Deepgram Changelog

Stay up to date with enhancements to our AI Speech Platform and ecosystem

Deepgram On-premises December Release (231207)

Container Images (release 231207) deepgram/onprem-api:release-231207 Equivalent image tag to deepgram/onprem-api:1.109.0 deepgram/onprem-engine:release-231207 Equivalent image tag to deepgram/onprem-engine:3.59.6 deepgram/onprem-license-proxy:release-231207 Equivalent image tag to deepgram/onprem-license-proxy:1.5.1 deepgram/onprem-billing:release-231207 Equivalent image tag to deepgram/onprem-billing:1.8.0 deepgram/onprem-dgtools:release-231207 Equivalent image tag to deepgram/onprem-dgtools:2.1.5 This Release Contains The Following Changes Improved support for container health checks/probes. There are now native endpoints available for all Deepgram containers to help you more easily manage container lifecycles and system maintenance. These probes can be configured with Kubernetes, or any other container orchestration technology that supports health probes. For help with using these endpoints, please contact your Deepgram Account Representative for updated configuration files. Further documentation will also be published describing available health probe endpoints, and will be linked to this changelog. Stability improvements, security patches, and bug fixes.🐛

Deepgram On-premises November Release (231114)

Container Images (release 231114) deepgram/onprem-api:release-231114 Equivalent image tag to deepgram/onprem-api:1.107.2 deepgram/onprem-engine:release-231114 Equivalent image tag to deepgram/onprem-engine:3.59.6 deepgram/onprem-license-proxy:release-231114 Equivalent image tag to deepgram/onprem-license-proxy:1.5.0 deepgram/onprem-billing:release-231114 Equivalent image tag to deepgram/onprem-billing:1.8.0 deepgram/onprem-dgtools:release-231114 Equivalent image tag to deepgram/onprem-dgtools:2.1.5 This Release Contains The Following Changes Support for Nova 2 models in general availability . License Proxy and Billing containers now accept configuration files license-proxy.toml and billing.toml , similar to API’s api.toml and Engine’s engine.toml . Compared to CLI flags, configuration files are easier to place into source control for comparing config changes to your onprem deployment over time. Reach out to your Deepgram Account Representative if you have an existing deployment and would like to migrate to using configuration files for License Proxy or Billing containers. Stability improvements, security patches, and bug fixes.🐛

Improvements to Language Detection

Deepgram now offers the ability to restrict which languages will be detected by Deepgram's language detection algorithm. If you currently use the detect_language=true feature of Deepgram but your audio files are, for example, only in English and Spanish, you can improve the accuracy of your results by restricting which languages will be detected. Here's an example of how to restrict the detectable languages to only English ( en ) and Spanish ( es ): curl \ --request POST \ --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \ --header 'Content-Type: audio/wav' \ --data-binary @youraudio.wav \ --url 'https://api.deepgram.com/v1/listen?detect_language=en&detect_language=es' This functionality is available for pre-recorded audio and Deepgram's models (not Whisper). For more information, head over to our developer documentation .

Announcing Nova-2 GA & Additional Language Support

Natalie Rutgers

We are pleased to announce additional language support and the General Availability (GA) of Nova-2, our newest speech-to-text model. Deepgram Nova-2 Nova-2 presents the new state-of-the-art in speech recognition. Read about Nova-2's performance and benchmarks in our announcement . The complete list of available use cases and languages can be found in our documentation . Nova-2 is available to all Pay as you Go and Growth customers. Premium customers will have access to Nova-2 at contracted Nova rates. If you are a Premium customer and do not have access, please reach out to your account team. Pricing for Nova-2 is available at deepgram.com/pricing .

Deepgram On-premises October Release (231026)

Container Images (release 231026) deepgram/onprem-api:release-231026 Equivalent image tag to deepgram/onprem-api:1.106.0 deepgram/onprem-engine:release-231026 Equivalent image tag to deepgram/onprem-engine:3.59.2 deepgram/onprem-license-proxy:release-231026 Equivalent image tag to deepgram/onprem-license-proxy:1.4.3 deepgram/onprem-billing:release-231026 Equivalent image tag to deepgram/onprem-billing:1.7.3 deepgram/onprem-dgtools:release-231026 Equivalent image tag to deepgram/onprem-dgtools:2.1.5 This Release Contains The Following Changes More control with language detection features! You can now restrict which languages can be detected , and view the language detection confidence score in returned ASR results. Adjusted order of operations with async requests to more consistently return a request ID immediately. Improved model loading logic. If you have explicit model loading directives under the features section of your engine.toml configuration file, you can remove it when upgrading to more recent releases. Stability improvements, security patches, and bug fixes.🐛

Deepgram Log Usage Data limited to 90 days

On Oct 18th 2023 Deepgram will be introducing a 90 day limit on the storage of log usage data for all of our customers. What this means: In the Deepgram Console > Usage > Logs users will now only be able to query for log data for up to 90 days of time. When using the Deepgram API Usage endpoint users will now only be able to query for usage data up to 90 days of time. You can still retrieve Summarized Usage for greater than 90 days. Questions? Please refer to our Documentation for more details on Usage & Logs.

