Frequently asked questions
Which voice is best for blogs?
Aria offers a warm, clear narrator style, while Nova provides a bright, upbeat tone suitable for engaging blog content. You can also use Luna for soft storytelling or Felix for energetic promotional posts. Since voices are presets, you select the one that best matches your blog’s specific editorial voice and audience expectations.
Are all voices the same price?
Yes, all eight voices are generated using the same underlying engine. The price is fixed at $10 per 1 million characters, regardless of which voice you choose. Whether you use Aria, Nova, or any other preset, the cost per character remains identical for both the tts-1 and tts-1-hd models.
Can voices speak multiple languages?
Each voice can speak any of the 23 supported languages, including English, Spanish, French, German, and Japanese. You do not need different voices for different languages. Simply specify the desired ISO language code in your request, or let the system guess the language from the text script if omitted.
What is the difference between Aria and Luna?
Aria is described as a warm, clear narrator, ideal for straightforward reading. Luna is softer and better suited for storytelling. While both are female voices, their tonal qualities differ. Aria works well for direct blog posts, whereas Luna enhances narrative content with a more gentle and immersive delivery style.
Is Felix good for news?
Felix is energetic and designed for promotional content. For news, Atlas is the better choice as he provides a neutral, news-style delivery. Felix’s upbeat tone may feel too informal for serious news updates. Use Atlas for a professional, objective sound that aligns better with standard news broadcasting expectations.
Do voices sound robotic?
The voices are based on licensed recordings from LibriTTS-R and LibriVox, providing natural-sounding speech. Each generated file also carries an inaudible watermark to mark it as synthetic. While they are not human, they are based on licensed recordings and offer clear audio for your content.
Can I mix voices in one file?
No, the API generates audio for one voice per request. To mix voices, you must generate separate audio files for each voice and then join them using your own audio editing software. The API returns individual files, so you handle the final assembly and mixing outside of the API call.
Are the voices based on real people?
Yes, the voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. These are real human recordings, but they are not specific celebrity or politician voices. They are synthesized presets derived from these licensed and public-domain sources for consistent quality.
What is the quality of Orion?
Orion provides a deep, documentary-style voice. This preset is ideal for long-form content, educational materials, or narrative pieces requiring a serious, authoritative tone. As with all voices, it supports 23 languages and can be adjusted for speed. It delivers high-quality audio suitable for professional documentary or instructional blog content.
Can I use Nova for podcasts?
Yes, Nova is described as bright and upbeat, making it well-suited for engaging podcast content. You can adjust the speed between 0.25 and 4.0 to fit your pacing needs. Since the API handles the audio generation, you can focus on your content while Nova provides a lively, professional audio track.
Do voices have accents?
The voices are designed to speak clearly in their supported languages without specific regional accents unless implied by the language code. For example, English voices do not have a marked accent by default. You can set the language explicitly to ensure the voice uses the correct pronunciation for your target audience.
Is Sage good for tutorials?
Sage is described as calm and instructional, making it an excellent choice for tutorials. Its steady tone helps listeners focus on the educational content without distraction. You can use Sage for step-by-step guides, technical explanations, or any content where clarity and a relaxed delivery are prioritized for the audience.
Can I change the speed of voices?
Yes, you can adjust the speed parameter between 0.25 and 4.0. This allows you to slow down complex explanations or speed up shorter updates. The speed adjustment applies to the generated audio file directly, giving you control over the pacing of your content without needing external editing tools.
Are the voices copyrighted?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. While the source data has specific licenses, the generated audio files are synthetic. Each file includes an inaudible watermark to identify it as synthetic speech. You should review the specific license terms for your commercial use case.
Aria: The Warm Narrator
Aria brings a warm, clear narrative voice to your written content. Her tone is consistent and engaging, making her an ideal companion for turning static text into immersive audio experiences. She avoids robotic monotony, delivering lines with a natural rhythm that keeps listeners engaged.
