Frequently asked questions
Which voice is best for product descriptions?
Aria offers a warm, clear narrator style suitable for product descriptions. Sage provides a calm, instructional tone suitable for detailed specifications. Felix delivers an energetic, promo-focused voice for promotional content. You can test these presets to see which best matches your brand’s voice without extra cost.
Can I mix male and female voices?
The API generates one audio file per request using a single voice preset. To mix voices, you must send separate requests for each text segment and join the resulting audio files. There is no native feature to blend voices within a single generation call.
Do all voices support all languages?
Yes, every voice preset can speak all 23 supported languages. You can use Aria for Japanese or Milo for German without restriction. If the language is not set, the system guesses it from the script, but you should specify it for non-English Latin text.
Is Aria better than Nova for blogs?
Aria is described as a warm, clear narrator, while Nova is bright and upbeat. Neither is objectively better; it depends on your blog’s tone. Use Aria for calm reading and Nova for energetic updates. Test both with your specific content to decide which fits your audience.
Does Milo sound too casual for news?
Milo is designed as a friendly, conversational voice. For news, Atlas is specified as a neutral voice, making it more suitable for standard reporting. If you prefer a conversational news style, Milo works, but Atlas provides a more traditional, neutral tone for serious updates.
Is Orion too deep for short ads?
Orion is described as deep and documentary-style. It can work for short ads if you want a serious, authoritative tone. For energetic or upbeat ads, Felix or Nova might be better. You can adjust the speed between 0.25 and 4.0 to change the pacing.
Can I adjust the pitch of the voices?
The API allows you to adjust the speed between 0.25 and 4.0, but it does not offer pitch control. You can change how fast the text is spoken, but the fundamental pitch remains fixed for each voice preset. Use speed to alter the delivery style.
Are the voices licensed for commercial use?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. The generated audio files are returned directly to you. You can use them in your e-commerce store without additional licensing fees beyond the API usage cost.
Do the voices sound the same in all languages?
Each voice maintains its character across all 23 supported languages. Aria sounds like Aria whether speaking English or Spanish. However, the naturalness depends on the language support. All listed languages are fully supported by every voice preset.
Which voice is best for accessibility?
Aria is described as a clear narrator, making it suitable for accessibility. Sage offers a calm, instructional tone also good for clarity. Ensure you use a supported language and clear text. The audio is generated quickly, helping users access content without delay.
Can I use multiple voices in one file?
No, each request generates audio with a single voice. To create a file with multiple voices, you must send separate API calls for each segment. Then, join the resulting audio files on your end. The API does not support multi-voice generation in one response.
Is there a difference between tts-1 and tts-1-hd?
Both models have the same price. The official documentation states they use the same engine. You can choose either for your requests without any change in cost.
Do the voices have emotions?
The voices do not have explicit emotion tags or controls. Each voice has a predefined character, such as Aria’s warmth or Felix’s energy. You cannot dynamically add sadness or excitement. The tone is fixed per voice preset, though speed adjustments can alter the feel.
Can I clone a specific voice?
Custom voice cloning is not offered. You cannot upload your own voice or clone a specific person. You must choose from the eight available presets. The voices are based on licensed recordings and cannot be customized to match a unique individual’s voice.
Female voices overview
Choose the right female voice to match your store’s personality. Aria, Nova, and Luna offer distinct styles for product pages and updates.
Aria: Warm and clear narrator
Aria delivers a warm, clear narrator style ideal for general product descriptions. Her voice ensures clarity without sounding overly formal, making complex details easy to digest for shoppers.
- Best for: General product descriptions
- Tone: Warm, clear narrator
Nova: Bright and upbeat tone
Nova brings a bright, upbeat energy perfect for promotional content. Her lively tone grabs attention quickly, making her ideal for limited-time offers or new arrival announcements.
- Best for: Promotions and new arrivals
- Tone: Bright, energetic
Luna: Soft storytelling style
Luna uses a soft, storytelling approach to engage listeners emotionally. She works well for brand stories or detailed product backgrounds where a gentle pace enhances connection.
- Best for: Brand stories
- Tone: Soft, narrative
Male voices overview
Male voices provide distinct tones for different store needs. Felix brings high energy to sales, while Milo offers a conversational feel for daily updates. Atlas remains neutral, making it ideal for clear, factual announcements.
Felix: Energetic promo style
Felix delivers an upbeat, energetic tone perfect for promotional content. His clear delivery works well for short ads or limited-time offers where you need to grab attention quickly.
