Skip to main content
​
Voice localizer in Studio
The Voice localizer is now in Studio, out of beta. Pick a voice, describe the accent you want, and compare three takes at different strengths. The one you keep is saved as a new custom voice. You can also start from Localize in any voice’s menu in the catalog. See the Voice Localization guide.Also new in Studio:
  • Voice search: describe what you need, such as “a calm older narrator, good for biographies”, and matching filters are suggested as you type. Results show why each voice matched.
  • Catalog filters: each filter only offers values that match your other filters, so you no longer pick a combination with no voices.
  • Sessions: your session history has its own page in the sidebar. Export the page on screen, or all sessions from the last 30 days.
  • Pronunciation rules: rules are applied in order, and you can now reorder them by dragging.
  • Overages on upgrade: choose whether to allow overages when you upgrade your plan.
​
Organization roles and data controls in Studio
The Organization page in Studio, opened from the Profile menu, now has two roles, Admin and Member, and a Data controls section that replaces Privacy settings.
  • Roles: only admins can edit the organization details, change data controls, invite people, change roles and remove members. The API enforces the same rules.
  • Invitations with a role: invite several people at once and choose whether they join as Member (the default) or Admin.
  • Team members: see each member’s role, status, member since and last login date. Search, sort and export the list to CSV.
  • Last admin: an organization always keeps at least one admin, so the last admin cannot be changed to Member or removed.
  • Delete an organization: admins can delete an organization from the danger zone, after reviewing what will be deleted and typing its name. Deletion is immediate and cannot be undone.
  • Data residency: every member can see the organization’s region and enforcement mode: Flexible, Per endpoint or Strict, the Studio names for the none, explicit and implicit modes. Admins can click Request a change; our support team applies it and replies by email.
  • Paid plans: Zero data retention and data residency need a paid plan. On a free plan, both settings are greyed out; hover them to see why, and use Upgrade plan at the top of the Data controls section.
See Organization, Zero data retention and Data residency.
​
SOC 2 Type II attestation
Gradium has completed its SOC 2 Type II attestation.Visit our Trust Center for security documentation.
​
1,000+ new voices and Studio improvements
The voice catalog grows from about 390 to more than 1,400 voices. The 1,035 new voices span all five languages and 29 accents, for use cases from customer service to characters. Browse them in the Studio voice library or read the announcement.Also new in Studio:
  • Preview samples: a voice can have several preview samples, each reading a different sentence. When you save a voice from Voice Design, the sentences you auditioned become its preview samples.
  • Faster catalog: the catalog stays smooth to scroll with the larger library, in both tile and list views.
  • Usage exports: export your sessions from the last 30 days as CSV or Excel, including the credit cost of each session. The Excel file adds a summary sheet.
  • Pronunciation dictionaries: manage them in a sortable table, and import rules in bulk by pasting them or uploading a file. A format guide shows the accepted formats, with a prompt you can copy to turn any word list into rules. Keyword boost sets get the same table view. See Pronunciation dictionaries.
​
Voice Localization
Make a voice you already have speak another language or accent, with the same speaker. Call POST /voice-generator/localize on a flagship or custom voice, pick an accent, and get candidates back in seconds to audition and convert like Voice Design candidates.GET /voice-generator/available-accents lists the accents you can target. Candidate listings now carry a per-kind config object (generate_config, edit_language_config, enhance_config), and prompt is deprecated. See the Voice Localization guide.Voice Enhance is out of beta, with no API change. See the Voice Enhance guide.
​
New TTS model
Our new Text-to-Speech model is now the default, with more expressive speech and lower latency. Existing requests using default use the new model without a setup change.gradium-tts-beta also routes to this model until the next TTS beta arrives. Keep that alias to follow future betas, or use default to stay on stable releases.cfg_coef is deprecated for TTS. Requests that include it are still accepted, but the new model ignores its value. Remove it from json_config. See Model selection and Voice Settings.
​
Voice Enhance (beta)
Clean up a voice you already have without changing its language or who is speaking. POST /voice-generator/enhance takes a flagship voice, a clone or a candidate and returns candidates with background noise reduced. Audition and convert them like Voice Design candidates.Voice Enhance is in beta; output quality will keep improving. See the Voice Enhance guide to get started.
​
New TTS public beta
Our new Text-to-Speech model entered public beta with lower latency and more expressive speech. At beta launch, we measured time to first audio under 50 ms, against 225 ms for the then-production model. Latency varies with network conditions and input.During the beta, setting model_name to "gradium-tts-beta" selected the new model. Requests using default stayed on the previous production model. See the September 30 release above for the current default.The beta ignored cfg_coef: requests that included it were accepted, but it did not adjust voice similarity. See Voice Settings for current TTS settings.
​
ISO 27001 certification
Gradium has achieved ISO 27001 certification, independently audited by A-LIGN.Visit our Trust Center for certification details and security documentation.
