Skip to main content
No leading silence on resampled TTS output
TTS output in resampled formats now starts without the extra 40 ms of silence.The first audio chunk is now 40 ms instead of 80 ms in these formats. Use start_s and stop_s rather than assuming a fixed chunk size. See Voice Settings for affected formats and how to restore the previous behavior.
Voice enhancement enabled by default for cloning
New voice clones are now enhanced by default. To opt out, set the boolean enhance field to false when calling POST /voices/. See Custom Voices for an example.
Voice list filters and catalog ordering
You can now filter GET /voices/ by locale, gender and use_case, including combinations of these filters.With include_catalog=true, results now list your organization’s voices first, followed by catalog voices ordered by rank, lowest first, with unranked voices last. Voice responses now include rank, which is null for custom voices. See Get Voices.
Phonon: on-device text-to-speech
Phonon brings text-to-speech to local devices, including phones, laptops, embedded devices and browsers. Run speech generation locally for applications that need offline operation or want to keep inference on the device.Use voices from the catalog, or custom voices created through Gradium, in your local applications.Phonon is available in several model variants with different language coverage and licenses. See the model cards for supported languages and usage terms.Read the launch announcement and get the Phonon 31m English weights on Hugging Face.
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.