Frequently asked questions
Which voice is best for car commercials?
Felix offers an energetic, promo-focused tone ideal for car commercials. His delivery suits fast-paced advertising needs. You can adjust his speed between 0.25 and 4.0 to match the rhythm of your spot. The voice is based on licensed recordings, ensuring clear licensing for your broadcast production workflow.
Which voice is best for tech products?
Sage provides a calm, instructional tone suitable for explaining tech features. His clear narration helps listeners understand complex details. You can pair Sage with the tts-1-hd model for higher quality. The API allows precise speed control, ensuring the explanation remains clear and professional for your audience.
Which voice is best for food ads?
Aria delivers a warm, clear narrator voice perfect for food advertisements. Her tone invites listeners in. You can generate audio in multiple formats like mp3 or wav. The system supports 23 languages, allowing you to localize your food spots for different regional markets effectively.
Can I mix voices in one audio file?
No, each API request generates audio from a single voice preset. To mix voices, you must send separate requests for each part and join the resulting audio files. The API returns individual files, so you handle the final assembly in your post-production workflow.
Do I need to specify gender?
No, you select a specific voice preset like Aria or Felix, which determines the gender. The system does not have a generic gender parameter. Each of the eight presets has a fixed character, so you choose the exact voice that matches your creative direction directly.
Which voice sounds most natural?
All voices are based on licensed recordings from LibriTTS-R and LibriVox. They carry an inaudible watermark marking them as synthetic. Naturalness depends on your preference for tone. Aria offers warmth, while Sage provides clarity. All are generated via the same engine with predictable pricing.
Can I use a voice for a long narrative?
Yes, you can send up to 4096 characters per request. For longer texts, split them into parts and join the audio files. Typical speed is roughly real time. Requests process sequentially, so under load, a request may wait in a queue before synthesis begins.
Do voices sound different in different languages?
No, every voice can speak all 23 supported languages. The voice character remains consistent regardless of language. If you do not set the language, the system guesses it from the script, defaulting to English for Latin text. You can explicitly set the language code.
How do I choose between Aria and Luna?
Aria is a warm, clear narrator, while Luna is soft and storytelling-focused. Choose Aria for direct, clear communication like product features. Choose Luna for softer, narrative-driven ads. Both are female presets available in multiple languages, allowing you to match the emotional tone of your spot.
How do I choose between Felix and Milo?
Felix is energetic and promo-oriented, ideal for high-energy sales spots. Milo is friendly and conversational, better for relatable, casual brand messaging. Both are male presets. You can adjust speed from 0.25 to 4.0 to fine-tune the energy level for your specific advertising context.
Is Atlas suitable for news broadcasts?
Yes, Atlas is designed as a neutral, news-oriented voice. His tone is professional and straightforward, making him suitable for informational spots. You can generate audio in wav or mp3 formats. The API supports clear delivery of factual content without emotional bias or dramatic flair.
Is Orion good for documentaries?
Yes, Orion offers a deep, documentary-style voice. His tone suits serious, narrative-driven content. You can use the tts-1-hd model for enhanced audio quality. Orion supports all 23 languages, allowing you to produce high-quality documentary-style spots for various international markets with consistent character.
Can I adjust the voice's age?
No, the voices are fixed presets based on specific recordings. You cannot adjust age parameters like pitch or tone significantly beyond speed. The eight presets offer distinct characters. If you need a different age range, you must select a different voice preset from the available list.
Do the voices have accents?
The voices are designed to speak clearly in their supported languages without specific regional accents unless implied by the voice character. They do not have strong regional dialects. You can set the language explicitly to ensure correct pronunciation. The system guesses language if not specified.
Female Voices Overview
Selecting the right female voice is critical for radio spots, as it sets the emotional tone for the listener. SpotLogic offers three distinct presets, each engineered for specific advertising contexts. These voices are based on licensed recordings from LibriTTS-R and LibriVox, ensuring clear licensing and broadcast-ready quality without the need for custom voice cloning.