Clear and warm tone
Aria’s vocal quality is designed to feel inviting and professional. She avoids overly dramatic shifts, ensuring the audio remains pleasant for extended listening sessions. This stability makes her suitable for content that requires sustained attention without listener fatigue.
Ideal for stories
Her voice handles narrative arcs smoothly, distinguishing between dialogue and description without jarring transitions. This makes her particularly effective for audiobook-style conversions where character consistency matters. The natural flow helps maintain the story’s emotional tone.
- Consistent pacing for long-form narratives
- Natural handling of dialogue and exposition
- Smooth emotional transitions without dramatic shifts
Best for fiction blogs
Fiction writers can use Aria to produce audio versions of their posts, reaching readers who prefer listening. Her warm presence complements creative writing, enhancing the storytelling experience without overshadowing the text. It’s a simple way to expand your content’s reach.
Nova: The Upbeat Assistant
Nova brings a bright, energetic quality to your audio content, making her ideal for keeping listeners engaged. Her upbeat delivery ensures that your technical explanations or quick tips land with clarity and enthusiasm, turning dry text into lively audio assets.
Bright and energetic
Nova’s voice cuts through background noise with clarity, ensuring your message is heard without strain. This energy helps maintain listener interest, especially in longer tutorials where attention might otherwise wander.
- High energy delivery keeps audiences engaged
- Clear enunciation reduces listener fatigue
- Optimized for short, punchy content
Good for tutorials
When explaining step-by-step processes, Nova’s upbeat tone makes instructions feel approachable rather than robotic. Her natural rhythm aligns well with the pacing of how-to guides, helping users follow along easily.
Best for tech blogs
Tech audiences appreciate precision paired with personality. Nova delivers complex information with a friendly, modern vibe, making your blog posts sound like a conversation with a knowledgeable colleague rather than a lecture.

Luna: The Soft Storyteller
Luna brings a soft, storytelling quality to your audio content. Her gentle voice creates a calming atmosphere, making her ideal for listeners who prefer a relaxed listening experience. This voice adds a layer of warmth and intimacy to your written words.
Gentle and calming
Luna’s delivery is smooth and unhurried, allowing your audience to absorb the narrative without feeling rushed. Her tone reduces cognitive load, making complex or emotional text feel more accessible. This subtle pacing helps maintain listener engagement over longer passages.
Perfect for bedtime stories
The soothing cadence of Luna’s voice makes her an excellent choice for bedtime stories or wind-down content. Her consistent rhythm helps create a soothing environment, perfect for helping listeners relax before sleep. This makes her particularly effective for nightly audio blogs.
Best for wellness content
For wellness blogs, Luna’s voice complements themes of mindfulness and self-care. Her calm presence aligns well with guided meditations or reflective essays. This voice helps establish a trustworthy and serene tone, encouraging readers to pause and listen.
Sage: The Calm Instructor
Sage delivers a calm, instructional tone ideal for structured learning. Her clear enunciation ensures complex concepts remain accessible without sacrificing clarity.
Instructional tone
Sage’s voice maintains a steady, authoritative yet gentle rhythm. This makes her perfect for breaking down technical topics or guiding users through step-by-step processes.
- Consistent pacing for complex instructions
- Gentle authority builds trust
- Ideal for how-to content
Clear enunciation
Each word is articulated precisely, reducing listener fatigue during long educational segments. This clarity is crucial for non-native speakers or noisy environments.
Best for educational posts
Use Sage for blog tutorials, webinar scripts, or course materials. Her neutral yet engaging delivery keeps readers focused on the content, not the voice.
Felix: The Energetic Promo
Felix brings high energy to your audio content, making him ideal for promotional material that needs to grab attention quickly. His voice is designed to stand out in crowded feeds, ensuring your message is heard above the noise.
High energy
Felix delivers a bright, upbeat delivery that keeps listeners engaged from start to finish. This energetic tone is perfect for short, punchy messages where every second counts.
