Choosing the Right TTS Voice for Video Ads

By SpotWave editorial team · Updated 2026-11-18

This guide helps ad agencies and content creators select the right synthetic voice for video ads and radio spots using the SpotWave API. We break down each of the eight available presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—by their specific tonal qualities and ideal use cases. You will learn how to match voice characteristics to your brand’s messaging, ensuring clarity and audience appeal in every spot.

Readers will also find concrete technical specifications, including supported formats, speed ranges, and character limits, alongside practical advice on script optimization and licensing. Whether you are producing e-commerce videos or explanatory content, this page provides the data needed to make informed decisions about voice selection, pricing, and workflow integration without guessing.

Choosing the Right TTS Voice for Video Ads

Frequently asked questions

Which voice is best for e-commerce?

Felix is described as energetic and ideal for promotions, making it suitable for e-commerce spots. Nova offers a bright, upbeat tone also well-suited for advertising. Sage provides a calm, instructional voice for clear product instructions. The choice depends on whether you prioritize energy or clarity in your specific ad format.

Is Aria better than Nova for ads?

Aria is a warm, clear narrator, while Nova is bright and upbeat. Neither is objectively better; the choice depends on your brand voice. Aria suits storytelling or softer product introductions, whereas Nova fits high-energy promotional content. Both are available presets within the same engine, allowing you to test which resonates better with your audience.

Can I use Orion for news segments?

Orion is described as deep and suited for documentaries. For news segments, Atlas is the neutral, news-oriented preset. While Orion can speak any supported language, Atlas provides a more standard journalistic tone. You can adjust the speed between 0.25 and 4.0 to match the pacing required for your specific news format.

Do the voices sound natural?

The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech. The service aims for realistic speech synthesis suitable for professional use, though the synthetic nature is technically present in every audio file produced by the API.

What is the difference between Sage and Atlas?

Sage is a female voice described as calm and instructional, ideal for guides or tutorials. Atlas is a male voice described as neutral and suited for news. Both are presets available in the API. You can select either based on whether your content requires a conversational instructional tone or a neutral journalistic delivery style.

Can I mix male and female voices?

The API processes one voice per request. To mix voices, you must send separate requests for each segment and join the resulting audio files. You can split longer texts into parts of up to 4096 characters. This allows you to combine different voices like Felix and Aria into a single final ad spot.

Are the voices licensed for commercial use?

The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. The API provides the synthesized audio for your use. The product facts confirm the licensing source but do not specify additional commercial restrictions beyond the base licenses. You can use the generated audio for video and radio spots as described in your workflow.

Do I need to attribute the voices?

The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox readings. CC BY 4.0 typically requires attribution. The generated audio also contains an inaudible watermark marking it as synthetic. You should verify if your specific usage of the CC BY 4.0 material requires visible attribution in your ad credits or description.

Can I change the accent of the voices?

Each voice can speak any of the 23 supported languages. If you do not set the language, it is guessed from the script, defaulting to English for Latin text. To change the accent, specify the ISO language code in the request. This allows you to produce Spanish audio with the Aria voice, for example.

How do I choose between tts-1 and tts-1-hd?

Both models use the same engine and have the same price. The only difference is the model identifier in your request. You can choose either 'tts-1' or 'tts-1-hd' without any cost or performance difference. They support the same voices and formats.

Is the audio quality consistent?

Quality is consistent as the same engine powers both model variants. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time for long texts. Short phrases may take a few seconds. The audio format (mp3, wav, opus, flac, pcm) determines the file type.

Can I use the voices in social media ads?

Yes, you can use the generated audio for social media ads. The API returns the audio file directly in the response. You can generate short phrases or split longer texts into 4096-character parts. The transparent pricing of $10 per million characters makes it cost-effective for bulk social media content creation.

Do the voices support all 23 languages?

Yes, every voice can speak any of the 23 supported languages, including Arabic, Chinese, English, German, Japanese, and Spanish. If the language is not set, it is guessed from the script. For non-English Latin-script text, you should explicitly set the language parameter to ensure correct pronunciation.

What is the watermark?

Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded in the audio data itself. It serves to identify the content as AI-generated without affecting the listening experience. The watermark is present in all formats returned by the API, including mp3, wav, opus, flac, and pcm.

Female voices review

Sound wave illustration for: Female voices review

The female voices in SpotWave API offer distinct tonal qualities tailored for advertising needs. Aria provides a warm, clear narration ideal for emotional storytelling, while Nova delivers a bright, upbeat energy suitable for high-impact spots. Luna excels in soft, narrative-driven content, adding depth to longer formats.

