Frequently asked questions
Which voice is best for meditation?
Luna is suitable for meditation with her soft, storytelling tone. Sage is suitable for guided sessions with a calm, instructional voice. Both provide clear, steady delivery without excessive energy, making them reliable choices for fitness and meditation app audio.
Can I mix voices in one audio?
No. Each API request generates audio from a single voice preset. To mix voices, you must generate separate audio files for each voice and join them using your own audio processing tools or library.
Do voices sound different in other languages?
The same eight voice presets speak all 23 supported languages. While the voice character remains consistent, the accent and pronunciation adapt to the target language. You can optionally set the language ISO code to ensure correct generation.
Is there a difference between tts-1 and tts-1-hd?
Both models use the same engine and have identical pricing. The distinction is purely in the model identifier used in the API request. There is no functional or quality difference between tts-1 and tts-1-hd for your use case.
Are the voices natural sounding?
The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They carry an inaudible watermark marking them as synthetic speech. They sound like clear narrators.
Do voices change over time?
The voice presets are static and do not change over time. They are based on fixed recordings from LibriTTS-R and LibriVox. Your generated audio will remain consistent across different requests and time periods using the same voice parameter.
Can I request a new voice?
No. We do not offer custom voice cloning or voice design. You must choose from the eight available presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion. New voices are not added on demand.
Is there a voice for children?
No. There is no specific child voice among the eight presets. All voices are adult presets. You can adjust the speed parameter between 0.25 and 4.0, but this does not change the fundamental voice character or pitch significantly.
Do voices have accents?
Voices adapt their pronunciation to the language specified or detected. For example, Aria speaks English with a standard accent, while Luna speaks French with appropriate French pronunciation. The voice character remains consistent, but the accent matches the language.
How do I preview voices?
You can generate short test texts via the API to hear each voice. Use the GET /v1/voices endpoint to list available voices and their details. There is no built-in player; you must generate audio files to listen.
Are voices gender-specific?
The presets are categorized as female (Aria, Nova, Luna, Sage) or male (Felix, Milo, Atlas, Orion). However, they are designed for specific tones like 'calm' or 'energetic' rather than strict gender roles. You can choose based on the desired tone.
Can I adjust voice speed?
Yes. You can set the speed parameter between 0.25 and 4.0. This allows you to slow down narration for meditation or speed up instructions for fitness routines. The default speed is 1.0, representing normal speech rate.
Is the audio quality consistent?
Quality is consistent as all requests use the same engine. However, under load, requests may queue, potentially increasing generation time. The audio format and voice characteristics remain stable regardless of request volume or queue position.
Do voices sound robotic?
No. The voices are based on licensed human recordings from LibriTTS-R and LibriVox. They avoid the typical robotic monotone of older TTS systems. Each generated file includes an inaudible watermark to identify it as synthetic speech.
Female Voices Overview
FitVoice offers three female presets designed for fitness and meditation workflows. Aria provides a warm, clear narration style ideal for steady app guidance. Nova delivers a bright, upbeat tone suitable for high-energy content. Luna specializes in soft, storytelling delivery for calming experiences.
Aria: warm narrator
Aria is designed for clear, articulate narration. Her tone is warm and steady, making her suitable for general fitness updates or introductory app content. She handles mixed scripts well, maintaining clarity across different languages.
- Best for: General narration, app intros, mixed-language scripts
- Limitation: No custom emotion tagging or SSML support
Nova: bright and upbeat
Nova brings a bright, energetic quality to your audio. She is ideal for morning routines, cardio prompts, or upbeat motivational segments. Her delivery remains consistent even at higher speeds, ensuring clarity during fast-paced workout sessions.
- Best for: Morning routines, cardio prompts, upbeat motivation
- Limitation: No voice cloning or custom pronunciation lexicons
Luna: soft storytelling
Luna offers a soft, calming presence perfect for meditation and sleep stories. Her gentle tone helps users relax, making her a strong choice for guided meditation tracks. She supports all 23 languages, allowing for diverse meditation content. Any voice can speak any of these languages.
