Deepgram Self-Hosted April 2024 Release (240426)

Container Images (release 240426)

• deepgram/onprem-api:release-240426

  • Equivalent image tag to deepgram/onprem-api:1.116.3

• deepgram/onprem-engine:release-240426

  • Equivalent image tag to deepgram/onprem-engine:3.68.12

  • Minimum required NVIDIA driver version: >=525.60.13

• deepgram/onprem-license-proxy:release-240426

  • Equivalent image tag to deepgram/onprem-license-proxy:1.6.0

• deepgram/onprem-billing:release-240426

  • Equivalent image tag to deepgram/onprem-billing:1.9.0

• deepgram/onprem-dgtools:release-240426

  • Equivalent image tag to deepgram/onprem-dgtools:2.1.7

This Release Contains The Following Changes

• Adds support for Aura text-to-speech (TTS) on a new speak/ endpoint! 🗣️

  • Reach out to your Deepgram account representative to receive new models to use TTS.

• Improves entity formatting.

• Improves intelligence features (sentiment, intents, topics, summarization).

• Lengthens the default streaming timeout from 10 seconds to 12 seconds, to align with Deepgram's hosted API.

• Adds configuration value (max_concurrently_loaded_models) to set an upper limit on the number of models loaded into memory, to mitigate memory errors and performance issues.

• Stability improvements, security patches, and bug fixes. 🐛