Aria: Warm narrator

Aria’s tone is clear and approachable, making her suitable for brand stories that require a personal touch. Her voice maintains clarity even at higher speeds, ensuring the message is never lost in production.

  • Ideal for lifestyle brands and emotional storytelling.
  • Clear articulation ensures message retention.

Nova: Bright upbeat

Nova brings high energy and brightness, perfect for promotional content that needs to grab attention quickly. Her upbeat delivery works well for short, punchy radio spots or social media ads where time is critical.

  • Best for promotional and fast-paced content.
  • High energy suitable for social media ads.

Luna: Soft storytelling

Luna offers a softer, more intimate tone, ideal for narrative-driven videos or explainer content. Her voice adds a layer of sophistication and calm, making complex information feel accessible and engaging.

  • Perfect for narrative-driven or explainer videos.
  • Adds sophistication to complex information.

Male voices review

Sound wave illustration for: Male voices review

Male voices in SpotWave API offer distinct tonal profiles tailored for specific advertising contexts. Each preset is engineered to convey a particular mood, allowing advertisers to match audio tone directly to visual content without the variability of human performance.

These voices are based on licensed LibriTTS-R recordings, ensuring commercial readiness. They provide consistent quality across bulk synthesis jobs, which is critical for maintaining brand voice in high-volume radio spot production.

Felix: Energetic promo

Felix delivers high-energy delivery ideal for promotional content. His tone is upbeat and dynamic, making it suitable for short-form video ads where attention must be grabbed immediately. This voice works well for product launches or limited-time offers.

The energetic cadence reduces listener fatigue during fast-paced cuts. It maintains clarity even at higher speeds, ensuring the call-to-action remains audible and compelling.

  • Ideal for: Promotional videos, social media ads
  • Tone: High-energy, upbeat
  • Best use: Short-form content

Milo: Friendly conversational

Milo offers a warm, conversational tone that feels personal and approachable. This voice is excellent for brand storytelling or customer testimonials where trust and relatability are key. It mimics natural speech patterns without sounding robotic.

Use Milo for longer narratives or explanatory segments where listener retention is crucial. The friendly demeanor helps maintain engagement over extended durations, making it suitable for explainer videos or branded podcasts.

  • Ideal for: Brand stories, testimonials
  • Tone: Warm, approachable
  • Best use: Narrative content

Atlas: Neutral news

Atlas provides a neutral, authoritative tone similar to news broadcasting. This voice is best for informational content, such as product specifications or corporate updates. It conveys reliability and professionalism without emotional bias.

Use Atlas when clarity and neutrality are prioritized over emotional appeal. It is particularly effective for technical explanations or factual reports where the message needs to be delivered with precision and calm authority.

  • Ideal for: News, corporate updates
  • Tone: Neutral, authoritative
  • Best use: Informational content

Specialty voices

Sound wave illustration for: Specialty voices

Beyond standard narrative styles, SpotWave offers specialized voices tailored for specific advertising contexts. Sage and Orion provide distinct tonal qualities that enhance instructional clarity or create immersive documentary-style atmospheres, ensuring your voice-over matches the exact mood of your spot.

These presets are built on licensed LibriTTS-R recordings, guaranteeing commercial usability without complex licensing negotiations. Selecting the right specialty voice can significantly impact listener retention and brand perception in competitive media environments.

Sage: Calm instructional

Sage delivers a calm, instructional tone ideal for explainer videos and e-commerce tutorials. Its clear enunciation ensures that complex product features are communicated without confusion. The voice remains steady and reassuring, making it perfect for guiding users through a process or detailing specifications in a video ad.

Use Sage when clarity is more important than emotional excitement. It works well for step-by-step guides, software demonstrations, or any content where the listener needs to absorb information without distraction.

  • Ideal for tutorials and how-to videos
  • Clear, steady pacing for complex information
  • Professional yet approachable demeanor

Orion: Deep documentary

Orion provides a deep, resonant voice suitable for documentary-style ads or high-impact brand stories. Its rich tone adds weight and seriousness to the narrative, making it effective for luxury goods or premium service promotions.

This voice creates an atmosphere of authority and trust. It is particularly effective for voice-overs that require a cinematic quality, such as brand histories or high-end product reveals.

