Frequently asked questions
Which voice is best for breaking news?
A: Atlas is designed as a neutral, news-oriented voice, making it suitable for breaking news segments. It delivers information clearly without unnecessary emotional inflection. You can select it via the voice parameter in your API request. It works well for delivering urgent updates where clarity and neutrality are prioritized over personality.
Can I use multiple voices in one audio file?
No. The API generates one audio file per request, using a single voice preset. To create a multi-voice audio file, you must send separate requests for each section and join the resulting audio files in your workflow. This allows precise control over which voice speaks which part of the content.
Do the voices sound human or robotic?
The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They are synthesized to sound natural and human-like, though every file carries an inaudible watermark marking it as synthetic speech. They avoid the typical robotic tone of older TTS systems.
Are the voices available in all languages?
No. The API supports 23 specific languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these supported languages.
Can I adjust the speed of the voices?
Yes. You can adjust the speed using the speed parameter, which accepts values between 0.25 and 4.0. This allows you to slow down complex news segments for clarity or speed up routine updates. The default speed provides a natural listening pace for most editorial content.
Is there a voice that sounds more authoritative?
Orion is described as deep and documentary-style, offering an authoritative tone suitable for serious news or long-form reports. Atlas provides a neutral, news-standard authority. Sage offers a calm, instructional tone. Choose Orion for depth or Atlas for standard news delivery depending on your editorial style.
Which voice is best for children's news?
Nova (bright, upbeat) and Luna (soft, storytelling) are suitable for children’s content. Luna’s gentle tone works well for storytelling segments, while Nova’s energetic style fits lighter news updates. Both voices remain clear and engaging for younger audiences without sounding overly childish, ensuring a professional yet approachable listening experience.
Do the voices have accents?
The voices are designed to be clear and neutral within their primary language. They do not have strong regional accents unless specified by the language parameter. For non-English Latin-script text, you should explicitly set the language to avoid default English pronunciation, ensuring accurate accent delivery.
Can I use the same voice for all my content?
Yes. You can use a single voice preset, such as Atlas for news or Luna for storytelling, across all your API requests. This ensures brand consistency in your audio output. You only need to change the voice parameter if you want to vary the tone for different segments.
How do I choose a voice for international news?
Select a voice that matches the tone of your content, then explicitly set the language parameter to the ISO code of the target language. For example, use Atlas for neutral news delivery in German or Japanese. This ensures the voice pronounces the text correctly in the chosen language.
Are there any voices specifically for sports news?
No voice is explicitly designated for sports news. However, Felix is described as energetic and promo-oriented, making him suitable for the fast-paced nature of sports updates. His tone conveys excitement, which aligns well with live highlights. While no other voice is specifically marked for this use case, Felix’s energy fits best among our eight presets.
Can I mix male and female voices?
You can mix male and female voices by sending multiple API requests, one for each voice segment, and joining the resulting audio files. The API does not support multiple voices in a single response. This workflow allows you to create dynamic conversations or varied commentary in your news broadcasts.
Is the audio quality consistent across voices?
Yes. All voices use the same underlying engine models (tts-1 or tts-1-hd). The quality is determined by the model choice, not the voice preset. Both models offer consistent audio fidelity, so switching between voices like Aria or Felix does not affect the technical quality of the output.
Do I need to credit the voice actors?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. While the specific voice actors are not individually credited in the API response, the underlying data is CC BY 4.0 licensed. Check the specific license requirements for your use case if needed.
Overview of Available Voices
NewsBrio provides eight distinct voice presets designed to match the diverse tonal needs of news broadcasting. Each voice is engineered for clarity and reliability, ensuring your editorial content is delivered with the appropriate weight and pace. Whether you need a neutral anchor for breaking news or a warm storyteller for features, the API lets you select the perfect tone instantly via Python.
The selection includes four female and four male voices, all supporting 23 languages. This flexibility allows news product teams to maintain brand consistency across different regions and content types without managing multiple voice providers. You can mix voices within a single broadcast by joining audio files from separate requests to keep listeners engaged and reduce fatigue.
8 presets tailored for different tones
Every generated audio file carries an inaudible watermark confirming its synthetic origin. The eight presets range from deep, documentary-style narration to bright, energetic presentations. This variety ensures that your audio output matches the specific context of the article, whether it is a serious investigative piece or a light lifestyle update.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat presenter
- Luna: Soft, storytelling voice
- Sage: Calm, instructional guide
- Felix: Energetic, promo style
- Milo: Friendly, conversational reporter
- Atlas: Neutral, news anchor
- Orion: Deep, documentary narrator
Male and female options available
The four male voices—Felix, Milo, Atlas, and Orion—offer distinct character options. Atlas provides a standard, objective tone ideal for straight news delivery, while Milo adds a conversational warmth suitable for interviews. Orion brings gravity to serious topics, and Felix captures attention for announcements.
