Frequently asked questions
Which voice is most professional for compliance?
Atlas is the neutral, news-style voice suitable for compliance materials. It delivers clear, consistent narration without emotional bias. Sage is also suitable for instructional compliance content. Both voices maintain a professional tone suitable for corporate training environments where clarity and authority are prioritized over personality.
Can I use the same voice for all languages?
Yes, every voice can speak all 23 supported languages. You can use Aria for English, French, and German modules without changing the voice preset. The system handles language detection or you can specify the ISO code. This consistency helps maintain brand identity across your multilingual training library.
Is there a difference in quality between voices?
All eight voices use the same underlying engine and quality standards. The difference lies in their tonal presets: Aria is warm, Nova is bright, and Atlas is neutral. You choose based on the desired mood of your training content, not on a hierarchy of audio fidelity or production value.
How do I choose between Aria and Luna?
Aria offers a warm, clear narrator style suitable for general corporate training. Luna provides a soft, storytelling tone better for engaging narratives or onboarding stories. Choose Aria for direct instruction and Luna when you want to create a more immersive, narrative-driven learning experience for your employees.
Which voice is best for technical training?
Sage is suitable for technical training, offering a calm, instructional tone that helps learners focus on complex information. Atlas is also suitable for technical specifications, providing a neutral, news-like delivery. Both voices ensure clarity without distracting emotional inflections, making them reliable choices for detailed educational content.
Can I mix voices in a single training module?
The API generates audio per request, so you can mix voices by sending multiple requests. Combine outputs from different voices to create a single module. You will need to join the audio files yourself. This allows you to assign specific voices to different characters or sections of your training.
Do voices sound different in different languages?
The voices retain their core tonal characteristics across all 23 supported languages. However, natural pronunciation nuances may vary slightly by language. The same voice preset maintains its personality, whether speaking English, Japanese, or Spanish, ensuring consistent character recognition for your learners regardless of the language used.
Is Milo suitable for formal presentations?
Milo is described as friendly and conversational, which may be too casual for strict formal presentations. Atlas or Sage are better choices for formal settings. Use Milo for informal updates or conversational training modules. Reserve the neutral or instructional voices for high-stakes or traditional corporate presentation styles.
What is the difference between Atlas and Orion?
Atlas is a neutral, news-style voice suitable for general corporate content. Orion is a deep, documentary-style voice ideal for immersive, serious narratives. Both are male voices but serve different tones. Use Atlas for standard training and Orion when you need a more dramatic, authoritative documentary feel.
Can I adjust the speed of Felix for promos?
Yes, you can adjust Felix's speed between 0.25 and 4.0. Felix is energetic and promo-focused, so increasing speed can enhance urgency. Decreasing speed ensures clarity. This flexibility allows you to tailor the pacing of your promotional training materials to match the energy and length of your content.
Are the voices based on real human recordings?
Yes, every generated file carries an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R, derived from LibriVox public-domain audiobook readings. While the source material is human, the output is synthesized audio, not a direct recording of the original speaker.
Do I need to pay more for the HD model?
No, there is no price difference between the models. Both tts-1 and tts-1-hd use the same engine and price. You can choose either model without affecting your cost per character. The pricing remains $10 per 1 million characters regardless of which model you select for your requests.
Which voice is easiest to understand for non-native speakers?
Atlas, the neutral news voice, is often easiest for non-native speakers due to its clear, standard delivery. Sage is also good for instructional clarity. Avoid highly expressive voices like Nova or Luna if clarity is the priority. Test with your specific audience, as individual preference may vary.
Can I use Luna for storytelling in HR?
Yes, Luna is described as soft and storytelling-oriented, making it perfect for HR narratives. Use it for onboarding stories, company history, or employee spotlights. Its gentle tone enhances engagement without being distracting. It helps create an emotional connection with your training content in a professional yet approachable way.
Aria: Warm and Clear Narrator
Aria brings a warm, clear narrator quality to your corporate training materials. Her voice is designed to aid comprehension through clear enunciation, making complex concepts easier to grasp for large teams. This makes her an ideal choice for soft skills and empathy training where tone matters.
Ideal for soft skills and empathy training
Aria’s warm tone helps learners engage with emotional intelligence modules. Her clear delivery ensures that nuanced interpersonal skills are conveyed accurately without distraction.
Clear enunciation aids comprehension
Her distinct articulation supports better retention of key learning points. This clarity is particularly useful when training diverse groups with varying language proficiencies across our 23 supported languages.
Suitable for welcome and intro modules
Aria sets a welcoming tone for new hire onboarding. Her consistent, friendly narration makes introductory content feel personal and accessible, helping employees feel connected from day one.
Nova: Bright and Upbeat
Nova delivers a bright, upbeat energy that transforms standard corporate audio. Her clear, positive tone keeps learners engaged and alert, making her an excellent choice for content that needs to maintain high interest levels throughout the session.
