Frequently asked questions
Which voice is best for TikTok?
Nova is optimized for bright, upbeat content, while Felix suits energetic promos. Luna works well for storytelling, and Sage provides calm, instructional narration. Select the preset that matches your video’s tone. All eight voices are available for short-form video creation via the API endpoint.
Are the voices real humans?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. They are not direct recordings of specific human performances but synthesized audio files.
Can I clone a specific voice?
No custom voice cloning is offered. You cannot upload your own voice or design a custom voice. The service provides eight fixed presets. If you require a specific human voice, you must select the closest available preset from the standard library.
Do all voices support all languages?
Yes, every voice can speak any of the 23 supported languages. These include English, Spanish, German, French, Japanese, Korean, and others. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text.
Is there a difference in price for voices?
No, all eight voices use the same engine and price structure. The cost is $10 per 1 million characters, regardless of the voice selected. Both tts-1 and tts-1-hd models maintain this uniform pricing model for all voice presets.
Can I adjust the pitch?
Pitch adjustment is not available. You can adjust the speed between 0.25 and 4.0. The voices have fixed tonal characteristics. For example, Orion is deep, while Aria is warm. There are no pitch controls in the API request parameters.
Are the voices copyright-free?
The underlying recordings are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. However, each generated file carries an inaudible watermark identifying it as synthetic speech. You should verify usage rights for your specific commercial context, as the output is a synthetic derivative.
What is the difference between Aria and Nova?
Aria is a warm, clear narrator voice suitable for storytelling. Nova is a bright, upbeat voice ideal for energetic content. Both are female presets. Choose Aria for calm narration and Nova for lively, upbeat short-form video content requiring a cheerful tone.
Which voice is best for news?
Atlas is designed as a neutral, news-style voice. It provides a professional and clear delivery suitable for reporting. Other voices like Sage offer calm instructional tones, but Atlas is specifically categorized for news-style content delivery via the API.
Can I use these voices in ads?
Yes, the voices can be used in advertisements. The service provides synthetic audio files via HTTP. Since the source material is from public-domain or CC BY 4.0 recordings, they are suitable for commercial use, though you should review specific license terms.
Do the voices sound natural?
The voices are synthesized from licensed recordings and public-domain audiobook readings. They are designed to sound natural for content creation. Each file includes an inaudible watermark. They are not real human recordings but high-quality synthetic audio generated by the API.
Is there a female voice for deep tones?
No, the female voices (Aria, Nova, Luna, Sage) do not have deep tones. Orion is the deep, documentary-style voice, but he is male. If you need deep tones, select Orion. There is no female preset specifically categorized as deep.
How do I test voices before buying?
Sign in with Google to receive a free trial of $0.50 credit, valid for 7 days. This allows approximately 50,000 characters of generation. Use the API endpoint to generate audio with different voices. Accounts created with email do not receive this trial credit.
Are there new voices coming?
The product facts list exactly eight presets. There is no mention of upcoming voices or a roadmap for new additions. The current library includes Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. No new voices are promised or confirmed.
Voice Overview
ClipSpeak offers eight voice presets optimized for short-form video content. The catalog includes four female voices and four male voices, each engineered for specific tonal qualities. These presets ensure consistent audio output across TikTok, Reels, and Shorts pipelines without manual recording.
Female Voices
Aria provides a warm, clear narration suitable for explanatory content. Nova delivers a bright, upbeat tone ideal for energetic clips. Luna offers a soft, storytelling voice for narrative-driven videos. Sage presents a calm, instructional tone for tutorials and guides.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male Voices
Felix generates energetic audio optimized for promotional material. Milo provides a friendly, conversational tone for direct-to-camera styles. Atlas delivers a neutral, news-style delivery for factual content. Orion offers a deep, documentary voice for serious or cinematic contexts.
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Tone Differences
Each voice is derived from licensed recordings, ensuring distinct acoustic characteristics. The selection depends on the desired emotional resonance of the final video. Creators can match voice personality to content style for better audience retention.
Female Voice Options
The four female presets cover the primary tonal range required for short-form content. Each voice offers distinct characteristics suitable for different narrative styles, from warm narration to energetic commentary. Selecting the correct voice ensures consistent audio branding across TikTok, Reels, and Shorts videos.
All female voices support the full range of 23 languages. The system automatically detects language from the input script, though explicit language codes are recommended for non-English Latin text. This ensures accurate pronunciation regardless of the source material.
Aria
Aria delivers a warm, clear narrator tone ideal for storytelling or educational content. Her voice provides clarity without sounding robotic, making it suitable for voiceovers that require a professional yet approachable demeanor.