The female voices—Aria, Nova, Luna, and Sage—cover a spectrum from educational clarity to soothing narration. Aria’s clear delivery works well for diverse audiences, while Luna’s gentle tone reduces listener fatigue during long segments. Nova keeps energy high for entertainment news, and Sage ensures clarity in complex explainers.
All voices support 23 languages
Each of the eight voices can speak any of the 23 supported languages, including Arabic, Chinese, French, German, Hindi, Japanese, Spanish, and more. This universal support means you do not need to manage separate voice profiles for different languages; the same voice ID works globally.
If the language parameter is not set, the API guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script content, explicitly setting the language code ensures accurate pronunciation and tone, maintaining the intended editorial voice across all supported languages.
Atlas: The Neutral News Anchor
Atlas provides a neutral, news-ready voice that strips away unnecessary emotion, letting the facts speak for themselves. It is engineered for straightforward news delivery where clarity and objectivity are paramount. The voice remains consistent across updates, ensuring your audience receives information without stylistic distraction.
Best for straightforward news delivery
Atlas excels at delivering core news content without imposing a specific attitude. This makes it ideal for general headlines where the story’s importance should drive the listener’s attention, not the narrator’s personality. It handles standard editorial text with ease, maintaining a steady pace that aligns with typical news consumption habits.
Clear and professional tone
The voice is designed to be easily understood by diverse audiences, avoiding the warmth of conversational styles like Milo or the depth of Orion. Its neutral timbre ensures that complex topics are heard clearly, reducing cognitive load for listeners scanning through daily updates. It serves as a reliable baseline for any news product team.
Ideal for breaking news updates
When speed and accuracy matter, Atlas provides a steady rhythm that keeps listeners informed without causing fatigue. It works well for frequent updates where consistency prevents listener confusion. You can switch voices easily if the tone needs to shift, but Atlas remains the go-to for pure, unadorned reporting.
Milo: The Conversational Reporter
Milo delivers a friendly, conversational tone that feels like a trusted colleague rather than a distant broadcaster. This preset excels in feature stories and interviews, where listener retention depends on natural pacing and approachable delivery.
Friendly and approachable style
Milo’s voice is designed to sound like a real person speaking directly to you. It avoids the rigid, monotone delivery common in traditional news TTS, making it ideal for segments that require a human touch without sacrificing clarity.
Great for feature stories and interviews
When covering human-interest stories or long-form interviews, Milo’s conversational rhythm keeps the narrative engaging. It handles the nuance of dialogue well, ensuring that the distinction between reporter and subject remains clear yet cohesive.
Engages listeners with warmth
The warmth in Milo’s preset reduces listener fatigue during longer broadcasts. By maintaining a consistent, inviting tone, it encourages audiences to stay tuned through complex narratives or multi-part series without feeling overwhelmed.
Orion: The Documentary Narrator
Orion provides a deep, authoritative tone ideal for serious storytelling. His voice adds necessary gravity to documentary-style reports, ensuring listeners perceive the weight of the subject matter without distraction.
This preset excels in long-form content where consistency and depth matter more than high energy. It transforms complex narratives into engaging audio experiences suitable for dedicated audiences.
Deep and authoritative voice
Orion’s lower register commands attention, making it perfect for serious news segments or investigative reports. The tone remains steady and professional, avoiding the cheerfulness of other presets like Nova.
This depth helps distinguish factual reporting from opinion pieces, providing a clear auditory cue to the listener about the content’s gravity.
- Low, resonant frequency
- Steady pacing
- Professional delivery
Perfect for long-form documentary content
For extended audio pieces, Orion’s consistent tone reduces listener fatigue. His voice sustains engagement over minutes of content without requiring frequent stylistic shifts.
Use this voice for deep dives into history, science, or political analysis where a steady, reliable narrator is preferred over a dynamic presenter.
- Sustained engagement
- Reduced fatigue
- Consistent tone
Adds gravity to serious topics
When covering crises, economic shifts, or solemn events, Orion’s voice conveys appropriate seriousness. It avoids the lightness of conversational voices like Milo.