- Best for: Guided meditation, sleep stories, relaxation apps
- Limitation: No real-time streaming or WebSocket support
Male Voices Overview
The male voices offer distinct tones for fitness and meditation apps. Felix delivers energetic promos, Milo provides a friendly conversational tone, and Atlas ensures neutral, professional updates.
Felix: energetic promo
Felix is designed for high-energy content. His voice is ideal for promo messages and cardio session cues where an upbeat tempo is required.
- Ideal for cardio sessions
- Promo-ready tone
Milo: friendly conversational
Milo offers a warm, approachable sound. He works well for coaching apps and instructional segments that benefit from a personal touch.
- Coaching-friendly tone
- Conversational style
Atlas: neutral news
Atlas provides a neutral, professional delivery. He is suitable for fitness stats, news-style updates, and content requiring clarity without emotional bias.
- Neutral delivery
- Professional updates
Voice: Luna
Luna offers a soft, storytelling voice ideal for guided meditation. Her calm delivery helps users relax and focus during sessions.
She is particularly effective for sleep stories, creating a soothing atmosphere that encourages rest without distraction.
Best for guided meditation
Luna’s gentle pacing and warm tone make her perfect for leading mindfulness exercises. She helps maintain a tranquil environment for users.
Soft and calming tone
Her voice is designed to be non-intrusive, allowing listeners to focus on their breathing or body scans without feeling rushed.
Ideal for sleep stories
Luna’s soothing narrative style is well-suited for bedtime stories, helping users drift off to sleep with a consistent, gentle rhythm.
Voice: Sage
Sage is engineered for instructional content, offering a calm and clear delivery that keeps users focused without distraction. Its steady pace makes it ideal for guided sessions where clarity matters more than flair.
In yoga classes, Sage provides consistent, soothing narration that helps maintain rhythm and breathing patterns. The voice remains neutral enough to fit various styles, from gentle restorative flows to structured vinyasa sequences.
Best for instructional content
Sage delivers instructions with a steady, unhurried tone that reduces cognitive load. This clarity ensures users understand cues precisely, which is critical when guiding physical movements or mindfulness exercises.
- Ideal for step-by-step workout guides
- Maintains focus during complex sequences
Calm and clear delivery
The voice avoids emotional spikes, providing a consistent auditory environment. This stability helps users relax and concentrate on their practice without being distracted by vocal variations.
- No sudden tone changes
- Consistent volume and pace
Good for yoga classes
Sage’s gentle narration supports both beginner and advanced practitioners. Its clarity ensures that alignment cues and breath instructions are heard clearly, enhancing the overall experience of a yoga session.
Users appreciate the non-intrusive nature of the voice, which blends seamlessly with background music or silence.
- Supports mindful movement
- Clear alignment cues
Voice: Atlas
Atlas provides a neutral, professional tone ideal for fitness apps delivering data-driven content. Its clear, news-style delivery ensures listeners focus on the information rather than the voice character, making it perfect for structured audio updates.
The voice handles factual statements with precision, avoiding emotional bias that might distract from performance metrics or health statistics.
Best for news-style updates
Atlas delivers information with a steady, journalistic rhythm. This consistency works well for daily fitness summaries or program announcements where clarity matters more than emotional engagement.
Neutral and professional
The voice avoids distinct personality traits, offering a clean auditory backdrop. This neutrality ensures that the content, whether it’s workout instructions or progress reports, remains the primary focus for the user.
Good for fitness stats
Use Atlas for reading out numerical data, such as step counts, heart rate zones, or calorie totals. Its precise articulation ensures that digits and technical terms are understood clearly without misinterpretation.
The straightforward delivery style reduces cognitive load, allowing users to quickly absorb performance metrics during or after a session.