Use Aria for scripted explanations or personal stories where listener retention depends on a steady, engaging pace. She handles complex sentences well without sounding overly dramatic.
- Best for: Educational videos, stories
- Tone: Warm, clear
- Language support: All 23 languages
Nova
Nova offers a bright, upbeat delivery perfect for promotional content or quick tips. Her energetic tone captures attention immediately, making her ideal for short clips under 60 seconds.
Nova works well for product showcases, trend commentary, or high-energy montages. Her pacing feels natural for fast-paced editing styles common in social media feeds.
- Best for: Promos, quick tips
- Tone: Bright, upbeat
- Use case: High-energy shorts
Luna
Luna provides a soft, storytelling voice suited for calm or reflective content. Her gentle tone works well for ASMR-style videos, bedtime stories, or ambient background narration.
Choose Luna when the visual content is visually dense or when a soothing audio track is needed to reduce viewer fatigue during longer scrolling sessions.
- Best for: Relaxing content, stories
- Tone: Soft, storytelling
- Audio role: Background narration
Sage
Sage delivers a calm, instructional tone excellent for tutorials and how-to guides. Her voice maintains clarity and authority without dominating the visual narrative.
Sage is optimal for step-by-step instructions where clarity of speech is paramount. She ensures viewers understand procedural details without distraction from vocal inflections.
- Best for: Tutorials, how-to guides
- Tone: Calm, instructional
- Clarity: High
Male Voice Options
The male voice presets cover high-energy promo work, conversational dialogue, news delivery, and documentary narration. Each preset is engineered for specific short-form content styles, ensuring consistent audio quality across TikTok, Reels, and Shorts pipelines.
Felix
Felix delivers an energetic, promo-ready tone ideal for quick cuts and promotional clips. Its bright cadence maintains viewer attention during fast-paced editing sequences.
- Best for: Promotional clips, product highlights, energetic intros.
Milo
Milo provides a friendly, conversational voice suitable for direct-to-camera addresses or casual storytelling. It creates a relatable connection with the audience without sounding artificial.
- Best for: Vlog-style narration, casual explanations, personal brand content.
Atlas
Atlas offers a neutral, news-style delivery for factual content. Its steady pace and clear articulation make it ideal for information-heavy videos requiring trust and clarity.
- Best for: News updates, factual recaps, educational snippets.
Orion
Orion features a deep, documentary-style voice for immersive storytelling. Its rich timbre adds gravity to narrative-driven content, enhancing the emotional weight of visual scenes.
- Best for: Documentary-style clips, dramatic storytelling, cinematic intros.
Language Compatibility
ClipSpeak supports 23 languages, allowing creators to localize content for global audiences without recording new audio. The API detects language from script when unspecified, but explicit language codes ensure accuracy for non-English Latin text.
All eight voice presets speak every supported language, including Arabic, Chinese, French, German, Hindi, Japanese, Korean, Spanish, and others. This uniformity simplifies pipeline management for multi-region short-form video strategies.
English Voices
English is the default language for Latin-script input. Voices like Aria, Nova, Luna, and Sage provide clear, native-level English suitable for TikTok and Reels narration.
Use the language parameter to enforce English pronunciation if the input text contains mixed scripts or ambiguous phrasing.
- Default detection for Latin script
Multilingual Support
The API supports 23 languages, including Swahili, Turkish, and Russian. Each voice maintains consistent tone across all supported languages.
Ensure language is set for non-English Latin texts to avoid misidentification.
- 23 supported languages
- Uniform voice performance across languages
Accent Variations
Each voice has a fixed timbre; accent variations arise naturally from the language model’s training data rather than explicit accent parameters.
The voice character remains consistent, with only phonetic adjustments for the target language.
- Fixed voice timbre
- Natural phonetic adaptation
Selection Criteria
Selecting the correct voice requires aligning audio tone with content pacing. Female voices like Aria and Luna suit narrative or instructional reels, while Nova and Sage work for upbeat or clear delivery. Male options range from Felix’s energetic promos to Orion’s documentary depth. Match the preset to the video’s emotional arc to maintain viewer retention.
Tone Matching
Align voice characteristics with content pacing. Use Aria for warm, clear narration or Felix for energetic promotional clips. Nova suits upbeat shorts, while Orion provides depth for documentary-style edits. Ensure the preset matches the video’s emotional tone to maintain consistency.
- Match voice energy to video pacing
- Align tone with content genre
- Test presets against raw footage
Audience Appeal
Consider demographic preferences for TikTok, Reels, and Shorts. Younger audiences may respond better to Nova’s bright tone or Milo’s conversational style. Older or professional segments might prefer Atlas’s neutral news delivery or Sage’s instructional calm. Select voices that resonate with the target viewer segment.