Perfect for engaging and energetic content
Nova’s vibrant delivery ensures that training modules remain lively and engaging. Her consistent energy helps sustain listener attention, particularly during longer sessions where monotony might otherwise set in.
Good for sales training and motivation
For sales teams, Nova’s enthusiastic style mirrors the drive needed in customer-facing roles. Her tone reinforces motivational messages, helping to energize teams during pitch practice or performance reviews.
Adds positivity to standard procedures
Even routine procedural updates benefit from Nova’s cheerful presence. By adding a touch of positivity to standard operating procedures, she makes dry content feel more approachable and less tedious for employees.
Note: While Nova adds character, she does not offer custom voice cloning or emotion tags, so her baseline upbeat style remains consistent across all generated audio.
bullets
Luna: Soft Storytelling Voice
Luna delivers a soft, storytelling voice ideal for narrative-based learning cases. Her gentle tone reduces listener fatigue during extended modules, making her perfect for history or culture content where engagement matters.
Best for narrative-based learning cases
Luna’s warm delivery transforms standard text into engaging stories. This approach helps learners retain information better by connecting emotionally with the material. Her clear enunciation ensures that complex narratives remain easy to follow, even for diverse audiences.
- Enhances retention through narrative structure
- Clear enunciation aids comprehension
- Warm tone builds connection
Gentle tone reduces listener fatigue
Long training sessions can become draining. Luna’s soothing voice keeps listeners engaged without causing ear fatigue. This makes her suitable for multi-part courses where consistency is key.
- Reduces cognitive load
- Soothing delivery for long modules
- Consistent tone across sessions
Ideal for history or culture modules
Use Luna for history or culture modules where context and nuance matter. Her voice adds depth to historical events or cultural practices, making learning feel immersive rather than just informational.
- Adds depth to historical context
- Immersive cultural storytelling
- Engaging narrative style
Sage: Calm and Instructional
Sage is designed for clarity and precision, making it the ideal choice for technical documentation that requires clear instruction. Its calm, neutral tone ensures that listeners remain focused on the content without distraction, which is essential for complex procedures.
Great for step-by-step technical guides
The voice’s steady pacing helps learners follow multi-step processes without feeling rushed. This consistency reduces cognitive load, allowing HR teams and instructional designers to deliver complex information effectively.
Neutral tone keeps focus on instructions
By avoiding emotional highs or lows, Sage ensures the message remains objective. This is particularly useful for IT training where the focus should be on accuracy rather than personality.
Suitable for software tutorials and IT training
Sage works well for software tutorials, providing a reliable auditory guide for users navigating new systems. Its clarity supports both new hires and experienced employees alike.
- All voices support 23 languages for global teams.
- Speed adjustment allows customization for different learning speeds.
- Formats include MP3, WAV, OPUS, FLAC, and PCM.
Felix: Energetic Promo Style
Felix brings high energy to your internal communications, making standard updates feel like exciting announcements. His preset delivers a crisp, promotional tone that captures attention quickly, ensuring employees actually listen to important news rather than skimming over it.
This voice excels when you need to convey enthusiasm without sacrificing clarity. It transforms routine messages into engaging content, keeping your team motivated and informed with a consistent, upbeat brand voice.
Used for promotional internal comms
Use Felix for newsletters, product launches, or company-wide achievements. His clear enunciation ensures that key details aren’t lost in the energy, making complex information accessible to large teams across multiple languages.
- Ideal for quarterly result announcements
- Perfect for new tool launches
- Great for recognition programs
High energy for event announcements
When promoting town halls, webinars, or holiday parties, Felix adds a sense of occasion. His dynamic delivery encourages participation and reduces the perception of mandatory meetings by framing them as engaging events.
- Webinar invitations
- Holiday party invites
- Team-building event promos
Engaging for marketing team updates
Marketing teams often struggle to maintain consistent tone across channels. Felix provides a reliable, energetic baseline for internal marketing updates, ensuring that strategic shifts or campaign highlights are delivered with the right level of enthusiasm and professionalism.
- Campaign launch updates
- Brand guideline changes
- Social media strategy shifts
Milo: Friendly and Conversational
Milo brings a friendly, conversational tone to your corporate training materials. As one of eight available presets, he delivers clear, approachable audio that helps new hires feel welcomed rather than instructed. His natural delivery reduces the stiffness often found in standard onboarding modules.
This voice excels in scenarios where relatability matters. Whether guiding employees through casual Q&A sessions or supporting their initial transition into the company, Milo’s engaging style keeps learners attentive without demanding high energy.
Best for casual onboarding and Q&A
Milo’s conversational style makes complex onboarding flows feel like a chat with a colleague. His clear enunciation aids comprehension, ensuring that new employees grasp essential information without feeling overwhelmed by formal narration.