Each voice delivers synthetic speech with a subtle inaudible watermark, marking it as AI-generated. For agencies, this provides a transparent, cost-effective alternative to hiring multiple voice actors, especially when producing high volumes of short-form content for digital and radio channels.
Aria: Warm Narrator
Aria provides a warm, clear narrative tone ideal for storytelling or brand introductions. Her voice works well for longer scripts where clarity and emotional connection are paramount.
Use Aria for voiceovers that require a gentle, inviting presence, such as luxury brand introductions or calm instructional segments.
- Best for: Brand storytelling, luxury products
- Tone: Warm, clear
- Limit: 4096 characters per request
Nova: Bright Upbeat
Nova brings a bright, energetic energy to advertisements. Her upbeat delivery is perfect for fast-paced promos, sales announcements, or youthful brand campaigns.
Nova’s voice captures attention quickly, making her suitable for short, punchy radio spots where immediate engagement is required.
- Best for: Sales promos, youthful brands
- Tone: Bright, upbeat
- Speed: Adjustable up to 4.0x
Luna: Soft Storyteller
Luna offers a soft, soothing voice ideal for bedtime stories, wellness brands, or calm instructional content. Her tone reduces listener fatigue in longer audio ads.
Luna is particularly effective for brands focusing on relaxation, health, or premium services where a gentle approach is preferred.
- Best for: Wellness, relaxation, storytelling
- Tone: Soft, soothing
- Language: Supports 23 languages including English, French, German
Male Voices Overview
The male voice presets offer distinct tonal ranges tailored for diverse advertising needs. Each voice is engineered to convey specific emotional cues, from high-energy sales pitches to grounded news delivery, ensuring your radio spots resonate with the intended audience without requiring complex mixing.
Felix: Energetic Promo
Felix delivers a bright, upbeat energy ideal for time-sensitive promotions. His clear articulation and dynamic pacing make him suitable for discount announcements or limited-time offers where immediate attention is required.
- Best for high-energy retail campaigns
- Clear enunciation for quick reads
- Ideal for short-form audio ads
Milo: Friendly Conversational
Milo provides a warm, approachable tone that mimics natural human conversation. This voice works well for brand storytelling, testimonials, or explanatory content where building trust and rapport with the listener is essential.
- Human-like conversational flow
- Excellent for brand narratives
- Engages listeners through relatable tone
Atlas: Neutral News
Atlas offers a balanced, authoritative voice perfect for news-style segments or factual reporting. His neutral delivery ensures the message remains the focus, making it ideal for corporate announcements or straightforward informational spots.
- Professional and unbiased delivery
- Suitable for corporate communications
- Clear, steady pacing
Voice Selection by Genre
Selecting the right voice for a radio spot requires aligning vocal characteristics with the specific genre of the advertisement. Different products evoke different emotional responses, and the synthetic voice must match the intended tone to effectively engage the target audience. This guide outlines how to choose voices for common advertising categories.
By understanding the nuances of each voice preset, advertisers can create more compelling audio assets. The following sections detail voice recommendations for automotive, technology, and food and beverage sectors, ensuring that the synthetic speech resonates with listeners and supports the campaign's goals.
Automotive Ads
For automotive advertisements, a voice that conveys reliability and excitement is essential. The Atlas voice offers a neutral, news-like delivery suitable for factual specifications and safety features. Alternatively, Felix provides an energetic, promotional tone ideal for highlighting deals and new model launches.
When describing performance or design, the warm and clear narration of Aria can add a premium feel to luxury car spots. The choice between Felix and Atlas depends on whether the ad prioritizes excitement or authoritative information.
- Use Atlas for factual, specification-heavy spots.
- Choose Felix for high-energy promotional announcements.
- Aria works well for premium, luxury branding.
Tech Products
Technology products often require a clear, instructional, or friendly tone. Sage’s calm, instructional voice is excellent for explaining complex features or guiding users through new interfaces. Milo’s friendly, conversational style makes tech accessible and approachable for general consumers.
