the API endpoint.

Are there any hidden fees for using the API?

There are no hidden fees. The price is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you successfully generate.

How long does it take to generate audio?

Typical speed is roughly real time, generating about 25 characters of text 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 before processing begins.

Can I use this for YouTube videos about products?

Yes. The voices are based on licensed recordings from LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech, so there is no risk of brand confusion or celebrity imitation. You can safely use these audio files for your YouTube product videos without worrying about unauthorized voice likeness claims.

What if I need more than 4,096 characters?

You must split the text into parts of up to 4,096 characters each. Generate audio for each part separately using multiple API requests. Then, join the resulting audio files together to create a single continuous track for your final content.

Is there a limit on how many files I can create?

There is no limit on the number of files you can create. You are limited by your balance and the rate limit of 60 requests per minute per key. Once you top up, you can generate as many files as your budget allows.

First request

curl

curl https://api.playg9999.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 online stores need audio content

Sound wave illustration for: Why online stores need audio content

Audio content transforms static product pages into engaging experiences. Spoken details help shoppers understand features quickly, while making your store accessible to visually impaired customers. It also allows you to create ready-to-use audio snippets for social media ads without hiring voice actors.

Boost engagement with spoken product details

Boost engagement with spoken product details

Reading long descriptions can be tedious. A natural voice narration keeps visitors on your product page longer, reducing bounce rates and helping them grasp key selling points without scrolling.

Make content accessible for visually impaired shoppers

Accessibility is not just a nice-to-have. Providing audio versions of your product text ensures that customers with visual impairments can browse your catalog independently, improving their overall shopping experience.

Create audio snippets for social media ads

Social platforms favor diverse media types. Generate short audio clips of your product descriptions to use in video ads or stories, giving your brand a unique voice across different channels.

How it works

Sound wave illustration for: How it works

Getting your store’s audio content running is straightforward: send your product descriptions or ad copy to a standard API endpoint, select a voice that matches your brand’s tone, and receive a ready-to-use audio file.

This process fits easily into your existing no-code workflows or backend scripts, allowing you to generate audio snippets for social media ads, product page details, or accessibility features without hiring voice actors.

Send text via API endpoint

Use a simple HTTP POST request to send your text to the endpoint. You can use up to 4,096 characters per request.

If your text is longer, split it into parts and join the resulting audio files. The API processes requests sequentially.

  • Use POST https://api.playg9999.com/v1/audio/speech
  • Send text in the JSON body under the input field
  • Maximum 4,096 characters per request

Choose a voice and language

Select from eight distinct voices, ranging from warm narrators like Aria to energetic promo voices like Felix. Each voice can speak any of the 23 supported languages.

You can also adjust the playback speed between 0.25x and 4.0x to fit your video or ad timing needs. If you don’t specify a language, the system guesses it from the text script.

  • 8 preset voices with distinct tones
  • Supports 23 languages globally
  • Adjustable speed from 0.25x to 4.0x

Receive audio file in your format

Once processed, you receive an audio file in your chosen format: MP3, WAV, OPUS, FLAC, or PCM. The file is ready to download and embed directly into your e-commerce platform or social media campaigns.

Each file includes an inaudible watermark to identify it as synthetic speech. Failed requests are free, so you only pay for successfully generated audio.

Keep in mind that requests are processed one after another, so under heavy load, there may be a short queue time.

  • Formats: MP3, WAV, OPUS, FLAC, PCM
  • Includes inaudible synthetic watermark
  • No charge for failed requests

Voices available for your store

Sound wave illustration for: Voices available for your store

Choosing the right voice shapes how customers perceive your brand. ShopVoice API offers eight distinct presets, each designed for specific e-commerce contexts like product storytelling, promotional ads, or clear instructions.

All voices support 23 languages, allowing you to localize content without hiring new talent. Every generated file includes an inaudible watermark to identify synthetic speech.

Female voices: Aria, Nova, Luna, Sage

Aria provides a warm, clear narrator tone ideal for detailed product descriptions. Nova offers a bright, upbeat style perfect for social media ads and flash sales. Luna delivers a soft, storytelling voice for brand narratives, while Sage ensures calm, instructional clarity for how-to guides.

  • Aria: warm, clear narrator
  • Nova: bright, upbeat
  • Luna: soft, storytelling
  • Sage: calm, instructional

Male voices: Felix, Milo, Atlas, Orion

Felix brings an energetic, promo-ready tone for limited-time offers. Milo sounds friendly and conversational, ideal for customer service updates or welcome messages. Atlas provides a neutral, news-style voice for announcements, while Orion offers a deep, documentary tone for brand heritage stories.

Each voice is based on licensed recordings from LibriVox, ensuring high-quality synthetic speech without celebrity licensing fees.

  • Felix: energetic, promo
  • Milo: friendly, conversational
  • Atlas: neutral, news
  • Orion: deep, documentary

Neutral tones for news-style updates

For stores needing consistent, unbiased audio, Atlas and Sage provide reliable, professional tones. These voices work well for order confirmations, shipping notifications, or policy updates where clarity matters more than personality.

All voices support the same 23 languages, allowing you to maintain a consistent brand voice across international markets.

Languages supported

Sound wave illustration for: Languages supported

ShopVoice API supports 23 languages, allowing your store to reach a global audience. You can specify the language code to ensure correct pronunciation, or let the system guess from the script.

English, Spanish, French, German

These are the most common languages for international e-commerce. If language is not set, Latin-script text defaults to English, so for non-English Latin-script text set language.

Chinese, Japanese, Korean, Arabic

We support major Asian and Middle Eastern markets. The same eight voices work across these languages, providing consistent brand audio whether you are selling in Tokyo or Dubai.