Use Milo for welcome videos or introductory modules where a warm tone sets the right culture from day one.
- Ideal for welcome and intro modules
- Clear enunciation aids comprehension
Approachable tone for new hire support
New hires often face information overload. Milo’s soft, storytelling-adjacent delivery helps reduce listener fatigue during long onboarding sequences. His voice feels supportive rather than authoritative, encouraging questions and engagement.
This approachability is crucial for HR teams aiming to build a positive first impression through audio content.
- Good for new hire support
- Reduces listener fatigue
Good for feedback and coaching modules
When delivering feedback or coaching tips, Milo’s friendly demeanor ensures the message lands positively. His neutral yet warm tone keeps the focus on the content, making it suitable for various learning contexts.
Combine Milo with speed adjustments (0.25–4.0) to tailor the pacing for different types of coaching content.
- Good for feedback and coaching modules
- Neutral tone keeps focus on instructions
Atlas: Neutral News Style
Atlas provides a neutral, news-style voice ideal for corporate training. Its balanced tone ensures clarity without distracting from the message.
This preset is particularly effective for delivering consistent audio content across large teams and diverse departments.
Standard choice for compliance training
Atlas is the standard choice for compliance training due to its clear, professional delivery. The voice maintains a steady pace, making regulatory details easy to follow.
Its neutral tone ensures that the focus remains on the content rather than the presenter's personality.
- Ideal for legal and regulatory updates
- Maintains consistent pacing for complex rules
Objective tone for policy updates
For policy updates, Atlas delivers an objective tone that conveys authority without bias. This helps employees understand new guidelines clearly.
The voice's clarity reduces ambiguity, ensuring that important changes are communicated effectively.
- Clear delivery of new policies
- Reduces ambiguity in communication
Widely accepted in corporate environments
Atlas is widely accepted in corporate environments for its professional and reliable sound. It fits seamlessly into various training modules.
Its versatility makes it a go-to choice for HR teams and instructional designers seeking consistent audio quality.
- Professional and reliable sound
- Fits seamlessly into various training modules

Orion: Deep Documentary Voice
Orion delivers a deep, documentary-style voice that lends immediate authority to your corporate audio content. Its rich tone is specifically engineered for serious, authoritative content where clarity and gravitas are paramount, ensuring the message is received with the appropriate weight and professionalism.
This preset is particularly effective for high-stakes communications where listener engagement must be maintained through a compelling, narrative-driven delivery. It transforms standard text into a polished audio experience that commands attention.
Used for serious, authoritative content
Orion’s distinct depth makes it the ideal choice for formal announcements or executive messages. The voice provides a neutral yet commanding presence, ensuring that complex corporate directives are delivered with clarity and seriousness without sounding robotic.
- Ideal for board-level updates
- Enhances perceived credibility of formal texts
- Reduces listener fatigue during long reads
Good for risk management and safety
In safety training and risk management modules, the tone must convey urgency and importance. Orion’s documentary style helps emphasize critical protocols, ensuring that employees retain key safety information without distraction from the voice's character.
- Clear enunciation aids comprehension
- Suitable for hazard warnings
- Professional tone for compliance docs
Adds weight to critical announcements
When communicating major company changes or critical updates, Orion adds necessary weight to the message. The deep timbre ensures the announcement stands out, signaling to the listener that the content requires focused attention.
Comparing Voice Characteristics
We compare distinct voice profiles to help HR teams select the right tone for their specific learning modules. Understanding these differences ensures that audio content matches the emotional context of the training material.
Aria vs. Luna: Clarity vs. Softness
Aria provides warm, clear narration with clear enunciation, making it ideal for soft skills and empathy training. Luna offers a soft, storytelling tone that reduces listener fatigue, perfect for narrative-based learning cases or history modules.
- Aria: Warm, clear narrator.
- Luna: Soft, storytelling voice.
Atlas vs. Orion: Neutral vs. Deep
Atlas delivers a neutral, news-style voice that serves as a standard choice for compliance training and policy updates. Orion provides a deep, documentary tone that adds weight to serious, authoritative content like risk management and safety announcements.
- Atlas: Neutral, news style.
- Orion: Deep, documentary voice.
Milo vs. Felix: Conversational vs. Energetic
Milo offers a friendly, conversational tone suitable for casual onboarding and new hire support. Felix brings energetic, promo-style energy, engaging for marketing updates or event announcements where high enthusiasm is required.
- Milo: Friendly, conversational.
- Felix: Energetic, promo style.
Matching Voices to Training Types
Aligning voice personalities with specific training goals enhances retention and engagement. By matching the tone of the audio to the content type, instructional designers can create a more immersive learning experience without the overhead of studio recording.