For tech launches that need to sound innovative yet trustworthy, Luna’s soft, storytelling approach can create a narrative around the product’s development. Milo is particularly effective for consumer electronics where a personal connection is desired.
Ensure the language code is set correctly to maintain clarity, especially when technical terms are used. The synthetic voices handle technical jargon well when paired with a clear, steady delivery.
- Sage is ideal for instructional and feature-explaining ads.
- Milo suits consumer electronics and friendly interfaces.
- Luna adds a narrative touch to product stories.
Food and Beverage
Food and beverage ads benefit from voices that evoke appetite and warmth. Luna’s soft, storytelling quality is perfect for describing the sensory experience of food, such as the crunch of a chip or the richness of a chocolate. Aria’s clear narration can effectively highlight ingredients and health benefits.
For fast-food promotions or quick bites, Felix’s upbeat energy matches the fast-paced nature of the industry. Nova’s bright, upbeat tone is also suitable for refreshing beverages or light snacks, adding a sense of joy and satisfaction.
The key is to match the voice’s warmth to the product’s appeal. Use Luna for crafted, artisanal foods and Nova or Felix for mass-market, energetic promotions.
- Luna excels in sensory, descriptive food ads.
- Felix is great for fast-paced, energetic promotions.
- Nova suits refreshing drinks and light snacks.
Tone Matching Strategies
Matching voice tone to brand identity is critical for radio spot effectiveness. The right vocal character reinforces your message without distracting the listener.
Selecting the appropriate voice ensures your ad resonates with the intended audience, whether you need authority, approachability, or calm reassurance.
Authoritative Tone
Atlas delivers a neutral, news-style delivery ideal for establishing credibility. His voice works well for financial services or corporate announcements where trust is paramount.
- Use for press releases and corporate updates
- Ideal for financial or legal services
Friendly Tone
Milo offers a conversational, warm delivery that puts listeners at ease. Felix adds energy for promotional spots, while Aria provides a clear, narrative warmth for storytelling brands.
- Milo for conversational brand voices
- Felix for energetic promotions
- Aria for warm narratives
Calm Tone
Sage provides a calm, instructional voice perfect for guided experiences or wellness products. Luna’s soft storytelling style suits emotional or reflective brand campaigns.
- Sage for instructional content
- Luna for emotional storytelling
Speed and Pacing
Speed defines the rhythm of your spot. The API accepts values from 0.25 to 4.0, letting you control exactly how fast the voice delivers the script. This control is critical for matching the energy of radio advertising.
Adjusting speed changes the perceived urgency without altering the voice’s character. Proper pacing ensures the message is understood within the limited airtime of a commercial break.
Fast-Paced Promos
High-energy promotions benefit from speeds around 1.5x to 2.0x. This range accelerates the delivery of offers and calls to action, creating a sense of immediacy without sacrificing clarity.
Felix works well at higher speeds for promo spots, maintaining energy while keeping the tone distinct.
- Ideal for flash sales
- Maintains clarity up to 2.0x
- Pairs well with Felix
Slow Storytelling
Narrative-driven ads require slower pacing, often between 0.75x and 0.9x. This allows listeners to absorb emotional nuances and brand stories.
Luna or Aria perform effectively at reduced speeds, emphasizing warmth and clarity in storytelling sequences.
- Best for brand stories
- Enhances emotional impact
- Suits Luna and Aria
Adjustable Speed
The speed parameter is applied directly in the JSON request body. You can test multiple speeds for the same script to find the optimal balance between speed and comprehension.
Remember that faster speeds consume the same character count but deliver the audio file more quickly in terms of playback duration.
- Set via speed parameter
- Test 0.75x vs 1.0x
- No extra cost for speed changes
Language Considerations
Language handling is critical for radio ads. Our eight synthetic voices support 23 languages, allowing agencies to produce localized spots without hiring new talent. Each voice can speak any supported language, ensuring consistency in tone across markets. If the language is not specified, the system guesses from the script, defaulting to English for Latin text.