Improved Redaction Functionality

Deepgram’s latest update offers enhanced redaction options for customers submitting pre-recorded audio to our hosted endpoint. Customers can now select specific types of entities, like locations, URLs, or names, to be redacted from their transcriptions. Here’s an example of how to accomplish redacting different types of entities (in this case, city names, ages, and emails): curl \ --request POST \ --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \ --header 'Content-Type: audio/wav' \ --data-binary @youraudio.wav \ --url 'https://api.deepgram.com/v1/listen?redact=location_city&redact=age&redact=email_address' For more information, head over to our developer documentation .

Deepgram On-premises September Release (230920)

Container Images (release 230920) deepgram/onprem-api:release-230920 Equivalent image tag to deepgram/onprem-api:1.102.1 deepgram/onprem-engine:release-230920 Equivalent image tag to deepgram/onprem-engine:3.58.1 deepgram/onprem-license-proxy:release-230920 Equivalent image tag to deepgram/onprem-license-proxy:1.4.2 deepgram/onprem-billing:release-230920 Equivalent image tag to deepgram/onprem-billing:1.7.2 deepgram/onprem-metrics-server:release-230920 Equivalent image tag to deepgram/onprem-metrics-server:2.0.6 deepgram/onprem-dgtools:release-230920 Equivalent image tag to deepgram/onprem-dgtools:2.1.5 This Release Contains The Following Changes Support for Deepgram Nova-2 . Please contact Deepgram Customer Success to request access to this new model architecture. Significant improvements in diarization quality for batch requests. Addresses a memory leak in onprem-engine that originated in a upstream dependency. This memory leak was only present in the August (230804) release. onprem-dgtools now accepts licensing information passed via the DEEPGRAM_API_KEY environment variable, similar to onprem-api and onprem-engine . Other stability improvements & bug fixes.🐛

Introducing Nova-2 Early Access

Natalie Rutgers

Deepgram is excited to announce early access to our next-gen speech-to-text model, Nova-2. As shared in our Marketing Announcement , Nova-2: Outperforms all alternatives in terms of accuracy, speed, and cost ( starting at $0.0043/min ). Is 18% more accurate than our previous Nova model and offers a 36% relative WER improvement over OpenAI Whisper (large). Pay as You Go and Growth users may access this model immediately in the API Playground or by requesting model=nova-2-ea in their API requests. Enterprise customers can reach out to their account representative or Contact Us for access. Nova-2 Early Access supports hosted and on-prem transcription of pre-recorded and streaming English audio. Read more about Nova-2 in the Deepgram Documentation .

Deepgram On-premises August Release (230804)

Container Images (release 230804) deepgram/onprem-api:1.97.1 deepgram/onprem-engine:3.53.6 deepgram/onprem-license-proxy:1.4.2 deepgram/onprem-billing:1.7.2 deepgram/onprem-metrics-server:2.0.6 deepgram/onprem-dgtools:2.1.4 Deepgram On-premises Release Tags deepgram/onprem-api:release-230804 deepgram/onprem-engine:release-230804 deepgram/onprem-license-proxy:release-230804 deepgram/onprem-billing:release-230804 deepgram/onprem-metrics-server:release-230804 deepgram/onprem-dgtools:release-230804 This Release Contains The Following Changes Summarization efficiency improvements for broader GPU compatibility. Summarization-related errors and warnings produced by API calls have been expanded and made more detailed; please see our docs on this topic . Opus compatibility improvements with multichannel audio. Added a configuration parameter for batch sizes specifically for Whisper models. Please contact your account manager for more details. Added additional error reporting for streaming-related failures when the initial request includes the debug=true query parameter. Stability improvements and bug fixes.🐛

Introducing New Summarization

We're excited to announce the release of our first domain-specific language model (DSLM) for speech summarization of call center interactions. You can request our new Summarization API endpoint by adding a summarize parameter set to v2 in the API call. It will then return a summary object in the response body of the output. The summary object includes status and a concise summary of the entire conversation. The URL query to call the DSLM-powered Summarization API might look like this: https://api.deepgram.com/v1/listen?summarize=v2 Example curl request: curl --location --request POST 'https://api.deepgram.com/v1/listen?summarize=v2' \ --header 'Authorization: Token <Your API KEY>' \ --header 'Content-Type: audio/wave' \ --data-binary '@/Path to file' You can send requests to the API with an Authorization header that references your project's API key Authorization: Token YOUR_DEEPGRAM_API_KEY The output response will contain the generated summary based on the provided audio. Summarization V2 supports English and Pre-Recorded audio. Primary difference between V1 (summarize=true) and V2 (summarize=v2) V1 provides summaries per channel. V2 provides a single summary across all the channels. V1 response contains summary objects (with summary, start, and end word). V2 response contains a single object with result and short key. V2 of our Summarization offers improved performance in terms of quality, content, and readability of generated summaries. For the best results moving forward, we recommend leveraging V2 of our summarization. Learn more about using our new Summarization V2 feature. Test Summarization V2 using our API Playground. We are thrilled to get this feature into your hands and await your feedback. Please share it with us at Product Feedback or your dedicated support channel.

