Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Soniox TTS lets you generate speech with distinct regional accents. The same English dialogue can be spoken with British, Australian, or Indian English voices, each with its own pronunciation, rhythm, and intonation. You can use accented voices from the Soniox voice library or preserve a speaker’s accent through voice... show more

Soniox

1,953 subscribers

316,644 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Comments

Aurora Lux1 month ago

Regional accents can make AI voices feel dramatically more natural and relatable 🌍🎙️ The ability to preserve those nuances through voice cloning is a huge step for truly global products. 🔥

Sheral Tech1 month ago

Soniox TTS delivers authentic regional accents making global voices beautifully natural

Aina Ai | Tools & Updates1 month ago

Such a smart feature real regional accents make TTS finally feel human and global

ZenithAi1 month ago

Regional accents make AI voices feel much more natural and relevant globally.

Japan Gor23 days ago

This is genuinely useful for localization without the "generic American" default. I've wasted too many hours trying to fake a UK accent in homegrown TTS. Do you know if the voice cloning preserves the speaker's native language rhythm, or does it force English phonemes onto n

Elise Tech Ai1 month ago

Regional accents make TTS feel far more natural and relevant for global audiences. Great step forward for voice AI.

RAZA | AI EXPLORER1 month ago

Love this for global products. Regional accents make AI voices feel much more natural and authentic.

Ella Tech & Tool1 month ago

Same script, local feel. Huge for global products 🎙️

Alice The Ai Expert1 month ago

Brilliant for global connection, accents make voices truly relatable!

RATH Chan Ponleu1 month ago

Hope that you will add Khmer voice Supported languages for your product.

Sani Ai Tech1 month ago

Regional accents make AI voices feel far more authentic

Related Videos

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:

Meet the new Soniox voice library. Soniox Text-to-Speech now includes more than 200 built-in voices, carefully curated for different applications, styles, accents, ages, and voice characteristics. Every voice works across 60+ languages, so you can choose the voice that fits your product and use that same voice globally while preserving its identity and character. You can now browse and filter voices by: • Gender • Age • Accent • Use case, such as conversational, narration, or social media • Style, such as warm, confident, friendly, calm, energetic, or deep This makes it much easier to find a voice for a specific application, for example: • Conversational + warm + middle-aged • Narration + deep + confident • Social media + young + energetic • Educational + calm + friendly We manually selected, reviewed, and tagged the voices so the metadata reflects how the voices actually sound and where they work well. We also redesigned the TTS Playground to make it easier to browse, filter, compare, and test voices with your own text and languages. Learn more:

Soniox

126,350 views • 22 days ago

One performance, infinite voices. Voice Conversion is now live on Hume’s creator studio and API! Generate the same pacing, pronunciation, and intonation with one recording across any voice you choose. Hear it for yourself ⬇️

One performance, infinite voices. Voice Conversion is now live on Hume’s creator studio and API! Generate the same pacing, pronunciation, and intonation with one recording across any voice you choose. Hear it for yourself ⬇️

Hume AI

20,033 views • 10 months ago

BREAKING 🚨: xAI is working on the Voice Cloning feature for Grok on iOS! Users will be able to record their own voices and share them as links with others. These voices can be later used in Grok Voice mode.

BREAKING 🚨: xAI is working on the Voice Cloning feature for Grok on iOS! Users will be able to record their own voices and share them as links with others. These voices can be later used in Grok Voice mode.

🚨 AI News | TestingCatalog

101,092 views • 7 months ago

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

666,014 views • 1 month ago

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

So you can clone any voice 100% locally using this new open source model?! Alibaba has released Qwen3-TTS on Hugging Face. You can easily: - Create custom voices - Clone any voice from a VERY short audio - Generate speech with style instructions Only 0.6B & 1.8B! Sound on🔊

Paul Couvert

149,398 views • 8 months ago

Now that is blowing up, I want more people to know that Freen really has a beautiful voice. Even when she’s just using her natural voice whether she’s singing in Thai or in English like this.. you can clearly hear how nice it is. It’s one of those voices that feels warm and pleasant, and it stays with you once you hear it. 😌 #srchafreen‌

Now that is blowing up, I want more people to know that Freen really has a beautiful voice. Even when she’s just using her natural voice whether she’s singing in Thai or in English like this.. you can clearly hear how nice it is. It’s one of those voices that feels warm and pleasant, and it stays with you once you hear it. 😌 #srchafreen‌

becbecbecbecbecbecbecbec ⚡️🤍

17,951 views • 9 months ago

A complete character isn't just how they look. It's also about how they sound. Introducing Characters with Voices - clone your own voice, design one from a text description, or choose from the library. Attach it to your character once, and it follows them across every workflow. Characters with Voices is live on OpenArt. 🎤

A complete character isn't just how they look. It's also about how they sound. Introducing Characters with Voices - clone your own voice, design one from a text description, or choose from the library. Attach it to your character once, and it follows them across every workflow. Characters with Voices is live on OpenArt. 🎤

OpenArt

3,394,360 views • 4 months ago

It's not a point and click adventure without VOICE ACTING Here's the full dialogue system with voices for EVERY SINGLE dialogue spoken. > Voice design > Text-to-speech > Background music All using Elevenlabs. Pretty much just one shotted it with their skills. 📣 Sound ON!