Great for ads
Use Felix for commercial spots, social media promotions, or product launches. His clear, dynamic voice ensures your call to action is memorable and effective.
Best for promotional content
Whether you are creating audio for a blog post or a podcast ad, Felix adds a professional yet lively touch. He helps transform standard text into compelling audio assets that drive engagement.
Milo: The Friendly Conversationalist
Milo brings a natural, conversational rhythm to your audio content, making complex topics feel like a casual chat rather than a formal broadcast. His voice avoids the stiffness often found in synthetic speech, allowing listeners to stay engaged without feeling lectured.
Natural flow
The cadence in Milo’s delivery mimics natural human pauses and emphasis, ensuring that longer texts do not sound monotonous. This smooth progression helps maintain listener interest, especially when reading through detailed script drafts or extended blog posts.
Conversational style
Milo’s tone is friendly and approachable, bridging the gap between professional narration and personal storytelling. This style works exceptionally well for direct-to-camera scripts where the creator wants to establish an immediate, relatable connection with their audience.
Best for vlogs
For freelancers producing video content, Milo is ideal for vlog voiceovers that require a sense of intimacy and authenticity. His style complements the informal nature of vlogs, ensuring the audio enhances the visual narrative without overpowering it.
Atlas: The Neutral News Anchor
Atlas provides a neutral, professional voice ideal for delivering factual updates without emotional bias. Its clear, objective delivery ensures that news content remains distinct from opinion, making it a reliable choice for freelancers managing editorial standards across multiple channels.
Professional tone
The voice maintains a steady, authoritative cadence suitable for breaking news or formal announcements. It avoids dramatic inflections, ensuring the listener focuses on the information rather than the speaker’s personality.
- Consistent pacing for readability
- No emotional bias in delivery
- Suitable for formal press releases
Objective delivery
Atlas delivers text with a flat affect, distinguishing it from warmer voices like Aria or Milo. This neutrality prevents the audio from interpreting the text, allowing the words themselves to carry the weight of the story.
- Neutral intonation profile
- Clear enunciation of proper nouns
- Reduces listener fatigue during long updates
Best for news updates
Freelancers covering tech, finance, or local events benefit from this straightforward presentation style. It pairs well with concise scripts, ensuring that time-sensitive information is conveyed quickly and accurately without unnecessary stylistic flair.
- Ideal for daily briefings
- Works well with tts-1 model
- Supports 23 languages for global reach

Orion: The Deep Documentary
Orion brings a deep, resonant quality to synthetic speech, making it ideal for long-form audio content. Freelancers creating documentary-style blogs or podcasts can leverage this voice to establish authority and maintain listener engagement through consistent, serious delivery.
Deep and resonant
The vocal range of Orion provides a rich, low-frequency tone that stands out in audio feeds. This depth helps reduce listener fatigue during extended listening sessions, which is common when producing detailed historical or investigative content for niche audiences.
- Low-frequency clarity for long-form audio
- Reduces listener fatigue during extended sessions
Serious tone
Orion maintains a consistent, professional demeanor without unnecessary emotional fluctuations. This stability ensures that factual information is delivered with appropriate gravity, making it suitable for news updates, educational posts, or serious commentary where tone credibility matters more than personality.
- Consistent professional demeanor
- Suitable for news and educational content
Best for documentaries
Content creators focusing on documentary-style blogs will find Orion’s preset aligns perfectly with narrative storytelling. The voice supports the pacing required for complex subjects, allowing listeners to absorb detailed information without distraction from an overly energetic delivery style.
- Ideal for narrative storytelling
- Supports detailed subject absorption
Language Versatility
BlogSpeak’s API supports 23 languages, allowing freelancers to localize content without hiring separate voice talent. Any voice can speak any supported language, from Arabic to Turkish, ensuring consistent audio quality across global audiences.
All voices support 23 languages
The eight preset voices—Aria through Orion—handle all supported languages equally. There is no premium for non-English voices; every voice delivers the same warm, clear, or deep character regardless of the language spoken.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish.