Use Sage for technical documentation
Sage offers a calm, instructional tone that keeps the focus on complex instructions. Its neutral delivery minimizes distraction, making it ideal for software tutorials and IT training modules where clarity is paramount.
- Ideal for step-by-step technical guides
- Maintains focus on instructions
- Suitable for software tutorials
Use Nova for sales and motivation
Nova brings a bright, upbeat energy that adds positivity to standard procedures. This preset is perfect for sales training and motivational content, helping to keep teams engaged and energized during onboarding or performance reviews.
- Perfect for engaging content
- Good for sales training
- Adds positivity to procedures
Use Orion for safety and compliance
Orion provides a deep, documentary-style voice that adds weight to critical announcements. Its serious tone is well-suited for risk management and safety protocols, ensuring that compliance training feels authoritative and memorable.
- Used for serious, authoritative content
- Good for risk management
- Adds weight to announcements
Technical Considerations for Selection
Selecting the right voice is only half the equation; technical configuration ensures your audio files integrate smoothly into your learning management system. The API supports 23 languages, allowing any voice to speak any supported language. If the language field is omitted, the system guesses from the script, defaulting to English for Latin text.
Adjusting speed between 0.25 and 4.0 works with all presets, letting you compress long modules or slow down complex instructions. You can export results in mp3, wav, opus, flac, or pcm, ensuring compatibility with diverse corporate audio players and bandwidth constraints.
All voices support 23 languages
Every voice preset can deliver content 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 flexibility is crucial for global training programs where consistency in tone matters more than specific regional accents.
When sending requests, explicitly set the language parameter for non-English Latin script text to avoid incorrect guessing. This prevents mispronunciations that could confuse learners during critical compliance or safety modules.
- Supports 23 distinct languages across all 8 voice presets
- Automatic language detection based on script if field is omitted
- Explicit language setting recommended for mixed-script content
Speed adjustment works with all presets
The speed parameter accepts values from 0.25 to 4.0, applying uniformly to all voice models. Slower speeds (e.g., 0.75) enhance comprehension for dense technical data or non-native speakers, while faster speeds (e.g., 1.5) help keep engaged learners moving through standard procedural content.
Requests are processed one after another, so under load a request may wait in a queue. Adjusting speed does not affect the character count billing, so you can optimize listening experience without increasing costs.
- Range: 0.25x to 4.0x speed
- Applies to all 8 voice presets
- Does not affect character-based billing
Formats available: MP3, WAV, OPUS, FLAC, PCM
Choose mp3 for efficient storage and broad web player compatibility, or wav for high-fidelity archival needs. Use opus for efficient compression, ideal for mobile LMS apps. flac offers lossless quality for professional editing, while pcm provides raw uncompressed audio for legacy systems.
All formats are generated via the same engine, whether using tts-1 or tts-1-hd. The choice affects file size and bandwidth usage, not the voice character or price. Ensure your LMS supports the chosen format before bulk generation.
- mp3: Efficient storage and broad web player compatibility
- wav: High-fidelity archival needs
- opus: Efficient compression for mobile/web delivery
- flac: Lossless quality
- pcm: Raw audio for legacy integrations
Pricing and Resource Usage
Our pricing is straightforward and consistent across all voice presets. You pay a flat rate of $10 per 1 million characters, which translates to just $0.01 per 1,000 characters. This simple structure allows HR teams to easily forecast audio production costs for large-scale training initiatives without hidden fees or tiered surprises.
The cost calculation is precise and includes all input text. Every character in your source material contributes to the total, ensuring transparent billing for every audio file generated.
All voices cost $10 per 1 million characters
Every voice preset, from Aria’s warm narration to Orion’s deep documentary tone, shares the same base rate. This uniformity means you can switch voices for different training modules without worrying about varying price points. Whether you are producing a short welcome message or a comprehensive compliance course, the unit cost remains constant.
- Flat rate: $10 per 1,000,000 characters
- Consistent pricing across all 8 voice presets
- No volume discounts or tiered pricing structures
No extra cost for HD model usage
You can choose between the standard "tts-1" model and the higher-fidelity "tts-1-hd" model without any price difference. Both engines deliver professional audio quality suitable for corporate environments, and the choice is purely based on your preference for audio richness rather than budget constraints.
- Both tts-1 and tts-1-hd models
- Identical pricing for standard and HD quality
- Choose based on preference, not cost
Character count includes spaces and punctuation
The character count for billing includes every element of your input text: letters, numbers, spaces, and punctuation marks. For example, a simple sentence like "Welcome to the new safety protocol" counts all 36 characters. This precise counting ensures you know exactly how much each request will cost before you send it.
- Spaces count as characters
- Punctuation marks are included
- Letters and numbers are counted normally
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This preset is particularly effective for delivering consistent audio content across large teams and diverse departments.
23 languages
Any voice speaks any of these languages.