For non-English Latin-script text, always set the language parameter explicitly. This prevents mispronunciation and ensures the intended dialect is used. Supported languages 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.
English Voices
All eight voices—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—deliver clear, broadcast-ready English. They are optimized for advertising clarity, ensuring every word lands with the intended impact. Use the default behavior or explicitly set language: en for consistency.
English remains the primary market for many global campaigns. Our voices handle complex ad copy, ensuring that pacing and emphasis match the creative vision without requiring extensive post-production editing.
- No need for separate English talent hires.
- Consistent brand voice across all English-speaking markets.
- High clarity for rapid-fire promo reads.
Multilingual Options
Expand your reach with support for 23 languages. Whether you need a German spot for the DACH region or Spanish for Latin America, the same API endpoint handles it. Each voice adapts to the phonetics of the target language, maintaining its core character traits.
Note that Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and others are not supported. Always verify your target language against the supported list before production to avoid unexpected results.
- Supports 23 distinct languages.
- Single API call for all languages.
- Avoid unsupported languages like Thai or Ukrainian.
Accent Variations
While we do not offer custom accent training, each voice has inherent tonal qualities that suit specific regional styles. For example, Atlas provides a neutral news tone suitable for international broadcasts, while Milo offers a friendly conversational style ideal for local community ads.
To refine accent perception, adjust the speed parameter. Faster pacing can sometimes mimic energetic regional styles, while slower rates enhance the calm, instructional tone of Sage or the deep documentary feel of Orion. Test combinations to find the best fit for your audience.
- No custom accent cloning.
- Use speed adjustments for nuance.
- Test voice-language combinations.
Technical Implementation
Include the language field in your JSON body. If omitted, the system guesses based on script, defaulting to English for Latin text. Explicit settings reduce risk.
Use POST /v1/audio/speech with your API key. Ensure your text fits within 4096 characters. For longer scripts, split and concatenate.
- Set
languageexplicitly for non-English Latin text. - Default to English if unspecified.
- Use 4096 char limit per request.
Technical Implementation
Integrating SpotLogic into your production pipeline requires a standard HTTP POST request to https://api.ah777.info/v1/audio/speech. Since the endpoint mirrors the OpenAI API structure, existing integrations can adapt by simply updating the base_url to https://api.ah777.info/v1. Authentication is handled via a Bearer token in the Authorization header, ensuring secure access to your account's voice synthesis capabilities.
The request body accepts JSON parameters for model, input text, voice, response_format, and speed. You can send up to 4096 characters per request. For longer scripts, split the text into chunks, generate each audio file separately, and concatenate them. This approach ensures consistent quality and avoids character limit restrictions while maintaining the intended narrative flow.
API Integration
To begin, configure your HTTP client to send a POST request to the speech endpoint. Include your API key in the Authorization header as Bearer <your-key>. The system processes requests sequentially, so under heavy load, you may experience slight queuing delays. For production environments, implement exponential backoff for retry logic to handle transient network issues gracefully.
The API returns the audio file directly in the response body. You can stream this data directly to your storage or processing pipeline. Ensure your client handles binary responses correctly, as the output is raw audio data rather than a JSON object containing a URL.
- Endpoint: POST /v1/audio/speech
- Auth: Bearer token in header
- Base URL: https://api.ah777.info/v1
- Rate limit: 60 requests/minute
Voice Parameter Setup
Select a voice preset that aligns with your campaign’s tone. For example, use aria for warm narration or felix for energetic promos. You can also adjust the speed parameter between 0.25 and 4.0 to match the desired pacing. Faster speeds work well for quick sales pitches, while slower speeds enhance storytelling clarity.
If the default language detection is inaccurate for non-English Latin scripts, explicitly set the language parameter using the ISO code. This ensures the synthetic voice pronounces words correctly. Supported languages include English, Spanish, German, French, and others listed in our documentation.