Auto-detection for Latin
If you do not specify a language, the system guesses based on the script. Latin-script text defaults to English, which simplifies workflows for English-first bloggers who rarely need explicit language codes for standard posts.
Manual language setting
For non-English Latin-script text, you must set the language field explicitly. This prevents the API from defaulting to English and ensures the voice uses the correct accent and phonemes for languages like German, French, or Dutch.
Audio Quality Features
BlogSpeak delivers audio assets ready for publishing, with built-in safeguards and flexibility for your workflow. Every generated file carries an inaudible watermark that marks it as synthetic speech, ensuring transparency without distracting the listener. You can choose the output format that fits your platform: mp3, wav, opus, flac, or pcm.
Generation happens in real time, with typical speeds matching roughly real-time playback for long texts (about 25 characters per second); short phrases take a few seconds. Short phrases take a few seconds, while longer texts process sequentially. Requests are handled one after another, so under load, a request may wait in a queue before synthesis begins.
Inaudible watermarks
Each audio file includes a subtle watermark that identifies the content as synthetic speech. This feature helps maintain authenticity when publishing audio blogs or podcasts, signaling to listeners that the voice is AI-generated without affecting the listening experience.
The watermark is embedded directly into the audio data, ensuring it persists across formats and platforms. It serves as a clear marker of origin without requiring additional metadata or tags.
Multiple output formats
Choose from mp3, wav, opus, flac, or pcm depending on your needs. MP3 is ideal for web playback, while WAV, FLAC, and Opus offer higher quality for archival or editing purposes. PCM provides raw audio data for further processing, while Opus offers high-quality compression for web delivery.
This flexibility allows you to integrate seamlessly into existing workflows, whether you are uploading to a WordPress site, a podcast host, or an internal archive. No conversion steps are needed.
Real-time generation
Text is converted to audio in real time, with generation speeds roughly matching real-time playback for long texts (about 25 characters per second); short phrases take a few seconds. Short phrases take a few seconds to process, while longer texts may take longer due to sequential processing.
Requests are handled one after another, so under load, a request may wait in a queue. This ensures consistent quality and prevents system overload, though it may slightly increase wait times during peak usage.
Pricing Impact
Voice selection does not affect your billing rate. Whether you choose the warm narration of Aria or the deep documentary tone of Orion, the cost remains identical. This uniformity simplifies budgeting for freelancers who rotate voices based on content type without worrying about tiered pricing structures.
Same price for all voices
All eight presets are priced uniformly. You can switch between conversational styles or instructional tones freely without incurring different rates. This allows you to optimize for audience engagement rather than cost constraints.
tts-1 vs tts-1-hd
The model version impacts audio fidelity, not price. Both "tts-1" and "tts-1-hd" use the same engine and incur the same charge. Choose "tts-1-hd" for higher quality without any additional cost.
Cost per character
Pricing is straightforward: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful synthesis.
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free

How to Choose
To turn written words into effective audio, align the voice’s personality with your content’s purpose. A mismatched tone can distract listeners, regardless of how clear the enunciation is.
Match tone to content
Use Luna for wellness or bedtime stories to create a calming atmosphere. Choose Felix for promotional content where high energy drives engagement. Select Atlas for news updates requiring neutral, objective delivery.
- Aria fits fiction blogs with her warm, clear narrator style.
- Sage works best for educational posts needing clear enunciation.
Test with sample text
Generate a short phrase using your API key to hear how the voice handles punctuation and pacing. Since requests are processed sequentially, test during low-traffic hours to avoid queue delays affecting your review.
Consider audience
Match the voice to your listener’s expectations. Tech blogs often benefit from Nova’s bright, upbeat style, while vlogs suit Milo’s conversational flow. Ensure the voice feels natural for your specific niche.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Mastering WordPress unlocks endless freelance opportunities for creative bloggers seeking financial independence.
23 languages
Any voice speaks any of these languages.