- Best for: Sales banners, holiday promotions, product launches
- Tone: Bright, active, engaging
Milo: Friendly conversational tone
Milo is a friendly, conversational voice. This voice is ideal for blog posts, FAQ sections, or customer updates where a warm, approachable tone builds trust with your shoppers.
- Best for: Blog posts, FAQs, welcome messages
- Tone: Warm, natural, approachable
Atlas: Neutral news style
Atlas provides a steady, neutral narration style. It is best used for factual content like shipping updates, policy changes, or new inventory arrivals where clarity matters more than emotion.
- Best for: Policy updates, shipping notifications, new arrivals
- Tone: Calm, clear, professional
Specialized male voice
Orion delivers a deep, resonant tone ideal for documentary-style narration. His voice adds a layer of gravity and seriousness to your content, making complex topics feel authoritative and well-produced.
Orion: Deep documentary style
Orion’s rich bass tones create a professional atmosphere suitable for in-depth product stories or brand history segments. His steady delivery ensures listeners remain engaged without feeling rushed, providing a cinematic quality to your audio content.
- Deep, resonant bass tones
- Cinematic documentary feel
- Steady, engaging delivery
Best for serious topics
Use Orion for explaining technical specifications, detailing warranty terms, or presenting serious brand values. His neutral yet profound presence helps convey trust and reliability, ensuring that important information is received with the appropriate weight and clarity by your customers.
Orion has a deep, documentary style. This makes him particularly effective for long-form content where maintaining listener attention over time is crucial.
High production value feel
Pairing Orion’s voice with clean audio formats like WAV or FLAC enhances the perceived quality of your store. Even simple product updates gain a polished, broadcast-ready aesthetic that distinguishes your brand from standard text-to-speech implementations.
This approach creates a consistent soundscape.
Matching voice to content type
Aligning your voice with content type ensures your store feels cohesive. Product descriptions benefit from clear, informative narration, while blogs allow for a more relaxed tone. Using the right voice helps listeners distinguish between sales pitches and editorial content without confusion.
Product descriptions vs. blogs
Use Aria or Sage for product pages to highlight features clearly. Their calm, instructional styles work well for detailed specs. For blogs, Nova’s upbeat tone keeps readers engaged with lighter, conversational updates about new arrivals or store news.
- Aria for clear product specs
- Sage for instructional details
- Nova for engaging blog stories
Ads vs. educational content
Felix brings energy to promotional ads, driving urgency with his energetic style. Educational content pairs better with Milo or Atlas, who offer a friendly, neutral delivery that explains concepts without sounding salesy. This distinction helps customers trust your guidance.
- Felix for high-energy promos
- Milo for friendly explanations
- Atlas for neutral facts
Customer updates vs. news
Customer updates benefit from Luna’s soft, storytelling approach, making shipping or policy changes feel personal. For broader news, Atlas provides a reliable, neutral voice suitable for announcements. Consistency here builds a recognizable brand voice across all touchpoints.
- Luna for personal updates
- Atlas for official news
- Maintain consistent tone
Language compatibility
Your online store might serve customers worldwide, but your TTS engine doesn’t need separate voices for every region. ShopVoice API lets you pick any of the eight preset voices—like Aria, Felix, or Luna—and have them speak in any of 23 supported languages. This simplifies your audio library while keeping a consistent brand voice across markets.
This flexibility means you don’t need to manage multiple voice profiles for different regions. A single voice model handles everything from Arabic to Swahili, ensuring your product descriptions and updates sound natural regardless of the listener’s language.
All voices speak all 23 languages
Every voice in our library is multilingual. Whether you choose the warm narrator Aria or the energetic promo voice Felix, they can deliver clear audio in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, or Turkish.
This universal compatibility reduces decision fatigue. You can stick to your preferred brand voice while expanding into new linguistic markets without retraining or hiring new voice actors.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic language detection
When you don’t specify a language, the API guesses the language based on the script. Latin script defaults to English, which works for most Western languages. For non-English Latin-script text, it’s safer to set the language explicitly.
This automation speeds up integration. You can send text in any supported language without worrying about complex configuration, letting the API handle the linguistic nuances behind the scenes.
Manual language setting
For best results, always set the language parameter when using non-English Latin-script text. This prevents the API from defaulting to English pronunciation. Supported ISO codes ensure accurate accent and intonation.
Manual control guarantees consistency. If your store sells in multiple European languages, setting the language code prevents the voice from sounding like it’s speaking with an incorrect accent, preserving your professional tone.
Tone and mood selection
To match your store’s personality, choose a voice that reflects the mood of your content. Upbeat voices energize promotions, while calm tones reassure customers during service updates.