This gravitas helps establish credibility and trust, essential for news products aiming to inform rather than just entertain.
Pair this voice with slower speeds (0.25–4.0) for maximum impact in documentary-style audio.
- Crisis coverage
- Economic analysis
- Historical context
Aria: The Clear Narrator
Aria offers a warm, clear delivery that serves as an excellent baseline for news narration. Her voice is designed to be unobtrusive yet engaging, ensuring that the focus remains on the editorial content rather than the vocal performance.
This preset is particularly suitable for educational news segments where clarity is paramount. By avoiding overly dramatic inflections, Aria helps maintain a consistent, professional tone across your audio workflow.
Warm and clear delivery
Aria’s vocal profile is calibrated for neutrality with a touch of warmth, making it ideal for standard news reading. This balance ensures that listeners remain engaged without feeling fatigued by excessive emotion or rigidity.
When used in Python scripts via the voice parameter, Aria provides a stable default that works well for most general-purpose news content, from brief updates to longer daily summaries.
- Neutral yet approachable tone
- Optimized for standard news reading
- Low listener fatigue
Suitable for educational news segments
For segments explaining complex topics or providing background context, Aria’s clear enunciation aids comprehension. Her style avoids the high energy of Felix or the deep gravity of Orion, offering a balanced middle ground.
This makes her an efficient choice for explainer pieces where the information density is high but the tone should remain accessible and informative rather than purely dramatic.
- High clarity for complex topics
- Consistent pacing
- Ideal for context-heavy segments
Easy to understand for diverse audiences
Aria supports all 23 languages, including English, Spanish, French, German, and others. This versatility allows news teams to produce multi-lingual content using a consistent vocal character.
Whether your audience is local or global, Aria’s clear articulation helps ensure that the message is understood clearly, regardless of the listener’s native language proficiency.
- Supports 23 languages
- Consistent vocal character
- Clear articulation
Nova: The Upbeat Presenter
Nova brings a bright, energetic tone to your audio content, making it ideal for keeping listeners engaged. Its upbeat style ensures that news segments feel fresh and dynamic, perfect for lifestyle or entertainment news where positivity is key.
By leveraging Nova’s voice, you can maintain a consistent level of energy throughout your broadcasts. This helps in reducing listener fatigue and keeps the audience connected with the content being delivered.
Bright and energetic tone
Nova’s voice is designed to stand out with its lively and vibrant characteristics. It adds a layer of enthusiasm that makes even routine news updates feel exciting and engaging.
Ideal for lifestyle or entertainment news
When covering topics like fashion, food, or celebrity gossip, Nova’s energetic delivery enhances the storytelling. It ensures that the content remains engaging and captivating for your audience.
Keeps listeners engaged and positive
Nova’s upbeat nature helps in maintaining a positive atmosphere throughout your broadcast. This is particularly useful for keeping the audience interested and motivated, especially during longer segments.
By integrating Nova into your Python API calls, you can easily automate the selection of this voice for specific types of news, ensuring a consistent and engaging listener experience.
Luna: The Soft Storyteller
Luna offers a gentle, soothing voice that transforms standard news scripts into calming audio experiences. Her soft delivery makes complex stories feel intimate and accessible, reducing the cognitive load on listeners who are consuming news during quiet hours or while winding down.
This voice is specifically designed to maintain clarity without the sharp edges of more energetic presets, ensuring that every word is heard clearly without strain. It provides a consistent, soothing backdrop for editorial content that prioritizes listener comfort.
Gentle and soothing voice ['Luna’s vocal tone is naturally warm and unhurried, making her ideal for segments where the message matters more than the excitement. Her clear articulation ensures that even nuanced details in soft news or human-interest stories are delivered with precision.', 'The voice avoids sudden pitch changes or aggressive pacing, creating a steady rhythm that feels like a trusted companion reading the evening edition. This consistency helps listeners stay focused on the content rather than being distracted by vocal variations.'] ['Warm, clear delivery suitable for diverse audiences', 'Consistent pacing that minimizes auditory stress', 'Ideal for human-interest and feature stories']
Great for late-night news or calm segments ['Late-night broadcasts often require a tone that respects the listener’s need for relaxation. Luna’s gentle style fits perfectly into evening news blocks, providing a smooth transition from the day’s busyness to the night’s calm.', 'She is also excellent for weekend morning shows or weekend wrap-ups, where the energy is lower, and the focus is on reflection rather than breaking updates. Her voice complements ambient backgrounds or quiet studio settings effectively.'] ['Perfect for evening and weekend news blocks', 'Complements quiet studio environments', 'Suitable for reflection-focused segments']
Reduces listener fatigue ['Prolonged exposure to high-energy voices can lead to auditory fatigue, especially during long broadcasts. Luna’s softer tone helps mitigate this effect, allowing listeners to consume more content without feeling drained.', 'By reducing the intensity of the vocal delivery, Luna ensures that listeners remain engaged for longer periods. This is particularly valuable for podcast-style news summaries or extended editorial features where attention span is critical.'] ['Minimizes auditory strain during long sessions', 'Supports longer listening sessions without fatigue', 'Enhances retention through gentle delivery']

Sage: The Instructional Guide
Sage provides a calm, instructional tone ideal for breaking down complex news topics. Its steady pacing helps listeners absorb detailed information without feeling rushed, making it a reliable choice for editorial content that requires clarity over emotional flair.
