Releasesby GlyphExample
{ "type": "FunctionCallRequest", "functions": [ { "id": "fc_12345678-90ab-cdef-1234-567890abcdef", "name": "get_weather", "arguments": "{\"location\": \"Fremont, CA 94539\"}", "client_side": true, "thought_signature": "abc123" } ] } The thought_signature field is optional and only relevant when using Google Gemini models.
Also shipped Apr 1, 2026Deepgram in April 2026 →
Revamped query editor experience
We’ve redesigned the query editor to make complex panels easier to build and manage. The new experience provides a unified view of your entire data pipeline, queries, expressions, transformations, and related alerts, with clearer visual feedback and faster access to the settings that matter.
Add Prerequisites to Product Discount Functions
Discount functions now support prerequisites for product discount candidates, allowing you to define the "Buy X" portion of a Buy X, Get Y (BXGY) discount. In a BXGY discount, customers must purchase a specified quantity of one product (Buy X) to receive a discount on another product (Get Y).
Add Tags to Discounts
Starting in API version 2026-04, discounts support tags allowing you to efficiently label, group, and organize your discounts. What's new: The tags field has been added to all discount types Tags can be added, updated, and removed via the Admin API For more information, visit the Admin API documentation
Cart and checkout validation adds billing address and PO number error targets
As of API version 2026-04, you can validate billing addresses and purchase order (PO) numbers in Cart and Checkout Validation Functions. We've added billing address and PO Number to the function input graph and introduced new checkout field targets.
Create unpaid orders from subscription billing attempts
In the API 2026-04 release candidate version, you can now include a new field called paymentProcessingPolicy when creating a billing attempt using the subscriptionBillingAttemptCreate mutation. A billing attempt is an action to charge a customer based on their subscription.
More from DeepgramEvery Deepgram release →
New thought_signature field for Gemini function calling
The Voice Agent API now includes an optional thought_signature field in function call messages. Some Gemini models (3.0 and 3.1 families) require this as an additional function call identifier.
New volume parameter for Cartesia TTS
The Voice Agent API now supports an optional agent.speak.provider.volume parameter when using Cartesia as the TTS provider. Valid values range from 0.5 to 2.0 . For more details, see Configure the Voice Agent or the Cartesia volume, speed, and emotion documentation .
Container Images (release 260402)
- quay.io/deepgram/self-hosted-api:release-260402 Equivalent image to: quay.io/deepgram/self-hosted-api:1.181.3 quay.io/deepgram/self-hosted-engine:release-260402 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.114.5 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260402 Equivalent image to...
This Release Contains The Following Changes
- Certificate Endpoint Fix , Engine now responds to /v1/certificates in addition to /certificates , consistent with the other container images. See Certificate Status for details. Model Name Consistency , The /v1/models endpoint now returns a canonical_name field matching the model name used in /v1/listen requests.
Nova-3 Model Update
🌏 Nova-3 now supports the following new languages and language codes: Chinese (Mandarin, Simplified): zh , zh-CN , zh-Hans Chinese (Mandarin, Traditional): zh-TW , zh-Hant Access these models by setting model="nova-3" and the relevant language code in your request. Learn more about Nova-3 and supported languages on the Models and Language Overview page.
NVIDIA LLM provider now available
NVIDIA is now a supported LLM provider for the Voice Agent API. The following model is available in the Standard pricing tier: nemotron-3-nano-30B-A3B , Nemotron 3 Nano 30B A3B provides cost efficiency with high accuracy for targeted agentic tasks.
TTS speak speed (Early Access)
You can now control the speaking rate of Deepgram TTS in the Voice Agent API using the agent.speak.provider.speed parameter. This parameter accepts a float value between 0.7 and 1.5 , with 1.0 as the default.
Updated LLM models
New OpenAI models , Two new models are now available in the Standard pricing tier: gpt-5.4-nano gpt-5.4-mini Gemini 2.0 Flash deprecated , The gemini-2.0-flash model is now deprecated. We recommend migrating to gemini-2.5-flash or a newer Gemini model. See the Google models table for alternatives.