[PR #5456] [CLOSED] feat: Integrate Deepgram for real-time STT streaming and TTS synthesis #5451

Closed
opened 2026-06-05 15:21:24 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/5456
Author: @yugborana
Created: 4/16/2026
Status: Closed

Base: masterHead: feat/deepgram-tts-stt-integration


📝 Commits (2)

  • d6f6b85 feat: Integrate Deepgram for real-time STT streaming and TTS synthesis
  • cc29f47 lint

📊 Changes

17 files changed (+678 additions, -140 deletions)

View changed files

frontend/src/components/SpeechToText/DeepgramSttOptions/index.jsx (+28 -0)
frontend/src/components/TextToSpeech/DeepgramOptions/index.jsx (+109 -0)
📝 frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/HistoricalMessage/Actions/TTSButton/index.jsx (+1 -0)
frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/BrowserNative.jsx (+149 -0)
frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/Deepgram.jsx (+170 -0)
📝 frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/index.jsx (+18 -140)
frontend/src/media/ttsproviders/deepgram.png (+0 -0)
📝 frontend/src/models/system.js (+16 -0)
📝 frontend/src/pages/GeneralSettings/AudioPreference/stt.jsx (+9 -0)
📝 frontend/src/pages/GeneralSettings/AudioPreference/tts.jsx (+9 -0)
📝 server/.env.example (+5 -0)
📝 server/endpoints/system.js (+23 -0)
📝 server/models/systemSettings.js (+5 -0)
server/utils/TextToSpeech/deepgram/index.js (+88 -0)
📝 server/utils/TextToSpeech/index.js (+3 -0)
📝 server/utils/helpers/customModels.js (+30 -0)
📝 server/utils/helpers/updateENV.js (+15 -0)

📄 Description

Pull Request Type

  • [yes ] feat (New feature)
  • 🐛 fix (Bug fix)
  • ♻️ refactor (Code refactoring without changing behavior)
  • 💄 style (UI style changes)
  • 🔨 chore (Build, CI, maintenance)
  • 📝 docs (Documentation updates)

Relevant Issues

resolves #4732

Description

This PR introduces Deepgram as a native provider option for both Speech-to-Text (STT) and Text-to-Speech (TTS) within AnythingLLM.

Visuals (if applicable)

Additional Information

Developer Validations

  • [ yes] I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated (if applicable)
  • [yes ] I have tested my code functionality
  • [ yes] Docker build succeeds locally

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Mintplex-Labs/anything-llm/pull/5456 **Author:** [@yugborana](https://github.com/yugborana) **Created:** 4/16/2026 **Status:** ❌ Closed **Base:** `master` ← **Head:** `feat/deepgram-tts-stt-integration` --- ### 📝 Commits (2) - [`d6f6b85`](https://github.com/Mintplex-Labs/anything-llm/commit/d6f6b852fc04828f0793d4a8114f69de9484c556) feat: Integrate Deepgram for real-time STT streaming and TTS synthesis - [`cc29f47`](https://github.com/Mintplex-Labs/anything-llm/commit/cc29f47fb2cdc411d4101f953935df55433e0ff0) lint ### 📊 Changes **17 files changed** (+678 additions, -140 deletions) <details> <summary>View changed files</summary> ➕ `frontend/src/components/SpeechToText/DeepgramSttOptions/index.jsx` (+28 -0) ➕ `frontend/src/components/TextToSpeech/DeepgramOptions/index.jsx` (+109 -0) 📝 `frontend/src/components/WorkspaceChat/ChatContainer/ChatHistory/HistoricalMessage/Actions/TTSButton/index.jsx` (+1 -0) ➕ `frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/BrowserNative.jsx` (+149 -0) ➕ `frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/Deepgram.jsx` (+170 -0) 📝 `frontend/src/components/WorkspaceChat/ChatContainer/PromptInput/SpeechToText/index.jsx` (+18 -140) ➕ `frontend/src/media/ttsproviders/deepgram.png` (+0 -0) 📝 `frontend/src/models/system.js` (+16 -0) 📝 `frontend/src/pages/GeneralSettings/AudioPreference/stt.jsx` (+9 -0) 📝 `frontend/src/pages/GeneralSettings/AudioPreference/tts.jsx` (+9 -0) 📝 `server/.env.example` (+5 -0) 📝 `server/endpoints/system.js` (+23 -0) 📝 `server/models/systemSettings.js` (+5 -0) ➕ `server/utils/TextToSpeech/deepgram/index.js` (+88 -0) 📝 `server/utils/TextToSpeech/index.js` (+3 -0) 📝 `server/utils/helpers/customModels.js` (+30 -0) 📝 `server/utils/helpers/updateENV.js` (+15 -0) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [yes ] ✨ feat (New feature) - [ ] 🐛 fix (Bug fix) - [ ] ♻️ refactor (Code refactoring without changing behavior) - [ ] 💄 style (UI style changes) - [ ] 🔨 chore (Build, CI, maintenance) - [ ] 📝 docs (Documentation updates) ### Relevant Issues resolves #4732 ### Description This PR introduces Deepgram as a native provider option for both Speech-to-Text (STT) and Text-to-Speech (TTS) within AnythingLLM. ### Visuals (if applicable) <!-- Add screenshots or screen recordings to demonstrate the changes, especially for UI updates. --> ### Additional Information <!-- Add any other context about the Pull Request here that was not captured above. --> ### Developer Validations <!-- All of the applicable items should be checked. --> - [ yes] I ran `yarn lint` from the root of the repo & committed changes - [ ] Relevant documentation has been updated (if applicable) - [yes ] I have tested my code functionality - [ yes] Docker build succeeds locally --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 15:21:24 -04:00
yindo closed this issue 2026-06-05 15:21:24 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5451