This voice excels in educational segments where precision matters more than dramatic delivery. It ensures that intricate explanations remain accessible to diverse audiences, supporting consistent understanding across your news product team's output.
Calm and instructional tone
Sage’s steady rhythm and neutral warmth make it suitable for delivering structured information. Unlike more energetic voices, it maintains a consistent pace that reduces listener fatigue during longer segments.
The voice avoids excessive emphasis, allowing the content itself to drive the narrative. This subtlety ensures that the message remains clear and undistracted by vocal performance.
- Steady pacing for better retention
- Neutral warmth reduces listener fatigue
- Consistent delivery for structured content
Perfect for explainers and how-to news
Use Sage for step-by-step news explainers or procedural updates. Its clarity ensures that listeners can follow along with complex instructions or multi-part stories without getting lost in tone shifts.
It works well for segments that require a teaching mindset, such as policy breakdowns or technical updates in journalism.
The voice’s instructional quality helps maintain focus on the factual content rather than the speaker's personality.
- Ideal for step-by-step breakdowns
- Supports procedural news updates
- Maintains focus on factual content
Clarity in complex topics
When covering intricate subjects like economic data or scientific findings, Sage’s clear articulation helps simplify the material. It ensures that even dense information remains digestible for a general audience.
By avoiding dramatic inflections, the voice allows the complexity of the topic to shine through without overwhelming the listener.
This clarity is essential for news products aiming to educate rather than just inform.
- Simplifies dense information
- Avoids overwhelming inflections
- Essential for educational news
Felix: The Energetic Promo
Felix brings high-energy and promotional flair to your audio workflow. His voice is designed to cut through the noise, making him ideal for news announcements and ads that need immediate impact.
High-energy and promotional
Felix delivers a bright, upbeat tone that commands attention. His energetic delivery ensures your promotional content stands out without sounding overly aggressive.
- Clear, upbeat vocal style
Ideal for news announcements and ads
Use Felix for breaking news alerts or promotional segments. His voice keeps the energy high, perfect for keeping listeners engaged during shorter, punchy updates.
- Perfect for short-form content
Grabs attention quickly
Start your broadcast with Felix to grab attention quickly. His distinct tone ensures listeners notice the shift from regular news to special announcements or advertisements.
- Immediate listener engagement
Milo vs. Atlas: Which to Choose?
Choosing between Milo and Atlas depends on whether your editorial team prioritizes strict neutrality or listener connection. Atlas delivers a neutral, news-ready tone ideal for breaking updates where objectivity is paramount. Milo offers a friendly, conversational style that feels more like a reporter speaking directly to you, making it better for feature stories or interviews where warmth engages the audience.
Atlas for neutrality and objectivity
Atlas provides a clear, professional delivery that strips away emotional bias. This makes it the reliable choice for straightforward news segments, press releases, or data-driven reports where the content should speak for itself without the voice adding extra interpretation.
- Ideal for breaking news updates
- Clear and professional tone
- Neutral delivery reduces bias
Milo for personality and engagement
Milo brings a friendly, conversational energy to your audio content. It is particularly effective for feature stories, interviews, or segments where you want to maintain listener interest through a warmer, more approachable delivery style.
- Great for feature stories
- Friendly and approachable style
- Engages listeners with warmth
Mix voices for varied content
You are not limited to a single voice. Use Atlas for hard news and switch to Milo for human-interest pieces. This variation keeps your audio feed dynamic and helps listeners distinguish between different types of content within your broadcast workflow.
