gradium-tts-beta

s.code,{children:any}),and the model detects it from the audio. Requests that already set a language or,_jsx(_components.code,{children:any}),are unaffected. See,_jsx(_components.a,{href:/guides/transcription-settings#languages,children:Transcription Settings}),.]}),_jsx(_components.p,{children:The Resources menu on the website now links straight to these release notes.})]}),\n,_jsx(Update,{label:2026.08.10,description:Gradium Studio and website updates,id:2026-08-10,children:_jsxs(_components.ul,{children:[\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Model selector in Gradium Studio}),: the ,_jsx(_components.a,{href:/guides/text-to-speech,children:Text-to-Speech}),page now has a Model dropdown to switch between the production model and,_jsx(_components.code,{children:gradium-tts-beta}),, showing each ,_jsx(_components.code,{children:model_name}), with a copy button.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Shareable studio links}),: pre-configure a session with ,_jsx(_components.code,{children:?voice=}),, ,_jsx(_components.code,{children:?model_name=}),, ,_jsx(_components.code,{children:?text=}),and,_jsx(_components.code,{children:?language=}),and share the full setup as a single link. Links now survive login and signup, so they work for recipients who are not signed in yet; voice IDs with ready-made links are on,_jsx(_components.a,{href:/guides/voices/flagship-voices,children:Flagship Voices}),.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Onboarding for new accounts}),: signing up or accepting an invitation now starts with a short three-step setup to get you up and running quickly.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Contact and feedback without leaving the studio}),: the profile menu now has Support > Contact and Support > Feedback, the same forms as on the website, with attachments.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:System appearance}),: a new System theme option in the studio follows your OS light or dark preference live.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Feedback page on the website}),: ,_jsx(_components.a,{href:https://gradium.ai/feedback,children:gradium.ai/feedback}), is a standalone form for product feedback, open to everyone.]}),\n,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:Live Translation demo}),: pick the target language and the output voice in one “Translate to … with the voice of …” row on the ,_jsx(_components.a,{href:https://gradium.ai,children:website demo}),.]}),\n]})}),\n,_jsxs(Update,{label:2026.08.03,description:Improved translation models,id:2026-08-03,children:[_jsxs(_components.p,{children:[Our live translation models (,_jsx(_components.code,{children:stt-translate}),for translated transcription and,_jsx(_components.code,{children:s2s-translate}), for Speech-to-Speech) now produce more natural, more accurate translations, with better context understanding across a conversation. The quality gains are most noticeable on conversational speech.]}),_jsxs(_components.p,{children:[See ,_jsx(_components.a,{href:/guides/speech-to-speech,children:Speech-to-Speech}),and the,_jsx(_components.a,{href:/guides/speech-to-text-overview,children:Speech-to-Text overview}), to get started.]})]}),\n,_jsxs(Update,{label:2026.07.30,description:Gradium TTS public beta,id:2026-07-30,children:[_jsx(_components.p,{children:A new Gradium Text-to-Speech model is available in public beta. It handles complex text natively, with no pre-processing or normalization on your side: phone numbers in national and international formats, email addresses, IBAN numbers, time expressions, reference codes, measurements, URLs and ordinals.}),_jsxs(_components.p,{children:[The beta is available through the API and in Gradium Studio. To use it from the API, set ,_jsx(_components.code,{children:model_name}),to,_jsx(_components.code,{children:gradium-tts-beta}), in your setup message, over both the SDK and the WebSocket API. Your existing voices, including custom voices, work as-is. On the API the current production model remains the default, so nothing changes unless you opt in.]}),_jsxs(_components.p,{children:[See ,_jsx(_components.a,{href:/guides/installation,children:Installation}),and the,_jsx(_components.a,{href:/api-reference/endpoint/tts-websocket#setup,children:TTS WebSocket setup}), to get started. Everyone who sends feedback during the beta receives 1M Gradium credits.]