​
Studio improvements
Studio has a redesigned voice catalogue, new voice search controls in Text-to-Speech, and more ways to preview voices in Voice Design.
  • Voice catalogue: Customize layout between tile or list views, group voices by language, and choose which properties to display. Studio saves your display preferences, and voice type labels distinguish catalogue, generated and cloned voices.
  • Filters and insights: Narrow the catalogue by language, accent, age, gender and other voice attributes. Click a bar in the insights panel to filter the results, or copy a link to share a filtered view.
  • Voice details: Open a voice’s details beside the catalogue. For your own voices, edit the name and properties directly in the panel. For catalog voices, browse the voice attributes.
  • TTS voice selection: Search and filter voices in a dedicated side panel. Describe what you need, such as “French Parisian voice”, to get suggested smart filters. If nothing matches, Studio suggests a prompt you can take into Voice Design.
  • Voice Design previews: Try a voice with three sample texts provided by default, regenerate the audio, and choose a different sample rate to hear how it sounds at your target rate.
  • Voice Cloning: Find Instant and Pro cloning under one entry. Short recordings and upload errors are reported in the capture step.
  • Updated typography: Studio uses a new typeface for improved readability.
​
Voice Design
Create a voice from a written description, no audio sample needed. Describe the accent, age and character you need, generate up to five candidates, and keep your favourite. The voice works with the same Text-to-Speech endpoint as any catalogue voice.In our blind listening evaluation, native speakers judged how well voices matched accent prompts. Gradium achieved a 72.6% win rate against ElevenLabs, Inworld, MiniMax and Fish Audio, counting ties as half a win, and ranked first in English, French, Spanish, Portuguese and German.See the Voice Design guide to get started.
​
Longer sessions
A session can last up to 3000 seconds. See Limits.
​
New Text-to-Speech model
A new Gradium Text-to-Speech model is live and is now the default. Existing voices, including custom voices, work as-is.The model reads the structured entities that break voice agents in production, such as phone numbers, email addresses, IBANs and reference codes, with no pre-processing or text normalization needed. On Coval, time to first audio P50 is 216 ms, 170 ms faster than the previous model.Full benchmarks, audio samples and the open-sourced evaluation set are in the release post. To get started, see Text-to-Speech.
​
Always set a language for transcription
Speech-to-Text requests now require a language in json_config. Our ASR gives its best results when the language is known, so set it whenever you can: en, fr, es, pt, or de. When the language is not known ahead of time, pass any and the model detects it from the audio. Requests that already set a language or any are unaffected. See Transcription Settings.The Resources menu on the website now links straight to these release notes.
​
Gradium Studio and website updates
  • Model selector in Gradium Studio: the Text-to-Speech page now has a Model dropdown to switch between the production model and gradium-tts-beta, showing each model_name with a copy button.
  • Shareable studio links: pre-configure a session with ?voice=, ?model_name=, ?text= and ?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 Flagship Voices.
  • 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.
  • 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.
  • System appearance: a new System theme option in the studio follows your OS light or dark preference live.
  • Feedback page on the website: gradium.ai/feedback is a standalone form for product feedback, open to everyone.
  • Live Translation demo: pick the target language and the output voice in one “Translate to … with the voice of …” row on the website demo.
​
Improved translation models
Our live translation models (stt-translate for translated transcription and 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.See Speech-to-Speech and the Speech-to-Text overview to get started.
​
Gradium TTS public beta
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.The beta is available through the API and in Gradium Studio. To use it from the API, set model_name to 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.See Installation and the TTS WebSocket setup to get started. Everyone who sends feedback during the beta receives 1M Gradium credits.
​
New Speech-to-Text model
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.See Turn-Taking for using semantic VAD signals to decide when a speaker has finished.
​
Keyword Boosting for Speech-to-Text
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 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.The keywords block takes a words dictionary and a boost weight. 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 3. A dictionary holds up to 500 single-token entries, matched by exact case and accent.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 keyword_boost_id.See the Keyword Boosting recipe and Transcription Settings for details.
​
Upgraded default TTS model
Gradium TTS now runs on an upgraded default model focused on more expressive speech and better reliable pronunciation for production voice agents.Improved natural prosody, phrasing, intonation, and pacing. This is especially noticeable in conversational turns and longer passages.The model is better at spelling out email addresses, reference numbers, confirmation codes, and acronyms such as API, SQL, and URL.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.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.Integrations pinned to a specific model can switch by changing the model identifier. To stay on the previous model temporarily, set model_name to gradium-tts-202602. The previous model will be gradually phased out over the next few weeks.
​
Gradium API and Studio updates
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.Advanced TTS and STT ModelsExperience 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.Custom Pronunciation DictionariesTake 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.WebSocket Multiplexing for Real-Time AudioBoost 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.Gradium Referral ProgramLove 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.AWS Marketplace & SageMaker AI DeploymentDeploy 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.Feedbacks are always welcome, do not hesitate to join our discord channel!