23 languages total for global stores

Beyond the major markets, we support Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Any voice can speak any of these languages.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German
  • Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay
  • Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Pricing for small businesses

Sound wave illustration for: Pricing for small businesses

ShopVoice API charges a flat rate of $0.01 per 1,000 characters, including spaces and punctuation. This predictable cost structure helps you budget for product descriptions, ad scripts, or accessibility audio without worrying about hidden fees or volume tiers.

$0.01 per 1,000 characters

Every character counts toward your total, so a 10,000-character script costs just $0.10. Failed requests are refunded in full, ensuring you only pay for successful audio generation.

No monthly fees or subscriptions

There are no monthly plans, seats, or minimum spend requirements. You simply top up your balance and use it as needed, making it ideal for stores with fluctuating content needs.

Pay with USDT cryptocurrency

We accept USDT on the TRON network (TRC-20) with a $5 minimum top-up. Payments are credited automatically within minutes, with no invoices or VAT to manage.

Pricing for small businesses

Technical details

Sound wave illustration for: Technical details

Our API mirrors the standard OpenAI speech endpoint structure, meaning you can reuse existing OpenAI SDKs by simply pointing your base URL to https://api.playg9999.com/v1. This compatibility allows for quick integration into your store’s backend without learning a new protocol.

You can choose from MP3, WAV, OPUS, FLAC, or PCM output formats. The API processes requests sequentially, so under heavy load, a synthesis job may wait briefly in a queue before being handled.

Standard OpenAI-compatible API

The endpoint accepts standard JSON bodies with fields like model, input, voice, and speed. Because the request shape matches the OpenAI speech endpoint, you only need to update your base_url and use your ShopVoice API key for authentication.

  • POST /v1/audio/speech endpoint
  • Compatible with official OpenAI SDKs
  • Standard JSON request body

Supports MP3, WAV, OPUS, FLAC formats

Specify your preferred audio format in the response_format field. Whether you need lightweight MP3 for web players or lossless FLAC for high-fidelity product demos, the API returns the file directly in the response.

  • MP3, WAV, OPUS, FLAC supported
  • PCM format available
  • Direct file download in response

Rate limit of 60 requests per minute

Each API key allows up to 60 requests per minute once funded. New accounts start with a limit of 10 requests per minute until the first top-up is processed.

  • 60 requests/minute per key
  • 10 requests/minute for new accounts
  • Limits reset automatically

Data privacy and quality

Sound wave illustration for: Data privacy and quality

When you send product descriptions or ad copy to ShopVoice API, that text is processed solely to generate the audio file. Input text is used only to produce the audio and is not used for training.

After the audio is generated and returned to your store, we do not store the audio files permanently. Only request metadata—such as timestamp, character count, and status—is kept briefly to handle billing accurately.

Input text is not used for training

Your product details, marketing copy, or store updates are used exclusively for the immediate synthesis of the audio file. Once the audio is generated, the input text is not retained for model training purposes, keeping your content private.

Generated audio is not stored permanently

We do not keep copies of the audio files you generate. They are returned in the response and not stored long-term. This minimizes data exposure and ensures your audio assets remain under your control.

Only essential request metadata, including time, character count, and status, is retained for billing purposes. This allows us to accurately track your usage and charges without storing the actual audio content.

Watermarked synthetic speech files

Every audio file generated by ShopVoice API contains an inaudible watermark. This marks the file as synthetic speech, which can be useful for transparency in advertising or content distribution.

Every generated file carries an inaudible watermark that marks it as synthetic speech.

Getting started

Sound wave illustration for: Getting started

To get started with ShopVoice API, create an account on our /get-api-key/ page using your Google sign-in for an instant free trial. You will receive $0.50 in credit, enough to generate about 50,000 characters of audio over seven days. This allows you to test voices without entering payment details immediately.

Once registered, your API key is available instantly. You can start generating speech for product descriptions or ad copy right away. The page shows the key, balance, trial, characters left, usage and a ready curl example.

Sign up with Google for free trial credit

Click the sign-up button and select Google authentication. Your account is created immediately, and $0.50 in trial credit is applied to your balance. This credit is valid for 7 days, giving you ample time to evaluate the 8 voice presets across different languages.

Generate your API key instantly

After logging in, navigate to the dashboard to view your unique API key. One active key is issued per account. You can generate a new key at any time if needed, and the previous key stops working immediately. The dashboard also displays your remaining characters and usage history.

Use our curl example to test immediately

The dashboard provides a ready-to-use curl command. Replace the placeholder key with yours and send a POST request to the speech endpoint. You will receive an audio file in seconds. This simple workflow lets you integrate the API into your e-commerce store’s backend or test it locally before full deployment.

Common questions

Sound wave illustration for: Common questions

Quick answers to common questions about using ShopVoice API for your e-commerce store.

Is this software really free to try?

Yes. Signing in with Google gives you $0.50 of credit, which covers about 50,000 characters. This trial lasts 7 days, letting you test voices and integrations without paying upfront.

Can I use the audio for commercial ads?

Absolutely. You can use the generated audio for product pages, social media ads, and store updates. Every file includes an inaudible watermark to mark it as synthetic speech.

Do I need technical skills to use it?

The API follows the standard OpenAI format, so you can use existing tools. For no-code users, you can integrate the endpoint via your store’s backend or simple scripts.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This voice is ideal for blog posts, FAQ sections, or customer updates where a warm, approachable tone builds trust with your shoppers.

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. Creative Commons Attribution 4.0
  3. Python documentation
  4. openai-python on GitHub
  5. FFmpeg documentation
  6. curl documentation
  7. Node.js documentation
  8. IETF RFC 7845: Ogg Opus
  9. W3C WAI: making audio and video accessible
  10. ISO 639 language codes
  11. LibriVox public-domain audiobooks
  12. OpenAI API reference: create speech

More on this site