})]}),\n,_jsxs(Update,{label:2026.07.28,description:New Speech-to-Text model,id:2026-07-28,children:[_jsx(_components.p,{children:A new Speech-to-Text model is now live on the standard endpoint. Transcription is more robust on low volume audio, so soft speakers and far field microphones are recognised with improved reliability. Endpointing is more reactive, so the end of an utterance is detected sooner and voice agents can start responding with less delay.}),_jsxs(_components.p,{children:[See ,_jsx(_components.a,{href:/guides/recipes/turn-taking,children:Turn-Taking}), for using semantic VAD signals to decide when a speaker has finished.]})]}),\n,_jsxs(Update,{label:2026.07.22,description:Keyword Boosting for Speech-to-Text,id:2026-07-22,children:[_jsxs(_components.p,{children:[Get the vocabulary specific to your product transcribed correctly: brand and product names, people, places, drugs, and jargon. Pass a dictionary of the terms you care about in your STT ,_jsx(_components.code,{children:json_config}),, and the model gives them priority while decoding, in real time, with no retraining. Rare, specific words that a general model rarely sees now come through correctly.]}),_jsxs(_components.p,{children:[The ,_jsx(_components.code,{children:keywords}),block takes a,_jsx(_components.code,{children:words}),dictionary and a,_jsx(_components.code,{children:boost}),weight.,_jsx(_components.code,{children:boost}),is applied in log-probability space, so its effect is exponential and a small value goes a long way. We recommend a boost of,_jsx(_components.code,{children:3}),. A dictionary holds up to 500 single-token entries, matched by exact case and accent.]}),_jsxs(_components.p,{children:[Dictionaries can also be saved in Gradium Studio under Vocabulary, in the Keyword boost tab, then used in a session by passing their id as ,_jsx(_components.code,{children:keyword_boost_id}),.]}),_jsxs(_components.p,{children:[See the ,_jsx(_components.a,{href:/guides/recipes/keyword-boosting,children:Keyword Boosting recipe}),and,_jsx(_components.a,{href:/guides/transcription-settings,children:Transcription Settings}), for details.]})]}),\n,_jsxs(Update,{label:2026.06.10,description:Upgraded default TTS model,id:2026-06-10,children:[_jsx(_components.p,{children:Gradium TTS now runs on an upgraded default model focused on more expressive speech and better reliable pronunciation for production voice agents.}),_jsx(_components.p,{children:Improved natural prosody, phrasing, intonation, and pacing. This is especially noticeable in conversational turns and longer passages.}),_jsxs(_components.p,{children:[The model is better at spelling out email addresses, reference numbers, confirmation codes, and acronyms such as ,_jsx(_components.code,{children:API}),, ,_jsx(_components.code,{children:SQL}),, and ,_jsx(_components.code,{children:URL}),.]}),_jsx(_components.p,{children:The upgraded model is now the default. If your integration uses the default model, you are already on the new Gradium TTS model with no code changes required.}),_jsx(_components.p,{children:Every voice from the previous model generation is available on the upgraded model, including custom voices. You do not need to re-clone or recreate voices.}),_jsxs(_components.p,{children:[Integrations pinned to a specific model can switch by changing the model identifier. To stay on the previous model temporarily, set ,_jsx(_components.code,{children:model_name}),to,_jsx(_components.code,{children:gradium-tts-202602}),. The previous model will be gradually phased out over the next few weeks.]})]}),\n,_jsxs(Update,{label:2026.02,description:Gradium API and Studio updates,id:2026-02,children:[_jsx(_components.p,{children:We’re excited to announce major updates to the Gradium API and Gradium Studio, delivering enhanced text-to-speech (TTS) and speech-to-text (STT) capabilities for developers and enterprises.}),_jsx(_components.p,{children:_jsx(_components.strong,{children:Advanced TTS and STT Models})}),_jsx(_components.p,{children:Experience our latest text-to-speech model and speech recognition model with improved audio quality, accuracy, and natural-sounding voice generation. Perfect for voice applications, transcription services, and conversational AI. Now by default.