Deepgram On-premises July Release (230705)

Container Images (release 230705) deepgram/onprem-api:1.95.0 deepgram/onprem-engine:3.53.0 deepgram/onprem-license-proxy:1.4.1 deepgram/onprem-billing:1.7.1 deepgram/onprem-metrics-server:2.0.6 deepgram/onprem-dgtools:2.1.4 Deepgram On-premises Release Tags deepgram/onprem-api:release-230705 deepgram/onprem-engine:release-230705 deepgram/onprem-license-proxy:release-230705 deepgram/onprem-billing:release-230705 deepgram/onprem-metrics-server:release-230705 deepgram/onprem-dgtools:release-230705 This Release Contains The Following Changes Support for license keys created and managed from Deepgram Console . Support for new Domain-Specific Language Model powered summarization. Learn more . The minimum supported CUDA runtime version for onprem-engine has changed from 11.0.3 to 11.3.1. Systems using NVIDIA drivers before version 450.80.02 might encounter errors when attempting to start this release of onprem-engine. Deepgram recommends installing the latest NVIDIA drivers for maximum compatibility, stability, and performance. The onprem-engine container size has been significantly reduced. Reduction in frequency of hallucinations when using Deepgram enhanced models. Improvements to accuracy of reported word times when using existing Whisper models. Duration values specified in the onprem-api configuration file can now include unit suffixes. For example, instead of writing 480 it is now possible to write 4m. Values with no suffix are assumed to be seconds. Stability improvements and bug fixes.🐛

Introducing Nova support for the Spanish language

Nova is Deepgram's most powerful and affordable speech-to-text model. Training on this model spans over 100 domains and 47 billion tokens, making it the deepest-trained automatic speech recognition (ASR) model to date. Nova doesn't just excel in one specific domain — it is ideal for a wide array of voice applications that require high accuracy in diverse contexts. This model now support the Spanish language es and es-419. Learn more about using our new Nova Model. Quickly test out this new Model using our API Playground. Learn more about Deepgram Language Support.

Deepgram On-premises June Release (230606)

Container Images (release 230606) deepgram/onprem-api:1.92.2 deepgram/onprem-engine:3.48.2 deepgram/onprem-license-proxy:1.4.1 deepgram/onprem-billing:1.7.1 deepgram/onprem-metrics-server:2.0.6 deepgram/onprem-dgtools:2.1.4 Deepgram On-premises Release Tags This release marks the first official Deepgram On-premises release to include support for a release tag. Instead of specifying a specific version tag for the individual container images, all of the images now support the release-230606 image tag. deepgram/onprem-api:release-230606 deepgram/onprem-engine:release-230606 deepgram/onprem-license-proxy:release-230606 deepgram/onprem-billing:release-230606 deepgram/onprem-metrics-server:release-230606 deepgram/onprem-dgtools:release-230606 This Release Contains The Following Changes New, easy-to-use deployments with embedded default configurations in the container images. Simply add the container environment variable DEEPGRAM_API_KEY to the docker-compose.yml stanzas for the api and engine container images. For more information, refer to the on-prem deployment documentation for your specific deployment OS. Deepgram’s new Speaker Diarization architecture with 53.1% improved accuracy overall from the previous version, a 10X faster turnaround time, and language-agnostic support, unlocking accurate speaker labeling for transcription use-cases around the globe. Currently only pre-recorded audio is supported. We are ending support for our legacy Diarization model. Please reach out to Deepgram Customer Success to ensure you are have the latest supported Diarization model. Deepgram’s revamped automatic language detection feature which enables users to automatically detect the dominant language in an audio file and transcribe the output in the detected language, providing unparalleled accuracy in detecting and transcribing audio data in over 15+ languages and dialects, including English, Spanish, Hindi, Dutch, French, and German. Currently only pre-recorded audio is supported. Addresses an issue where onprem-license-proxy was inappropriately coloring logs when directed to output to a file. Addresses CVE-2020-26235 in onprem-license-proxy . Other stability improvements & bug fixes.🐛

Stream KeepAlive

Customers can now keep Deepgram streaming connections open during periods where no audio data is being sent. Previously, if no audio was being sent over the websocket, connections would close after a short window of time. We’ve introduced a new KeepAlive WebSocket message that clients can use to indicate to Deepgram that the WebSocket should be kept open even though no data is being sent through. For more information, visit our documentation .

Page 1 of 6

Stop building work-arounds for STT systems that don't work.

Start Free Talk to an expert