Deepgram Python Conversational Stt
- 25 installs
- 454 repo stars
- Updated August 3, 2026
- deepgram/deepgram-python-sdk
Add turn-aware streaming transcription with Deepgram Conversational STT v2 / Flux (/v2/listen) and end-of-turn detection to a Python conversational UI.
About
A Python SDK skill for Deepgram Conversational STT v2 (Flux) at the /v2/listen WebSocket endpoint, giving turn-aware streaming transcription with explicit end-of-turn detection. Reach for it when building a conversational UI that needs clear turn boundaries and barge-in handling rather than general-purpose captions, using client.listen.v2.connect and Flux models like flux-general-en. It sits between plain v1 ASR and a full interactive voice agent.
- Turn-aware streaming STT at /v2/listen with Flux models
- Explicit end-of-turn (EOT) detection for conversational UIs
- client.listen.v2.connect with typed TurnInfo events
- Lower-latency turn signals than v1 utterance_end
Deepgram Python Conversational Stt by the numbers
- 25 all-time installs (skills.sh)
- Ranked #9,764 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/deepgram/deepgram-python-sdk --skill deepgram-python-conversational-sttAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 25 |
|---|---|
| repo stars | ★ 454 |
| Last updated | August 3, 2026 |
| Repository | deepgram/deepgram-python-sdk ↗ |
What it does
Add turn-aware streaming transcription with Deepgram Conversational STT v2 / Flux (/v2/listen) and end-of-turn detection to a Python conversational UI.
Who is it for?
Conversational UIs needing explicit turn boundaries and low-latency EOT signals
Skip if: Batch/caption transcription or a full STT+LLM+TTS agent
When should I use this skill?
Using client.listen.v2.connect with Flux models for turn-aware audio
What you get
A working Flux v2 streaming transcription loop that emits turn and end-of-turn events.
- Python streaming client using Deepgram Flux v2
By the numbers
- v2/listen is WSS-only - no REST path
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Is there a REST path for v2 listen?
No - v2/listen is WebSocket-only.
When should I use this over v1 STT?
When you need explicit turn-taking and end-of-turn detection for conversational audio.