}),_jsx(_components.p,{children:_jsx(_components.strong,{children:Custom Pronunciation Dictionaries})}),_jsx(_components.p,{children:Take control of speech synthesis with pronunciation dictionaries. Ensure brand names, technical terminology, and industry-specific acronyms are pronounced correctly every time. Ideal for healthcare, finance, and industry specific applications.}),_jsx(_components.p,{children:_jsx(_components.strong,{children:WebSocket Multiplexing for Real-Time Audio})}),_jsx(_components.p,{children:Boost performance with multiplexing support: process multiple TTS or STT requests simultaneously over a single WebSocket connection. Reduce latency, minimize connection overhead, and scale efficiently for high-volume applications.}),_jsx(_components.p,{children:_jsx(_components.strong,{children:Gradium Referral Program})}),_jsx(_components.p,{children:Love Gradium? Join our referral program: share Gradium with your network and earn up to 9M API credits while your referrals get exclusive discounts. Win-win for developers and businesses alike.}),_jsx(_components.p,{children:_jsx(_components.strong,{children:AWS Marketplace \u0026 SageMaker AI Deployment})}),_jsx(_components.p,{children:Deploy Gradium TTS and ASR models directly on AWS SageMaker with full bidirectional streaming support. Accelerate your deployment timeline while keeping your voice AI infrastructure secure within your private cloud network. Now available on AWS Marketplace.}),_jsxs(_components.p,{children:[Feedbacks are always welcome, do not hesitate to join our ,_jsx(_components.a,{href:https://discord.com/invite/bcysuPRzXE,children:discord channel}),!]})]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(Expected +(component?component:object)+" \"+id+\" to be defined: you likely forgot to import, pass, or provide it.")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Release Notes","description":"Latest updates and improvements to the Gradium API","noindex":true,"rss":true,"href":"/guides/release-notes"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"2026.10.16","slug":"2026-10-16","depth":1,"children":[]},{"title":"2026.10.16","slug":"2026-10-16-2","depth":1,"children":[]},{"title":"2026.10.12","slug":"2026-10-12","depth":1,"children":[]},{"title":"2026.10.09","slug":"2026-10-09","depth":1,"children":[]},{"title":"2026.10.08","slug":"2026-10-08","depth":1,"children":[]},{"title":"2026.09.30","slug":"2026-09-30","depth":1,"children":[]},{"title":"2026.09.24","slug":"2026-09-24","depth":1,"children":[]},{"title":"2026.09.22","slug":"2026-09-22","depth":1,"children":[]},{"title":"2026.09.16","slug":"2026-09-16","depth":1,"children":[]},{"title":"2026.09.15","slug":"2026-09-15","depth":1,"children":[]},{"title":"2026.09.08","slug":"2026-09-08","depth":1,"children":[]},{"title":"2026.09.02","slug":"2026-09-02","depth":1,"children":[]},{"title":"2026.08.31","slug":"2026-08-31","depth":1,"children":[]},{"title":"2026.08.24","slug":"2026-08-24","depth":1,"children":[]},{"title":"2026.08.10","slug":"2026-08-10","depth":1,"children":[]},{"title":"2026.08.03","slug":"2026-08-03","depth":1,"children":[]},{"title":"2026.07.30","slug":"2026-07-30","depth":1,"children":[]},{"title":"2026.07.28","slug":"2026-07-28","depth":1,"children":[]},{"title":"2026.07.22","slug":"2026-07-22","depth":1,"children":[]},{"title":"2026.06.10","slug":"2026-06-10","depth":1,"children":[]},{"title":"2026.02","slug":"2026-02","depth":1,"children":[]}],"codeExamples":{}},"jsLinks":["/_mintlify/custom/gradium/6237bef2decf40f6/reo.js"],"subdomain":"gradium","siteName":"Gradium API","title":"Release Notes - Gradium API","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{"en":{"href":"/guides/release-notes","matchLevel":0},"fr":{"href":"/fr","matchLevel":4}}},"lastModified":"2026-10-20T10:32:33.618Z","originalFileLocation":"guides/release-notes.mdx","locale":"en"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem("isDarkMode")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p="dark"}var r=p==='system'?(matchMedia("(prefers-color-scheme: dark)").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute("data-theme-preference",p)})();\u003c/script>\u003cmeta data-mint-head name="description" content="Latest updates and improvements to the Gradium API">\u003cmeta data-

Read from the provider's text; the quote is the provider's exact lines.