Releasesby Ibis2026.10.08
BetatodayUnverifiedAdded Oct 16, 2026
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.
Topics: Developer tools
More Gradium releases
Every Gradium release2026.09.15
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.
2026.09.08
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.
2026.09.02
A session can last up to 3000 seconds. See Limits .
2026.08.03
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.
2026.09.24
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.
2026.09.22
Our new Text-to-Speech model is available in public beta, with lower latency and more expressive speech. In our latest measurements, the beta reaches time to first audio in under 50 ms, against 225 ms for the production model. Latency varies with network conditions and input. Set model_name to "gradium-tts-beta" in your TTS setup to use the beta.
2026.09.16
Gradium has achieved ISO 27001 certification, independently audited by A-LIGN. Visit our Trust Center for certification details and security documentation .
2026.08.24
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.
Also shipped on Oct 16, 2026
Gradium in October 2026Unified Login for SendGrid Marketplace Customers
SendGrid marketplace customers can now take advantage of the Unified Login feature that lets you create a Twilio login for every individual user accessing your SendGrid account. This provides a more secure access pattern with the ability to define permissions for each user instead of a single, shared admin permission set.
Spot slow and flaky tests faster from your test suite Summary
Your test suite's Summary page now brings together more of the data you need to keep your suite healthy and fast, so you can see where time is going and where reliability is slipping without digging through individual tests.
Know when the Buildkite CLI is done or needs you, without watching its tab
You can now see when bk preflight or bk build watch finishes or needs you, without switching back to its tab. From Buildkite CLI v3.64.0 , bk tells your terminal what it's doing, so a terminal that supports it can show you while you work somewhere else.
READ METADATA privilege support for compliance security profile standards
The READ METADATA privilege now supports all compliance security profile standards supported by Databricks and is available by default for workspaces with the compliance security profile enabled. For a full list of supported compliance standards, see Compliance security profile .
- Images and bounding boxes in prompt_jev() : prompt_jev() can now classify and score images
- Images and bounding boxes in prompt_jev() : prompt_jev() can now classify and score images. Pass PNG or JPEG images as BLOBs, for example loaded from a URL with read_blob , and ask questions about what's in them.
Multi-repo support and other improvements for GitHub Copilot in Slack and Microsoft Teams
Multi-repo support in Slack and Microsoft Teams GitHub Copilot in Slack and Microsoft Teams now supports working across multiple repositories in a single conversation.