- Switch voices based on content type
- Keeps audio feed dynamic
- Improves listener distinction
Implementation in Python
Integrating NewsBrio’s TTS into your Python workflow is straightforward. Use the official OpenAI SDK or plain HTTP to send requests to https://api.innwa.info/v1. Pass the voice name directly in the JSON body, alongside your model and input text.
This simple structure allows you to generate audio files efficiently, though longer texts must be split into parts of up to 4096 characters and joined. You can quickly iterate on which voice best suits your specific news segment, ensuring high-quality audio output with minimal code overhead.
Select voice by name in the API call
Pass the voice name directly in the request body. For example, use "voice": "atlas" for breaking news or "voice": "milo" for feature stories. The API accepts eight preset names.
Set the model to tts-1 or tts-1-hd. Include your input text, ensuring it stays under 4096 characters. Specify response_format as mp3 or wav depending on your CMS needs.
- Use
atlasfor neutral, professional delivery. - Use
milofor conversational, friendly tones. - Set
modeltotts-1ortts-1-hd. - Keep input text under 4096 characters.
Test different voices for tone fit
Generate short audio clips for each voice using the same text sample. Compare how aria, nova, and sage handle complex sentence structures versus atlas or milo’s more direct style.
Listen for clarity and emotional resonance. Different voices suit different content types, so test luna for soft storytelling and felix for energetic promos to find the best match.
- Test
ariafor warm, clear narration. - Test
novafor bright, upbeat segments. - Compare
lunaandsagefor calm tones. - Evaluate
felixfor high-energy content.
Automate voice selection based on content
Write a Python script that analyzes your editorial text and selects the appropriate voice. For instance, route breaking news to atlas and lifestyle features to nova based on keywords or metadata.
This automation ensures consistency across your broadcast workflow. You can integrate this logic directly into your CMS pipeline, sending the correct voice parameter with each API request for seamless audio generation.
- Map news categories to specific voices.
- Use keywords to trigger voice selection.
- Integrate with CMS pipelines automatically.
- Ensure consistent audio tone across content.
Licensing and Rights
NewsBrio’s voices are derived from licensed recordings, primarily sourced from the LibriTTS-R dataset under CC BY 4.0 and public-domain LibriVox audiobooks. This foundation ensures that the underlying vocal performances are legally cleared for commercial synthesis, though generated files carry an inaudible watermark.
Voices based on licensed recordings
The eight presets, including Atlas and Milo, are built on these established, rights-cleared source recordings. This means you are not paying for raw voice talent but for the specific synthesis and delivery of these pre-licensed performances.
Clear usage rights for generated audio
Every generated audio file carries an inaudible watermark marking it as synthetic speech. This watermark identifies the output as AI-generated without restricting your ability to broadcast, publish, or distribute the content across your news platforms.
No additional licensing fees required
You pay only for the characters processed. There are no separate royalty fees, no per-broadcast checks, and no complex licensing tiers. Once the audio is generated, you own the rights to use it within your editorial workflow.
Future-Proofing Your Audio
NewsBrio’s architecture ensures that your audio workflows remain stable as the underlying engine evolves. Because the API adheres to a standard request shape, your integration logic stays intact even when model improvements are deployed behind the scenes. You get consistent quality without needing to rewrite your Python code.
The use of standard HTTP methods and JSON bodies means you are not locked into a proprietary protocol. This standardization reduces technical debt and keeps your newsroom’s audio pipeline reliable for years to come.
Consistent voice quality across updates
Updates to the TTS engine do not alter the fundamental output characteristics of a specific voice preset. Your news segments will maintain their intended tone and pacing, ensuring brand consistency across daily broadcasts without surprising listeners with sudden shifts in delivery style.
This stability is crucial for news product teams who rely on predictable audio outputs for automated feeds and CMS integrations.
Standardized API integration
By using a familiar JSON structure similar to major industry standards, your Python scripts can integrate with your CMS or broadcast workflow with minimal custom code. This reduces the risk of breakage when your engineering team changes or when you scale your operation.
You can rely on standard HTTP libraries like requests in Python, avoiding the need for heavy, opinionated SDKs that might change rapidly.
Easy to switch voices if needed
If editorial strategy shifts, you can swap voices instantly by updating the voice parameter in your API calls. There is no retraining or new licensing process required. This flexibility allows news teams to test different tones for different segments without complex infrastructure changes.
You can A/B test voices for feature stories versus breaking news updates by simply changing a string value in your Python script.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This variation keeps your audio feed dynamic and helps listeners distinguish between different types of content within your broadcast workflow.
23 languages
Any voice speaks any of these languages.