  • Deep, resonant tone for premium branding
  • Suitable for documentary and narrative ads
  • Adds authority to brand stories

Voice characteristics

All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. This ensures that the synthetic speech maintains high naturalness while remaining legally compliant for commercial use in advertising.

Each generated file includes an inaudible watermark identifying it as synthetic. This allows for easy verification of content origin if needed, though it does not affect the listener's experience.

  • Based on CC BY 4.0 licensed recordings
  • Public domain source material from LibriVox
  • Inaudible synthetic watermark included

Selection criteria

Sound wave illustration for: Selection criteria

Selecting the right voice requires balancing vocal tone with the specific demands of your ad format. Clarity ensures the message is understood instantly, while tone sets the emotional context for the listener.

Tone and clarity

Clear articulation is critical for radio spots where audio is often background noise. Voices like Atlas provide a neutral, news-style delivery that minimizes listener fatigue, while Felix offers an energetic promo style that grabs attention quickly.

Audience appeal

Match the voice to your target demographic. Luna’s soft, storytelling tone works well for lifestyle brands, while Orion’s deep, documentary style suits tech or automotive reviews. Testing variations helps identify what resonates.

Brand alignment

Ensure the voice reflects your brand’s personality. A warm narrator like Aria suits premium services, whereas a bright, upbeat Nova fits fast-paced e-commerce ads. Consistency in voice across multiple spots builds brand recognition over time.

Use case matching

Sound wave illustration for: Use case matching

Matching voice presets to specific media formats ensures your spot resonates with the intended audience. Each voice carries distinct tonal qualities suited for different advertising contexts, from high-energy e-commerce bursts to calm instructional narratives.

The following breakdown aligns our eight voice presets with three primary use cases, helping you select the optimal audio profile for your video or radio deliverables.

E-commerce videos

For fast-paced product showcases, use Felix for energetic promotions or Nova for bright, upbeat appeals. These voices drive engagement in short social media clips and retail video ads where attention spans are limited.

Luna works well for soft storytelling in lifestyle branding, while Aria provides a warm, clear narrator tone suitable for detailed product features in longer format ads.

  • Felix: energetic, promo
  • Nova: bright, upbeat
  • Luna: soft, storytelling
  • Aria: warm, clear narrator

Radio commercials

Atlas delivers a neutral, news-style delivery ideal for straightforward announcements and time-sensitive offers. Milo offers a friendly, conversational tone that builds trust in direct-response radio spots.

Orion’s deep, documentary style adds authority to premium brand advertisements, while Sage’s calm instructional voice works for service-oriented radio content requiring clarity.

  • Atlas: neutral, news
  • Milo: friendly, conversational
  • Orion: deep, documentary
  • Sage: calm, instructional

Explainer videos

Sage is the primary choice for instructional content, offering a calm, clear tone that aids comprehension. Aria also serves well for detailed feature explanations in tech or software demos.

Use Luna for narrative-driven explainers that require a softer, more engaging storytelling approach. Ensure speed settings between 1.0–1.5x to maintain clarity without rushing the message.

  • Sage: calm, instructional
  • Aria: clear, detailed
  • Luna: narrative-driven
  • Speed: 1.0–1.5x recommended

Technical specifications

Sound wave illustration for: Technical specifications

The API supports five audio formats—MP3, WAV, OPUS, FLAC, and PCM. OPUS offers efficient compression for web apps, while WAV and FLAC provide lossless quality for radio broadcasting. PCM is available for raw audio processing.

Format options

MP3 is standard for web delivery. WAV and FLAC ensure broadcast-ready fidelity. PCM allows direct integration with audio editing software.

  • MP3 for web
  • WAV for broadcast
  • FLAC for lossless
  • OPUS for compression
  • PCM for raw data

Speed range

Speed adjusts from 0.25x to 4.0x. This allows fine-tuning voice pacing for different ad lengths. Faster speeds suit quick e-commerce promos, while slower rates enhance clarity for complex instructions.

  • Range: 0.25–4.0x
  • Adjusts pacing
  • Optimizes ad length

Character limits

Each request accepts up to 4096 characters. Longer scripts require splitting into segments. The API returns separate audio files for each part, which you join during post-production.

  • Max 4096 chars
  • Split long scripts
  • Join audio parts

Licensing details

Sound wave illustration for: Licensing details

SpotWave API voices are derived from the LibriTTS-R dataset, which carries a CC BY 4.0 license. This framework permits commercial use provided proper attribution is given to the original data sources.