It's not a point and click adventure without VOICE ACTING Here's the full dialogue system with voices for EVERY SINGLE dialogue spoken. > Voice design > Text-to-speech > Background music All using Elevenlabs. Pretty much just one shotted it with their skills. 📣 Sound ON!

Chong-U

14,890 views • 3 months ago

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Rowan Cheung

55,915 views • 3 years ago

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.

ElevenLabs

153,990 views • 1 year ago

We're launching the ElevenLabs Impact Program to help 1 million people reclaim their voice. We’re partnering with nonprofits to provide free licenses to enhance accessibility, advance education, and improve shared cultural experiences. Our first initiative, made possible through partnership with Bridging Voice and The Scott-Morgan Foundation, is aimed at helping everyone with ALS / MND preserve their voice through free access to our technology to create personalized digital voices that closely match their natural speech. If this can benefit you or a loved one, learn more here: If your nonprofit can benefit from AI Audio, get in touch:

We're launching the ElevenLabs Impact Program to help 1 million people reclaim their voice. We’re partnering with nonprofits to provide free licenses to enhance accessibility, advance education, and improve shared cultural experiences. Our first initiative, made possible through partnership with Bridging Voice and The Scott-Morgan Foundation, is aimed at helping everyone with ALS / MND preserve their voice through free access to our technology to create personalized digital voices that closely match their natural speech. If this can benefit you or a loved one, learn more here: If your nonprofit can benefit from AI Audio, get in touch:

ElevenLabs

109,635 views • 2 years ago

This is the most realistic voice cloning I’ve ever heard. It captures voice, emotion, speaking style, and even your rhythm. Powered by EVI 3, Hume’s next-gen speech-to-speech model that: ➔ Streams your speech → replies in real-time ➔ Understands tone and context ➔ Adapts emotion on cue (“whisper fearfully,” “sound excited”) Try it now: 🔗 (live demo, no prompt edits) 🔗 (customize voices, integrate with LLMs) You can even integrate it with top AI models like Groq, Anthropic, and DeepSeek 👇 Talk to the voice I cloned here:

This is the most realistic voice cloning I’ve ever heard. It captures voice, emotion, speaking style, and even your rhythm. Powered by EVI 3, Hume’s next-gen speech-to-speech model that: ➔ Streams your speech → replies in real-time ➔ Understands tone and context ➔ Adapts emotion on cue (“whisper fearfully,” “sound excited”) Try it now: 🔗 (live demo, no prompt edits) 🔗 (customize voices, integrate with LLMs) You can even integrate it with top AI models like Groq, Anthropic, and DeepSeek 👇 Talk to the voice I cloned here:

Ali Sufian

15,063 views • 1 year ago

instead of scrolling through endless voices trying to find the right one, you can just describe what you want and pick from the results. I asked for a 22-year-old streamer with a deep English voice, polite delivery, and a calm, relaxing tone. the second option nailed it. voice discovery and voice creation are two completely different things.

instead of scrolling through endless voices trying to find the right one, you can just describe what you want and pick from the results. I asked for a 22-year-old streamer with a deep English voice, polite delivery, and a calm, relaxing tone. the second option nailed it. voice discovery and voice creation are two completely different things.

roman

11,768 views • 23 days ago

I don't know the creative motive why in English the female voice of Chrysalis is not Lisa. In French there is also the mixture of voices, but you can hear perfectly well that it is Clara. So, why do they have a different way to do it in English? 🤨

I don't know the creative motive why in English the female voice of Chrysalis is not Lisa. In French there is also the mixture of voices, but you can hear perfectly well that it is Clara. So, why do they have a different way to do it in English? 🤨

Miraculous Fans World 🐾

13,177 views • 7 months ago

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Charly Wargnier

59,144 views • 8 months ago

Introducing Arcana: AI Voices with Vibes 🔮 We just launched the most realistic spoken language (TTS) model like ever! At Rime, we're dedicated to capturing the authentic nuances of real human speech, accents, laughter, sighs, and everything in between. Arcana also lets developers generate infinite voices just by providing a description or a fictional name. Live on our API and dashboard from day one. No waitlists, no barriers. Ready for building! Perfect for: ✨Relatable business voice agents ✨Fully immersive chatbots ✨Creative and dynamic storytelling ✨Natural multilingual conversations Try chatting with Arcana on our homepage now. Links below ⬇️