- Voice presets: aria, nova, luna, sage, felix, milo, atlas, orion
- Speed range: 0.25–4.0
- Language code: optional ISO code
Format Selection
Choose the output format based on your distribution needs. MP3 is ideal for web and mobile playback due to its small file size. WAV provides uncompressed quality for broadcast masters. OPUS and FLAC offer efficient compression with high fidelity, while PCM is suitable for raw audio processing.
Each format has specific use cases. For radio spots, WAV is often preferred for its compatibility with broadcast equipment. MP3 is sufficient for digital ads. Ensure your playback system supports the chosen format to avoid playback issues.
- Formats: mp3, wav, opus, flac, pcm
- MP3: web/mobile
- WAV: broadcast
- OPUS/FLAC: high fidelity

Cost Efficiency
SpotLogic charges $0.01 per 1,000 characters, including spaces and punctuation. This predictable rate simplifies budgeting for high-volume radio campaigns, as costs scale linearly with script length without hidden fees for processing time.
Character Count Impact
Every character counts toward the final bill. A 4,000-character script costs $0.04. Short bursts may feel cheap, but cumulative usage adds up quickly during multi-voice productions. Splitting long texts into 4,096-character chunks ensures consistent pricing without exceeding API limits.
- Space and punctuation count as characters.
- Standard rate: $0.01 per 1,000 characters.
- No minimum spend or monthly fees.
Volume Discounts
There are no tiered discounts or volume rebates. Pricing remains flat at $10 per million characters regardless of usage volume. This simplicity helps agencies forecast exact costs for large-scale radio spot campaigns without complex calculation tables.
Budget Planning
Start with the $0.50 trial to test voice suitability. Fund accounts with USDT (TRC-20) for instant credit. Since failed requests are free, you can experiment with different voice models without financial risk. Balance never expires, allowing flexible campaign scheduling.
- Use trial credit to test voices.
- Top up with USDT (TRC-20).
- Failed requests cost nothing.
Quality Assurance
Ensuring broadcast readiness requires selecting the correct output format and verifying audio integrity before integration into your campaign workflow. SpotLogic provides multiple formats to suit different delivery standards, from compressed MP3 for web use to lossless FLAC for archival masters. Understanding these options helps agencies maintain consistent quality across various radio and digital platforms without unnecessary re-encoding.
Sound clarity is paramount for synthetic voices used in advertising. Each generated file undergoes rigorous processing to ensure crisp articulation and consistent volume levels. The API returns high-fidelity audio that meets standard broadcast specifications, allowing producers to integrate the tracks directly into their editing timelines with minimal post-production adjustments.
Audio Formats
The API supports MP3, WAV, Opus, FLAC, and PCM formats. Choose MP3 for efficient web delivery or WAV/FLAC for lossless quality in professional editing suites. PCM is ideal for raw data processing.
Selecting the right format depends on your final distribution channel. Lossless formats preserve the full nuance of the synthetic voice, while compressed formats reduce file size for faster streaming.
- MP3: Best for web and quick delivery
- WAV/FLAC: Ideal for professional editing and archival
- PCM: Raw audio for custom processing
Sound Clarity
Each voice preset is optimized for clear articulation, ensuring that every word in your radio spot is understood. The synthesis engine reduces background hiss and ensures consistent volume, so your ad sounds polished from the first second.
Clarity is maintained even at higher speeds. The voices remain intelligible up to 4.0x speed, which is crucial for fast-paced promotional spots where time is limited.
Background Noise
The generated audio is clean and free of ambient noise, as it is synthesized digitally. This eliminates the need for extensive noise reduction during post-production, saving time and budget.
Since the audio is synthetic, there are no room reflections or microphone artifacts. This makes it easy to mix the voice with music and sound effects in your DAW.
Common Mistakes
Agencies often waste budget on rejected spots by mismatching voice personality to the creative brief. A calm narrator for a high-energy promo can feel disjointed, while an upbeat voice in a serious context undermines credibility. Always align the voice preset with the intended emotional tone of the spot before generating audio.
