Releasesby GlyphAura-2 TTS Language Expansion
Deepgram has expanded Aura-2 (Text-to-Speech) to support the following languages: Dutch German French Italian Japanese Additionally, new voices have been added to the Spanish (es) model.
Also shipped Dec 12, 2025Deepgram in December 2025 →
Branchable Auth, 80 Free plan projects, and purely usage-based billing release - Dec 12, 2025
Neon Auth branchable identity in your database. We've rebuilt Neon Auth using Better Auth as the foundation. Auth was the last part of Neon that didn't yet bran...
What's new in Sigma
Admin Enable multiple identity providers for your organization (Beta) You can now enable multiple identity providers (IdPs) for your Sigma organization. If you would like to enable multiple IdPs for your organization, please contact Sigma support. For more information, see Using multiple identity providers for your Sigma organization (Beta) .
Durable Objects, Workers - Billing for SQLite Storage
Storage billing for SQLite-backed Durable Objects will be enabled in January 2026, with a target date of January 7, 2026 (no earlier). To view your SQLite storage usage, go to the Durable Objects page Go to Durable Objects ↗ If you do not want to incur costs, please take action such as optimizing queries or deleting unnecessary stored data in order to...
Advanced Customizations for Universal Login has reached General Availability
We are excited to announce that __Advanced Customizations for Universal Login (ACUL)__ is now generally available. ACUL enables developers to create custom, client-rendered user interfaces for Universal Login using their preferred frontend technologies.
Deprecation of `OrderTransaction.authorizationCode` in favor of `OrderTransaction.paymentId`
Starting with the 2026-01 API version, the authorizationCode field on the OrderTransaction object is deprecated. We recommend using the paymentId field instead. The paymentId field provides a consistent, standardized identifier for payment reconciliation across all payment providers on Shopify.
- Query Scheduling Improvements: Small queries now complete faster without getting stuck waiting behind...
- Query Scheduling Improvements: Small queries now complete faster without getting stuck waiting behind large, resource-intensive queries, even when heavy queries are processing in the background Search Enhancements: The search bar in the top left pane of the Object Explorer can now be used to search for schemas, tables, and columns in addition to databases...
More from DeepgramEvery Deepgram release →
PHI Redaction Now Available for Batch and Streaming Speech-to-Text
We're excited to announce that PHI (Protected Health Information) redaction is now available for both batch (pre-recorded) and streaming speech-to-text. redact=phi You can now redact protected health information using the new phi parameter, which redacts the following entity types: condition , drug , injury , blood_type , medical_process , and statistics .
Container Images (release 251210)
- quay.io/deepgram/self-hosted-api:release-251210 Equivalent image to: quay.io/deepgram/self-hosted-api:1.172.2 quay.io/deepgram/self-hosted-engine:release-251210 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.104.10 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-251210 Equivalent image...
This Release Contains The Following Changes
- Expands Nova-3 with 10 New Languages , Building on the 11-language expansion from the 251118 release, Nova-3 now supports 31 total languages. This release adds 10 additional languages, bringing improved accuracy and contextual understanding across: Southern and Eastern Europe : Greek (el), Romanian (ro), Slovak (sk), Catalan (ca) Northern and Baltic...
EU Endpoint Now Generally Available
The Deepgram EU endpoint ( api.eu.deepgram.com ) is now generally available for customers requiring data processing within the European Union.
Supported APIs
The EU endpoint supports the following Deepgram APIs: Speech-to-Text : /v1/listen and /v2/listen (excluding Whisper models) Text-to-Speech : /v1/speak Voice Agent : /v1/agent/converse Text Intelligence : /v1/read
Configuration
To use the EU endpoint, replace api.deepgram.com with api.eu.deepgram.com in your SDK or API requests. Your existing API keys and tokens will work with the EU endpoint.
Nova-3 Multilingual Now Supports Keyterm Prompting
Keyterm Prompting has been expanded to include the Nova-3 multilingual model. Previously, this feature was only available for monolingual Nova-3 models , now you can use keyterms with both.
Container Images (release 251229)
- quay.io/deepgram/self-hosted-api:release-251229 Equivalent image to: quay.io/deepgram/self-hosted-api:1.173.4 quay.io/deepgram/self-hosted-engine:release-251229 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.107.0 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-251229 Equivalent image to...