LibriTTS-R license

The underlying voice models are trained on the LibriTTS-R dataset, licensed under Creative Commons Attribution 4.0. This allows commercial integration into video ads and radio spots without additional licensing fees, provided you attribute the source appropriately in your project documentation.

Public domain source

Many training recordings originate from LibriVox, where readers have released their performances into the public domain. This ensures that the core vocal characteristics are free from restrictive copyright claims, simplifying rights clearance for broadcast and digital media.

Commercial usage

You may use generated audio for monetized YouTube videos, paid radio spots, and e-commerce commercials. The synthetic nature of the output means you own the resulting audio file, with no per-unit royalties required by the voice provider.

Licensing details

Comparison with human voices

Sound wave illustration for: Comparison with human voices

Replacing human voice talent with synthetic speech offers immediate cost savings for ad agencies. Each character costs $0.00001, eliminating per-minute or per-project fees. Failed syntheses are free, ensuring you pay only for usable audio files.

This model allows budget flexibility without sacrificing quality. You can experiment with multiple voices without the high marginal cost of re-hiring talent for minor script tweaks.

Cost efficiency

Standard human voiceover rates often exceed $100–$300 per hour of final audio, plus studio time and editing. Our API charges $10 per million characters. A 15-second radio spot averages roughly 30–40 characters, costing less than half a cent per read.

Bulk synthesis scales linearly. Producing 1,000 variations of a commercial for A/B testing costs pennies, whereas hiring a human for each variation would be prohibitive. Failed requests incur no charge, protecting your budget from technical errors.

  • $0.00001 per character (including spaces)
  • No hourly studio rental fees
  • Zero cost for failed requests
  • No minimum spend or monthly retainers

Consistency

Human voice actors vary in performance due to fatigue, health, or mood. Synthetic voices deliver identical tone, pitch, and speed across thousands of requests. This uniformity is critical for brand identity across multiple video ads.

Once you select a voice like Atlas for news-style spots or Luna for storytelling, every output matches that baseline. There are no off-days, ensuring consistent audio quality for your radio campaigns.

  • Identical tone across infinite reads
  • No fatigue or health variations
  • Uniform pacing and intonation
  • Instant availability for urgent deadlines

Variety

Access eight distinct presets instantly: warm narrators, upbeat announcers, deep documentarians, and calm instructors. Switching from Felix’s energetic promo style to Milo’s friendly conversational tone requires only a parameter change, not a new booking.

Each voice supports all 23 languages. You can test different demographic appeals by swapping voices within seconds, allowing rapid iteration on script-to-voice fit without logistical delays.

  • 8 distinct voice presets
  • 23 languages with native accent accuracy
  • Instant voice swapping
  • No booking scheduling conflicts

Common mistakes

Sound wave illustration for: Common mistakes

Selecting a voice that mismatches the ad’s intent is a common error. For instance, using Aria for a high-energy promo feels flat, while Orion for a quick e-commerce clip sounds overly heavy. Match the preset to the script’s emotional core to avoid audience disconnect.

Ignoring speed settings or writing scripts without considering character limits also degrades quality. Scripts exceeding 4096 characters require manual splitting, and improper speed adjustments can make speech unnatural. Always test variations before finalizing.

Wrong voice selection

Using a warm narrator voice for a hard-sell promo confuses listeners. Ensure the preset matches the desired tone—Nova for upbeat energy, Felix for energetic promos, or Atlas for neutral news-style spots.

Mismatched gender or tone can undermine brand credibility. Review the voice characteristics list to align the preset with your target demographic and ad style.

  • Use Nova or Felix for upbeat promos
  • Use Aria or Luna for warm storytelling
  • Use Atlas for neutral, clear announcements

Ignoring speed settings

Speed ranges from 0.25 to 4.0. Setting it too high makes speech unintelligible; too low makes it dragging. Adjust speed to match the natural rhythm of the script.

Requests are processed sequentially, so longer texts may queue. Ensure your script length fits within the 4096-character limit per request to avoid unnecessary splitting and joining delays.

Poor script writing

Scripts must be concise and clear. Avoid complex punctuation or ambiguous phrasing that the TTS engine might misinterpret. Spaces and punctuation count as characters, so keep scripts tight.

Test the script with the chosen voice and format before full production. Small adjustments in wording can significantly improve clarity and engagement in the final audio file.

Optimization tips

Sound wave illustration for: Optimization tips

To get natural-sounding ad spots, adjust the speed parameter between 0.25 and 4.0. Faster rates work for quick e-commerce promos, while slower speeds suit storytelling.