Technical oversights also derail production. Ignoring speed limits can result in unnatural pacing, while overlooking language codes may cause the engine to misidentify the script, leading to incorrect pronunciation or fallback to English for non-English Latin text.
Wrong Tone Selection
Selecting a voice that contradicts the brand message is a common error. Using Felix for a somber documentary or Luna for a fast-paced sale can confuse listeners. Ensure the voice preset matches the specific genre and emotional requirement of the ad.
For example, Atlas provides a neutral news tone suitable for factual updates, while Orion’s deep documentary voice suits longer narrative ads. Mismatching these leads to a lack of authenticity, which listeners detect immediately.
- Match voice preset to emotional tone
- Avoid genre-voice mismatches
- Test voice in context
Ignoring Speed Limits
The API allows speeds from 0.25 to 4.0, but extreme values can distort clarity. Fast-paced promos might become unintelligible if pushed beyond natural limits. Conversely, overly slow narration can bore listeners in short spots.
Keep speeds within recommended ranges for radio spots. Typically, 1.0–1.25 works well for most ads, ensuring clear articulation without sacrificing energy.
- Stay within 0.25–4.0 range
- Test clarity at high speeds
- Avoid unnatural pacing
Overlooking Language Codes
If the language field is omitted, the engine guesses based on script. Latin text defaults to English, which causes errors for other languages like Dutch or Swedish. Always specify the ISO code for non-English texts.
This ensures accurate pronunciation and intonation. For multilingual campaigns, explicitly setting the language code prevents the engine from defaulting to English for Latin-script languages.
- Set language ISO code
- Prevent default English fallback
- Ensure accurate pronunciation
Case Studies
Case studies demonstrate how SpotLogic’s synthetic voices meet specific advertising needs. By adjusting speed and voice presets, agencies can align audio tone with brand identity without the overhead of hiring multiple voice actors.
These examples highlight the practical application of our API for radio spots, showing how technical parameters like speed and language codes directly impact the final broadcast quality.
Retail Campaign
A national retail chain used Aria for warm, clear narration in their holiday sales spots. The voice’s clarity ensured promotional details were audible even during high-noise periods. By setting the speed to 1.2x, the agency compressed a 30-second script into a tight 25-second spot, saving broadcast time and reducing costs per impression.
Characters were counted precisely, ensuring the $0.01 per 1,000 characters rate remained predictable. The resulting audio was broadcast-ready, requiring no additional editing.
- Voice: Aria
- Speed: 1.2x
- Format: MP3
Tech Launch
- Voice: Atlas
- Language: en
- Format: WAV
Local Business Ad
A local car dealership used Felix for energetic, promo-style announcements. His upbeat tone matched the fast-paced nature of limited-time offers. The API’s 60 requests per minute limit allowed the team to generate multiple variations quickly for A/B testing.
Each variation was under the 4,096 character limit, ensuring single-request processing and immediate delivery. This efficiency reduced the turnaround time from script to air-ready audio to under two minutes.
- Voice: Felix
- Speed: 1.5x
- Model: tts-1
Final Recommendations
Selecting the right voice is the final step in ensuring your radio spot resonates. Avoid guesswork by aligning voice traits with your specific campaign goals.
Use these curated picks to streamline your production workflow and maintain consistent brand audio identity across all channels.
Top Picks for General Ads
For broad-reach campaigns, Aria offers a warm, clear narrator style that appeals to diverse demographics. For energetic promotions, Felix delivers an upbeat tempo that drives immediate attention.
- Aria: Warm, clear narrator
Top Picks for Niche Ads
Tech products benefit from Atlas’s neutral, news-style delivery, conveying reliability. Food and beverage ads often pair well with Luna’s soft, storytelling approach to evoke comfort.
- Atlas: Neutral, news
Testing Strategy
Run A/B tests using the API’s 0.25–4.0 speed range to find optimal pacing. Generate multiple variations of the same script with different voices to identify the highest-converting option before scaling.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the right format depends on your final distribution channel.
23 languages
Any voice speaks any of these languages.