- Ideal for reading numerical data
- Clear articulation of technical terms
- Reduces cognitive load for users
Voice: Felix
Felix brings an energetic and fast delivery style, making him ideal for high-intensity environments. His voice cuts through background noise with clear, driving cadence, keeping users motivated during intense physical activity.
Best for high energy workouts
Felix’s dynamic tone is designed to sustain momentum. His energetic delivery matches the pace of vigorous exercise, ensuring audio cues remain engaging without becoming fatiguing over long sessions.
- High-energy vocal tone
- Fast-paced delivery
- Motivational cadence
Energetic and fast
The voice processes text at a brisk rate, aligning with the rapid nature of interval training. This speed helps maintain the rhythm of your app’s audio without lagging behind the user’s physical pace.
- Rapid articulation
- Upbeat rhythm
- Sustained energy
Good for cardio sessions
Cardio routines require consistent auditory stimulation. Felix’s consistent energy level supports long-duration activities like running or cycling, providing a reliable companion voice that doesn’t lose intensity.
- Steady motivation
- Consistent volume
- Endurance support
Voice: Milo
FitVoice offers a reliable text-to-speech API designed for product teams building fitness and meditation applications. Our straightforward integration allows you to convert scripts into audio files efficiently, supporting 23 languages and eight distinct voice presets. With a flat rate of $0.01 per 1,000 characters and no premium tiers, you can scale your audio content without complex pricing structures.
Best for conversational tone
Milo delivers a natural, conversational quality that feels less like a robot and more like a real person speaking. This makes it ideal for apps that rely on dialogue or interactive feedback, keeping users engaged without the stiffness of traditional synthetic voices.
Friendly and approachable
The voice is warm and inviting, reducing the friction in user experiences. Whether guiding someone through a workout or providing encouragement, Milo’s tone remains consistent and pleasant, helping to maintain a positive atmosphere within your application.
Good for coaching apps
Coaching platforms benefit significantly from Milo’s clarity and ease. It handles instructional text well, ensuring that cues and tips are delivered clearly. This reliability helps product teams focus on feature development rather than audio quality issues.
- Supports texts up to 4096 characters per request
- Available in all 23 supported languages
- No emotion tags or SSML required for basic use

Voice: Aria
Aria delivers a warm, clear narration style ideal for fitness and meditation apps. Her tone is articulate and steady, making complex scripts easy to follow without sounding robotic.
Best for clear narration
Aria’s voice is designed for clarity. She maintains a consistent pace, ensuring that instructions are understood clearly. This makes her suitable for guided workouts where precise timing matters.
- Clear enunciation
- Steady pacing
- No filler words
Warm and articulate
Her delivery is warm yet professional. Users find her voice comforting during meditation sessions. It avoids being too casual or too formal, striking a balance suitable for daily routines.
- Comforting tone
- Professional yet approachable
- Consistent volume
Good for audiobooks
Aria works well for longer text formats. Her voice remains engaging over extended periods. This reduces listener fatigue during long meditation tracks or fitness program narratives.
- Long-form content
- Low listener fatigue
- Engaging delivery
Voice: Nova
Nova delivers a bright, positive tone that energizes listeners. Her clear, upbeat cadence makes her ideal for content requiring enthusiasm without sounding artificial.
Best for upbeat content
Nova’s energetic delivery works well for short motivational clips or app notifications. Her voice maintains clarity even at higher speeds, ensuring messages are received without strain.
Bright and positive
The preset is designed to convey optimism. This makes it suitable for progress updates or daily affirmations where a cheerful tone enhances user engagement.
Good for morning routines
Use Nova for morning check-ins, weather updates, or workout reminders. Her tone matches the start-of-day energy, helping users transition smoothly into their daily fitness or meditation practice.
Voice: Orion
Orion offers a deep, authoritative presence ideal for premium fitness content and documentary-style narration. His voice conveys weight and seriousness, making him suitable for high-end app experiences where tone matters as much as clarity.
Use Orion for introductory trailers, membership onboarding, or guided meditations that require a grounded, cinematic feel. His distinct timbre helps distinguish premium tiers from standard workout tracks.