Choose formats like MP3 for web delivery or WAV for broadcast. Keep scripts under 4096 characters to ensure consistent synthesis quality without queue delays.

Adjusting speed

Set speed to 1.0 for standard narration. Increase to 1.5–2.0 for energetic radio spots. Decrease to 0.75–0.9 for calm, instructional content. Test how speed affects clarity in your specific voice preset.

  • Standard speed: 1.0
  • Fast promo: 1.5–2.0
  • Calm narration: 0.75–0.9

Choosing formats

Use MP3 for general web use to balance quality and size. Select WAV or FLAC for high-fidelity radio broadcast requirements. PCM is ideal for raw audio processing workflows. OPUS offers efficient compression for web apps.

  • MP3: Web and social media
  • WAV/FLAC: Professional broadcast
  • OPUS: Efficient web streaming

Testing variations

Generate short samples with different voices and speeds. Compare audio quality across formats before finalizing production. Check character count limits to avoid truncation in longer scripts. Verify language settings for non-English scripts to ensure correct pronunciation.

  • Test multiple voices
  • Compare format quality
  • Verify language settings

Pricing and access

Sound wave illustration for: Pricing and access

SpotWave uses a simple per-character billing model at $10 per million characters, ensuring predictable costs for high-volume ad production. Failed requests are free, so you only pay for successful audio generation. This transparency eliminates hidden fees for agencies managing multiple campaigns.

Access begins with a $0.50 free trial (7 days) via Google sign-in, allowing you to test voice quality before committing. For sustained production, top-ups are processed via USDT (TRC-20) on the TRON network, with balances credited automatically within minutes. No subscriptions or minimum spends apply.

Per-character billing

The rate is $0.01 per 1,000 characters, including spaces and punctuation. This straightforward metric helps you budget accurately for radio spots and video voice-overs without guessing about session durations or hidden usage caps.

  • $10 per 1 million characters
  • $0.01 per 1,000 characters
  • Failed requests are free

Free trial credit

New accounts signed in with Google receive $0.50 in trial credit, valid for 7 days. This allows approximately 50,000 characters of generation to test voice suitability for your specific brand tone.

  • $0.50 credit
  • 7-day validity
  • Google sign-in only

Top-up with USDT

Add funds via USDT on the TRON network (TRC-20) with a $5 minimum. Transfers are credited automatically within minutes, ensuring your campaigns never stall due to billing delays. Balance never expires.

  • USDT (TRC-20) only
  • $5 minimum top-up
  • Automatic credit within minutes

Conclusion

Sound wave illustration for: Conclusion

Choosing the right voice is the final step in ensuring your ad resonates. Whether you need the warm clarity of Aria for e-commerce or the deep authority of Orion for documentaries, consistency and tone matter more than novelty. Use the speed and format options to match your production workflow precisely.

With transparent per-character billing and no hidden fees, you can scale your voice-over production predictably. Test variations across your eight voices to find the perfect fit for your brand’s identity without breaking the budget.

Final recommendations

Start with the free trial to evaluate quality against your specific scripts. Select voices that match the emotional tone of your spot, then lock in your preferred speed and format for consistency across campaigns.

Use the bulk synthesis approach for longer scripts, splitting text into 4096-character chunks to ensure stable generation and easy troubleshooting if a single segment fails.

  • Match voice personality to ad genre
  • Test speed settings between 0.5 and 2.0
  • Use MP3 for web, WAV for broadcast

Next steps

Generate your API key via the /get-api-key/ page. Use the provided curl example to send your first request to the /v1/audio/speech endpoint. Integrate the response audio directly into your editing timeline.

Monitor your balance in the dashboard. Top up with USDT on TRON when needed to keep production running without interruption.

  • Sign up for API access
  • Test with a 100-character sample
  • Integrate into your editing pipeline

Support contact

For technical issues or billing questions, reach out via email. We do not offer live chat or phone support, so please include your API key and request details in your message for faster resolution.

Response times are typically within one business day. For urgent production issues, consider duplicating your request with a different voice as a fallback.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

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. TRON developer hub: TRC-20
  3. Python documentation
  4. LibriVox public-domain audiobooks
  5. openai-python on GitHub
  6. MDN: Web Speech API
  7. FFmpeg documentation
  8. Tether (USDT)
  9. LibriTTS-R paper (arXiv 2305.18802)
  10. OpenAI API reference: create speech
  11. IETF RFC 7845: Ogg Opus
  12. Creative Commons Attribution 4.0

More on this site