Introducing Arcana: AI Voices with Vibes 🔮 We just launched the most realistic spoken language (TTS) model like ever! At Rime, we're dedicated to capturing the authentic nuances of real human speech, accents, laughter, sighs, and everything in between. Arcana also lets developers generate infinite voices just by providing a description or a fictional name. Live on our API and dashboard from day one. No waitlists, no barriers. Ready for building! Perfect for: ✨Relatable business voice agents ✨Fully immersive chatbots ✨Creative and dynamic storytelling ✨Natural multilingual conversations Try chatting with Arcana on our homepage now. Links below ⬇️

Rime

48,135 views • 1 year ago

This is Kenyan President William Ruto boasting that Kenyans speak better English than Nigerians 🤣🤣🤣 He is confusing accent with diction. When African presidents boast that their citizens speak “better English” than others, they are not demonstrating a strong education system, as Ruto claims, they are showcasing a deep inferiority complex rooted in colonial conditioning. English is a colonial language, not a measure of intelligence, capability, or national progress. You can be fully fluent in a language and still have an accent that is difficult for some listeners to understand, as Nigerians do. Fluency means you have a strong command of vocabulary, grammar, and the ability to express ideas. Accent, on the other hand, relates to pronunciation, rhythm, and intonation, which are shaped by your first language and speech environment, which is what Ruto is confusing with good English. Has he ever had someone from Scotland, Liverpool, or Birmingham speak? Accents are a natural linguistic outcome, not a measure of education. They emerge from the influence of a person’s first language, the sounds and speech patterns they grow up with, and the environment in which they learn and use another language. Every language has its own phonetic structure, and when people speak a second language like English, those underlying patterns shape pronunciation, rhythm, and tone. That is why accents vary across regions and countries. They reflect history, identity, and exposure, not intellectual or educational superiority. I know that there is some kind of tension between Nigeria and Kenya, but such misleading statements undermine the confidence of young people. When they hear a president speak like that about how they speak, it erodes their self-belief, and that is not a good thing to come from a president.

This is Kenyan President William Ruto boasting that Kenyans speak better English than Nigerians 🤣🤣🤣 He is confusing accent with diction. When African presidents boast that their citizens speak “better English” than others, they are not demonstrating a strong education system, as Ruto claims, they are showcasing a deep inferiority complex rooted in colonial conditioning. English is a colonial language, not a measure of intelligence, capability, or national progress. You can be fully fluent in a language and still have an accent that is difficult for some listeners to understand, as Nigerians do. Fluency means you have a strong command of vocabulary, grammar, and the ability to express ideas. Accent, on the other hand, relates to pronunciation, rhythm, and intonation, which are shaped by your first language and speech environment, which is what Ruto is confusing with good English. Has he ever had someone from Scotland, Liverpool, or Birmingham speak? Accents are a natural linguistic outcome, not a measure of education. They emerge from the influence of a person’s first language, the sounds and speech patterns they grow up with, and the environment in which they learn and use another language. Every language has its own phonetic structure, and when people speak a second language like English, those underlying patterns shape pronunciation, rhythm, and tone. That is why accents vary across regions and countries. They reflect history, identity, and exposure, not intellectual or educational superiority. I know that there is some kind of tension between Nigeria and Kenya, but such misleading statements undermine the confidence of young people. When they hear a president speak like that about how they speak, it erodes their self-belief, and that is not a good thing to come from a president.

Hopewell Chin’ono

141,735 views • 5 months ago

Meet the new Qwen3-TTS (2025-11-27): a major step forward in lifelike voice generation! > 49+ distinctive voices ranging from playful to authoritative, giving creators precise control over personality and style. > Global language coverage with 10 languages and multiple authentic dialects, including Minnan, Wu, Cantonese, Sichuan, Beijing, Nanjing, Tianjin, and Shaanxi. > Human-level delivery with adaptive rhythm, pacing, and intonation that makes speech sound genuinely performed.

Meet the new Qwen3-TTS (2025-11-27): a major step forward in lifelike voice generation! > 49+ distinctive voices ranging from playful to authoritative, giving creators precise control over personality and style. > Global language coverage with 10 languages and multiple authentic dialects, including Minnan, Wu, Cantonese, Sichuan, Beijing, Nanjing, Tianjin, and Shaanxi. > Human-level delivery with adaptive rhythm, pacing, and intonation that makes speech sound genuinely performed.

steven

45,890 views • 10 months ago

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

Aaliya

28,046 views • 1 year ago