{"slug": "soniox-text-to-speech-v2", "title": "Soniox Text-to-Speech v2", "summary": "Soniox has launched Text-to-Speech v2, a new AI speech generation platform offering expressive control, instant voice cloning, and low-latency streaming in 60+ languages at $0.70 per generated hour. The platform uses audio tags to direct emotion and delivery, handles multilingual code-switching naturally, and accurately pronounces complex terminology and alphanumerics across domains such as medicine, law, and finance.", "body_md": "# The new frontier in text-to-speech\n\nCreate extraordinary voice experiences in 60+ languages with expressive control, exceptional precision, instant voice cloning, and low-latency streaming.\n\n$0.70 per generated hour.\n\nTrusted by teams building global voice products\n\n## A new standard for AI speech\n\nNatural, expressive, and multilingual speech with unprecedented control over how every voice sounds and performs.\n\n### Direct every performance\n\nAudio tags let you direct emotion, delivery, and vocal reactions, from whispers, laughter, and hesitation to excitement, tension, and reassurance.\n\n### Speech that feels human\n\nSoniox generates speech with natural rhythm, pacing, emphasis, and expression, adapting its delivery to the meaning of the text.\n\n### Natural and expressive\n\nI thought I knew exactly how the evening would unfold. Then the phone rang. For a moment, I considered letting it go to voicemail—but something told me to answer.\n\n### Conversational\n\nAbsolutely. I found three flights that arrive before noon. The first is the least expensive, but the second gives you a much shorter connection. Would you like me to compare them?\n\n### Storytelling\n\nBy the time we reached the top of the hill, the sun was already beginning to set. We stopped for a moment, looked back at the road behind us, and realized the entire valley had turned gold.\n\n### Exceptional quality in 60+ languages\n\nHear the same voice deliver natural, expressive speech across 60+ languages with consistent quality, identity, and pronunciation.\n\n### Mix languages naturally\n\nSoniox handles foreign names, technical terminology, and language changes naturally within one continuous utterance.\n\nYour reservation is confirmed. Cuando llegues al hotel, muestra este código en recepción: ES-4928.\n\nThe meeting has been moved to Tuesday. Merci de confirmer votre disponibilité avant la fin de la journée.\n\nTo enable the new feature, open Settings and select 음성 복제, then tap Continue.\n\nYour order is ready for pickup. 店頭で注文番号 A-7392 をお見せください.\n\nThe deployment completed successfully. Bitte prüfen Sie jetzt die Produktionsumgebung und bestätigen Sie, dass alles funktioniert.\n\n## Clone any voice from seconds of audio\n\nCreate a high-fidelity voice clone that preserves the speaker’s identity, accent, rhythm, personality, and expressive range.\n\n### From everyday recording to studio-quality speech\n\nRecord anywhere. Soniox removes background noise, echo, and recording artifacts to create a clean, faithful voice clone.\n\n### More than imitation\n\nGenerate entirely new speech that sounds natural, expressive, and unmistakably like the original speaker.\n\n## Exact speech\n\nComplex terminology, names, numbers, and structured information spoken clearly and precisely.\n\n### Built for every domain\n\nFrom medicine and science to law, finance, and engineering, Soniox accurately pronounces specialized terminology across fields of human knowledge.\n\nThe differential diagnosis includes pheochromocytoma, hyperthyroidism, and supraventricular tachycardia.\n\nDeoxyribonucleic acid is transcribed into messenger RNA before translation occurs at the ribosome.\n\nThe court applied the doctrine of promissory estoppel and remanded the case for further proceedings.\n\nThe portfolio uses collateralized loan obligations, interest-rate swaps, and inflation-linked securities.\n\nThe system uses asynchronous replication, Byzantine fault tolerance, and hardware-accelerated cryptography.\n\n### Alphanumerics spoken correctly\n\nPhone numbers, email addresses, verification codes, prices, dates, addresses, and identifiers are spoken clearly and precisely.\n\nYou can reach our support team at +1 415 682 9074.\n\nSend the completed form to alex.chen+support@example.com.\n\nYour verification code is 7Q4M9B. I repeat: 7Q4M9B.\n\nYour delivery is going to 1427 North St. Andrews Place, Apartment 6B, Los Angeles, California 90028.\n\nYour case number is CX-8047-A19, and the affected device is model XR-12 Pro.\n\nYour total is $1,284.37, including tax and delivery.\n\nYour appointment is scheduled for October 21, 2026, at 8:45 a.m.\n\n### Names pronounced naturally\n\nSoniox uses language and context to pronounce people, places, brands, and organizations naturally and accurately.\n\nYour appointment with Siobhan O’Connor is confirmed.\n\nNguyễn Minh Anh will be joining the meeting shortly.\n\nOur Asian engineering office is located in Guangzhou.\n\nYour hotel is located near the historic center of Aix-en-Provence.\n\nThe application is deployed on Kubernetes across several regions.\n\nThe workload runs on NVIDIA H100 GPUs.\n\n## Built for real-time conversation\n\nlow-latency streaming with precise control over what has already been spoken.\n\n### Speech starts before the sentence ends\n\nStart playback while text is still streaming, without waiting for the full message.\n\nAbsolutely, I can help you change your reservation. What date would work better?\n\n### Precise timing for every character\n\nCharacter-level timestamps let applications synchronize text and audio, stop cleanly during interruptions, and continue from the correct point.\n\n### Faster, more responsive speech\n\nReduce pauses between sentences and punctuation while preserving natural, fluent delivery.", "url": "https://wpnews.pro/news/soniox-text-to-speech-v2", "canonical_source": "https://soniox.com/text-to-speech", "published_at": "2026-08-11 21:41:04+00:00", "updated_at": "2026-08-11 22:12:07.251277+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-products", "natural-language-processing"], "entities": ["Soniox"], "alternates": {"html": "https://wpnews.pro/news/soniox-text-to-speech-v2", "markdown": "https://wpnews.pro/news/soniox-text-to-speech-v2.md", "text": "https://wpnews.pro/news/soniox-text-to-speech-v2.txt", "jsonld": "https://wpnews.pro/news/soniox-text-to-speech-v2.jsonld"}}