- Target demographic alignment
- Engagement optimization
- Voice-audience compatibility
Brand Fit
Ensure voice consistency across all content assets. Use a single preset for series branding or switch voices to distinguish segments. Avoid mixing tones within a single video unless intentional. Maintain a cohesive auditory identity to reinforce brand recognition across platforms.
- Consistent branding
- Series voice identity
- Auditory recognition
Technical Specs
The ClipSpeak API delivers high-fidelity audio with realistic intonation, optimized for short-form video platforms. Each request generates a distinct audio file, ensuring consistent quality across batches. The system handles up to 4096 characters per call, processing requests sequentially to maintain stability under load.
Audio generation speed averages roughly real-time, producing approximately 25 characters of text per second for standard-length inputs. Short phrases may require a few seconds to synthesize. During high traffic, requests may queue, but processing remains reliable and sequential.
Audio Quality
Synthesized audio maintains clear articulation and natural pacing, suitable for TikTok, Reels, and Shorts. The engine uses licensed recordings from LibriTTS-R and LibriVox. Each output file contains an inaudible watermark to identify synthetic speech.
- Realistic intonation and pacing
- Inaudible synthetic watermark
- Licensed source material
Speed Range
Adjustable playback speed allows fine-tuning of voiceover timing. Users can set the speed parameter between 0.25 and 4.0. This range supports both slow, deliberate narration and fast-paced promotional content without distorting voice quality significantly.
- Speed range: 0.25 to 4.0
- Adjustable via API parameter
- Suitable for varied content pacing
Format Support
The API supports multiple audio formats to suit different editing workflows. Choose between mp3, wav, opus, flac, or pcm based on your platform’s requirements. All formats are generated directly from the same engine, ensuring uniform audio quality.
- Supported formats: mp3, wav, opus, flac, pcm
- Uniform quality across formats
- Direct API response
Comparison Table
Selecting the correct voice preset is critical for maintaining audience retention in short-form video content. Each of the eight available voices offers distinct tonal characteristics optimized for specific narrative styles, from energetic promotions to calm instructional guides.
The following table maps each voice to its primary tonal description and recommended content type, ensuring consistent audio branding across TikTok, Reels, and Shorts pipelines without requiring manual recording adjustments.
Voice Names
The API provides eight distinct voice presets. Four are female (Aria, Nova, Luna, Sage) and four are male (Felix, Milo, Atlas, Orion). Each voice is derived from licensed recordings or public-domain audiobook readings.
- Aria, Nova, Luna, Sage
- Felix, Milo, Atlas, Orion
Tone Descriptions
Voices are categorized by their auditory profile. Aria offers a warm, clear narrator style. Nova provides a bright, upbeat energy. Luna delivers a soft, storytelling tone. Sage ensures a calm, instructional delivery. Felix is energetic and promo-oriented. Milo sounds friendly and conversational. Atlas maintains a neutral, news-like quality. Orion provides a deep, documentary voice.
- Warm/Clear (Aria)
- Bright/Upbeat (Nova)
- Soft/Storytelling (Luna)
- Calm/Instructional (Sage)
- Energetic/Promo (Felix)
- Friendly/Conversational (Milo)
- Neutral/News (Atlas)
- Deep/Documentary (Orion)
Recommended Use
Match the voice to the content format to maximize engagement. Use Nova or Felix for promotional clips and product showcases. Select Luna or Aria for narrative storytelling. Choose Sage for tutorials. Use Milo for conversational vlogs. Select Atlas for news updates. Use Orion for documentary-style content.
- Promo: Felix, Nova
- Storytelling: Luna, Aria
- Tutorials: Sage
- Vlogs: Milo
- News: Atlas
- Documentary: Orion

Implementation
ClipSpeak integrates directly into your content pipeline via a standard HTTP endpoint. Send a POST request to https://api.playa001.com/v1/audio/speech with your JSON payload. The API returns the generated audio file immediately, allowing seamless automation for TikTok, Reels, or Shorts production without manual file management.
Use the voice parameter to select one of the eight presets. Pair this with the model parameter (tts-1 or tts-1-hd) to define quality. Ensure your input text stays within the 4096-character limit. For longer scripts, split the text, generate individual audio segments, and join them in your editing software.
API Integration
Use the official OpenAI SDK or plain HTTP to connect. Set the base_url to https://api.playa001.com/v1 and include your Bearer token in the Authorization header. This ensures compatibility with existing tools while leveraging our specific voice engine.
Voice Parameter
Pass the desired voice name (e.g., aria, nova, felix) in the request body. Each voice is optimized for specific tones, from warm narration to energetic promos. Select based on your video’s emotional context rather than generic labels.