Upbeat for sales promotions
Use Nova or Felix for flash sales and new arrivals. Their bright, energetic delivery captures attention quickly, making promotional messages feel urgent and exciting without sounding artificial.
- Nova for upbeat, clear promotions
- Felix for energetic, promo-style announcements
Calm for customer service
Luna or Sage work well for help pages or refund policies. Their soft, instructional tone reduces stress, making complex information easier to digest during support interactions.
- Luna for soft, storytelling clarity
- Sage for calm, instructional guidance
Neutral for factual content
Atlas delivers consistent, clear narration for blogs or product specs. His neutral style ensures facts are presented without bias, maintaining professionalism across diverse content types.
- Atlas for neutral, news-style clarity
Accessibility considerations
Natural-sounding speech significantly improves accessibility for visually impaired shoppers, making your store inclusive and easier to navigate. Unlike robotic text-to-speech, these voices provide clear articulation that helps users comprehend product details without strain.
Clear articulation for screen readers
Voices like Aria and Sage offer crisp diction that pairs well with screen reader software. This clarity ensures customers can accurately hear product specifications and descriptions without missing critical details.
- Aria: Warm, clear narrator ideal for detailed product specs
- Sage: Calm, instructional tone perfect for step-by-step guides
Consistent pacing
Adjustable speed settings (0.25–4.0x) allow users to control how fast audio plays. This flexibility helps shoppers who prefer slower, deliberate speech or those who need to quickly scan updates.
Avoiding monotone delivery
Dynamic voices like Nova and Felix add emotional nuance, keeping listeners engaged. This variation prevents the fatigue often associated with flat, robotic audio during long product tours or blog reads.

Brand voice alignment
Your store’s audio should reflect its personality, whether playful, professional, or reliable. Aligning your voice choice with your brand identity ensures that customers recognize your content instantly. For instance, a boutique fashion store might prefer Nova’s upbeat tone, while a tech retailer might lean toward Atlas’s neutral clarity. This alignment creates a cohesive user experience that reinforces your brand’s core values.
Consistency is key to building trust. Using the same voice across product pages, ads, and updates helps customers feel familiar with your brand. Avoid switching voices randomly, as this can confuse users and dilute your brand’s message. Instead, stick to one or two voices that best represent your store’s character.
Matching brand personality
Identify your store’s core traits. Are you friendly and approachable? Choose Milo for a conversational tone. Are you authoritative and trustworthy? Atlas delivers a neutral, professional sound. Match the voice to your brand’s unique personality to create a consistent auditory identity.
For example, a luxury goods store might prefer Luna’s soft, storytelling style to evoke elegance, while a discount retailer might use Felix’s energetic promo voice to convey excitement and urgency. This alignment ensures your audio content feels authentic to your brand.
- Define your brand’s core values
- Choose a voice that reflects these values
- Avoid mixing voices unless necessary
Consistency across pages
Use the same voice for all product descriptions on your site. This creates a seamless experience for customers browsing multiple items. Consistency helps customers recognize your brand’s audio signature, even if they are visiting different sections of your store.
For customer updates and news, maintain the same voice used in your primary content. This ensures that your brand’s tone remains uniform, whether customers are reading about new arrivals or store policies.
- Use one voice for product pages
- Maintain the same voice for updates
- Avoid random voice changes
Creating a recognizable sound
A consistent voice helps customers associate your brand with a specific tone. This recognition builds trust and familiarity over time. Whether it’s the warmth of Aria or the calm of Sage, a recognizable sound becomes part of your brand’s identity.
To enhance recognition, pair your chosen voice with consistent audio formats and speed settings. This ensures that your brand’s audio content feels polished and professional, reinforcing your store’s unique personality.
- Stick to one voice for key content
- Pair voice with consistent audio settings
- Build a recognizable auditory brand
Technical performance
Technical performance directly impacts user experience in your online store. Understanding how speed, format, and latency interact helps you deliver audio that feels natural without unnecessary delays.
These settings allow you to balance file size, loading speed, and audio quality to suit different content types, from quick product updates to detailed educational guides.
Speed settings (0.25–4.0x)
You can adjust the speech rate between 0.25 and 4.0 times normal speed. Faster speeds are useful for quick product announcements or ads where brevity matters. Slower rates improve clarity for complex instructions or accessibility needs.
Adjusting speed does not affect the character count or pricing, so you can optimize for listening comfort without extra cost.
- Use 1.0x for standard product descriptions.
- Increase speed for short promotional banners.