Best for deep documentaries
Orion’s rich bass tones create a sense of importance and depth. This makes him perfect for narrating detailed fitness histories, athlete profiles, or long-form meditation journeys where listener immersion is key.
- Ideal for long-form audio content
- Creates a cinematic atmosphere
- Engages listeners in narrative-driven apps
Deep and authoritative
His voice commands attention without shouting. This authority is valuable for premium coaching segments or serious health advice where trust and stability are paramount.
Good for premium content
Pair Orion with higher-quality audio formats like FLAC for maximum impact. His distinct sound profile justifies premium subscriptions by offering a unique auditory identity.
Language Support
Text-to-speech synthesis supports 23 languages, covering major markets for meditation and fitness applications. This range ensures your app can serve a global audience without needing multiple voice providers.
The API allows you to select any of the 8 preset voices regardless of the target language. This flexibility simplifies your development process and maintains consistent audio quality across different regions.
23 languages supported
Our API supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
These languages cover most use cases for meditation apps, fitness trackers, and instructional guides. You can generate content in any of these languages using the same API endpoint.
- Arabic, Chinese, Danish, Dutch, English
- Finnish, French, German, Greek, Hebrew
- Hindi, Italian, Japanese, Korean, Malay
- Norwegian, Polish, Portuguese, Russian, Spanish
- Swahili, Swedish, Turkish
Any voice speaks any language
Each of the 8 voices can pronounce text in any of the 23 supported languages. You do not need to swap voices based on language; the engine handles pronunciation automatically.
This feature ensures consistent character personality across your app, whether users are listening to a yoga guide in English or a news update in Spanish.
Default to English for Latin
If you do not specify a language in the request, the system guesses it from the script. Latin-script text defaults to English.
For non-English Latin-script text, such as Spanish or French, you should set the language parameter explicitly. This prevents mispronunciation and ensures accurate accent delivery.
Technical Constraints
FitVoice provides straightforward synthetic speech without the complexity of advanced markup. Our API returns clean audio files, which simplifies integration for fitness and meditation apps that do not require fine-grained control over every phoneme or pause.
No voice cloning
We do not offer custom voice cloning. You cannot upload your own voice or design a new one. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark to identify it as synthetic speech.
No emotion tags
The voices deliver their lines with consistent tonal characteristics. There are no emotion tags to modulate feelings like happiness or sadness. For example, Luna remains soft and storytelling-oriented regardless of context, while Felix stays energetic.
No SSML support
We do not support Speech Synthesis Markup Language (SSML). You cannot use XML tags to control pauses, pronunciation, or emphasis. If you need specific pacing, you can adjust the speed parameter between 0.25 and 4.0.
Pricing for Voices
Every voice in our API costs the same, regardless of which preset you choose. You do not pay extra for deeper tones or clearer narration; the engine and pricing are uniform across all eight options. This structure simplifies budgeting for fitness and meditation apps, allowing you to switch voices without worrying about variable rates.
Same price for all voices
All voices share a single rate card. Whether you select Aria for warm narration or Orion for deep documentaries, the cost per character remains identical. This ensures predictable expenses as your app scales, with no hidden tiers or voice-specific premiums.
$0.01 per 1k chars
The standard rate is $0.01 per 1,000 characters, which includes spaces and punctuation. Failed requests are free, and you can start with a $0.50 trial credit valid for seven days. Top-ups via USDT (TRC-20) are processed automatically, ensuring your account stays active without manual invoicing.
- Rate: $0.01 per 1,000 characters
- Failed requests are free
- Trial credit: $0.50 (7 days)
No premium voices
There are no premium tiers or exclusive voice unlocks. All eight presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are available to every account at the same base price. You can experiment with different tones for your meditation scripts or fitness updates without any additional cost.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The voice handles factual statements with precision, avoiding emotional bias that might distract from performance metrics or health statistics.
23 languages
Any voice speaks any of these languages.