Testing
Verify output format and speed by sending test requests with response_format set to mp3 or wav. Check the speed parameter between 0.25 and 4.0 to match your video’s pacing. Use the free trial credit to validate integration before scaling production.
Licensing Notes
ClipSpeak generates audio by recombining phonemes from licensed source recordings rather than stitching whole phrases together. This method ensures consistent vocal quality while maintaining a distinct synthetic character. The resulting voiceovers are optimized for short-form video platforms, providing creators with reliable, copyright-safe narration without the need for manual recording sessions.
Source Material
Our voice models are built from the LibriTTS-R dataset, which uses recordings licensed under CC BY 4.0. Additionally, we incorporate public-domain audiobook readings from LibriVox. These sources provide the foundational vocal textures for all eight presets, ensuring a broad and legally clear origin for the synthetic voices.
- LibriTTS-R (CC BY 4.0)
- LibriVox public-domain readings
Synthetic Nature
The audio files produced are entirely synthetic. They do not contain recordings of real human conversations or live performances. This distinction is important for content creators who need to disclose AI-generated voiceovers or ensure their content does not imply a real person is speaking.
Watermark
Every generated audio file includes an inaudible digital watermark. This marker identifies the clip as synthetic speech, aiding in content verification and compliance with platform guidelines regarding AI-generated media. The watermark does not affect audio quality or playback.
Cost per Voice
Every voice preset shares identical pricing, ensuring consistent cost regardless of your selection. The rate is fixed at $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests incur no charge, with the cost returned in full if synthesis fails.
Uniform Pricing
All eight voices—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—use the same engine and cost structure. You pay strictly for character volume, not voice complexity. This uniformity simplifies budgeting for high-volume short-form content pipelines.
No Extra Fees
There are no monthly plans, no seat limits, and no minimum spend requirements. You do not pay extra for higher quality formats like FLAC or OPUS. The only variable is the length of your input text, which directly determines the final invoice amount.
Volume Discounts
The pricing model scales linearly with usage. There are no tiered discounts or bulk rate adjustments; the rate remains $0.01 per 1,000 characters regardless of whether you generate 10,000 or 10 million characters. This flat rate ensures predictable costs for consistent content creation.
Future Updates
The API structure supports future voice integrations without breaking existing implementations. New presets will be added to the /v1/voices endpoint, allowing creators to access additional styles as they become available. The core engine remains consistent, ensuring that any new voice adheres to the same character limits and speed parameters. Updates are deployed directly to the API endpoint, requiring no client-side changes. Creators can immediately benefit from refined audio generation without upgrading their integration code or adjusting their automation pipelines.
Voice Additions
New presets will appear in the /v1/voices list, maintaining the same eight-voice structure initially. Each new voice undergoes rigorous testing for consistency across languages and speeds.
- New voices added via API endpoint updates
- No breaking changes to existing parameters
- Consistent pricing across all presets
Quality Improvements
Enhancements target audio clarity and emotional resonance in brief clips. We optimize the synthesis engine to handle rapid text variations more naturally. These improvements are applied server-side, ensuring immediate availability for all accounts.
- Improved prosody in short segments
- Reduced generation latency
- Better handling of punctuation
Feedback Loop
Creator input drives our development roadmap. We monitor usage patterns and technical reports to identify areas for refinement. Your data helps us prioritize features that matter most to video creators.
You can submit technical issues or tone preferences via email. We review these inputs regularly to guide updates to voice behavior and API performance.
- Email support for technical feedback
- Usage data informs engine tuning
- Regular review of creator requests

Pricing and Account Details
ClipSpeak charges $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you pay only for successful synthesis. There are no monthly plans, seats, or minimum spend requirements, allowing creators to scale usage according to their production volume without contractual obligations.
Character Pricing
The cost is uniform across all eight voice presets and two model variants (tts-1 and tts-1-hd). You are billed based on the exact character count of the input text, processed up to 4096 characters per request. This transparent model eliminates hidden fees for different voice types or audio formats.
Payment Methods
We accept USDT on the TRON network (TRC-20) exclusively. The minimum top-up amount is $5, and funds are credited automatically within minutes of transfer. We do not process credit cards, PayPal, or issue invoices with VAT, maintaining a streamlined, borderless payment infrastructure for global content creators.
Free Trial
New accounts signed in with Google receive $0.50 in trial credit, equivalent to approximately 50,000 characters, valid for 7 days. Accounts created using an email and password start without this trial credit. Your balance does not expire, and unused trial funds are forfeited if not used within the validity period.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the correct voice ensures consistent audio branding across TikTok, Reels, and Shorts videos.
23 languages
Any voice speaks any of these languages.