- Slow down for detailed instructional content.
Audio format impact
Choose between mp3, wav, opus, flac, or pcm based on your platform’s requirements. MP3 offers the best balance of quality and file size for web delivery. WAV and FLAC provide lossless quality but result in larger files.
PCM is useful for raw audio processing, while OPUS offers efficient compression for streaming scenarios. Selecting the right format ensures fast loading without compromising clarity.
- MP3: Best for general web use.
- WAV/FLAC: High quality, larger files.
- OPUS: Efficient compression format.
Latency considerations
Requests are processed sequentially, so under load, a request may wait in a queue. Typical generation speed is roughly real-time, producing about 25 characters of text per second. Short phrases may take a few seconds to generate.
For longer texts, split the input into parts of up to 4096 characters and join the resulting audio files. This approach minimizes individual request latency and ensures consistent delivery.
- Real-time generation for long texts.
- Queue delays possible under high load.
- Split long texts for better performance.
Cost vs. quality
Your store’s audio budget is straightforward: $0.01 per 1,000 characters, regardless of model choice. Both tts-1 and tts-1-hd share this flat rate, so you never pay extra for higher fidelity. Failed requests are free, ensuring you only pay for successful audio generation. This simplicity helps no-code stores forecast costs without complex tier calculations or hidden fees for specific voice qualities.
The difference lies entirely in the audio engine, not the price tag. You can upgrade your product page narration to HD quality without increasing your monthly spend. This allows you to reserve premium audio for high-impact areas like homepage ads or key product descriptions, while keeping background updates or less critical notifications on the standard model.
Standard vs. HD model
The tts-1-hd model uses a more advanced engine than tts-1, delivering clearer audio with less background noise. Both accept the same input parameters and generate audio at the same rate. You can switch between them instantly in your API calls without changing your workflow or billing structure.
- tts-1: Standard engine, efficient processing
- tts-1-hd: Enhanced clarity, reduced noise
- Both models: $0.01 per 1,000 characters
Same price, different quality
Since the character count determines cost, not the model, you have full flexibility. Use tts-1-hd for your main store introduction where first impressions matter. Switch to tts-1 for internal updates, blog summaries, or less critical notifications. This strategy maximizes perceived quality where it counts most, without inflating your audio bill.
Choosing based on use case
Reserve HD audio for customer-facing marketing assets like hero banners or promotional videos. Use the standard model for bulk content like category descriptions or FAQ sections. This approach ensures your store sounds professional where it matters, while keeping operational audio costs low. Remember, both models support all 23 languages and 8 voices equally.
Testing strategies
Testing helps you find the right voice for your store without guessing. By comparing options, you ensure your audio sounds natural and fits your brand.
A/B testing different voices
Run parallel tests on product pages. Use Aria for descriptions and Nova for ads. Measure which voice you prefer.
- Test one voice per page variant
- Keep text identical to isolate voice impact
- Run tests for at least one week
Gathering user feedback
Ask visitors directly if the audio is clear and helpful. Simple surveys or feedback buttons work well for no-code stores to collect qualitative insights.
- Use embedded feedback widgets
- Ask specific questions about clarity
- Log comments in your CRM
Monitoring engagement metrics
Track time on page and click-through rates. Higher engagement often indicates the voice resonates better with your audience’s preferences and needs.
- Monitor average session duration
- Track audio play rates
- Compare conversion rates by voice type
Implementation tips
Implementing your TTS engine doesn’t require a full overhaul. Start by generating audio for your most critical pages, like product descriptions or key landing sections, using a single consistent voice. This lets you verify integration with your store’s backend and assess the natural flow without overwhelming your catalog.
Once the workflow is stable, gradually expand the library by adding voices for specific content types, such as using Felix for promotional banners or Luna for blog posts. This phased approach ensures quality control and helps you identify which voices resonate best with your shoppers.
Start with one voice
Choose one voice that aligns with your primary brand tone and apply it to high-traffic pages first. This simplifies the initial API integration and lets you troubleshoot any issues with a single configuration before scaling up.
Gradually expand library
As you become comfortable with the API, introduce additional voices for distinct content categories. For example, use a neutral voice for factual updates and a brighter tone for sales announcements. This variety enhances engagement without requiring immediate complex routing logic.
Update based on performance
Monitor which voices drive better engagement or completion rates. If a specific voice performs well in ads, consider applying it to similar content. Regularly review your usage and switch voices if your brand direction evolves, ensuring your audio remains fresh and relevant.
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.
23 languages
Any voice speaks any of these languages.
