Deepgram Python Speech To Text
- 32 installs
- 454 repo stars
- Updated August 3, 2026
- deepgram/deepgram-python-sdk
Transcribe prerecorded or live audio with Deepgram Speech-to-Text v1 (/v1/listen) from Python via REST (transcribe_url/transcribe_file) or WebSocket streaming.
About
A Python SDK skill for basic Deepgram Speech-to-Text (ASR) on the /v1/listen endpoint, covering both REST one-shot transcription of files or URLs and continuous WebSocket streaming for live audio. Reach for it when you need a plain transcript - batch captioning, offline analysis, or real-time microphone/phone input - without analytics overlays. It is the foundation skill; separate skills add summarization, turn-taking, or full voice agents.
- REST transcribe_url / transcribe_file for batch and captions
- WebSocket client.listen.v1.connect for live streaming
- nova-3 model with smart_format and punctuation
- Auth via DEEPGRAM_API_KEY (Token, not Bearer)
Deepgram Python Speech To Text by the numbers
- 32 all-time installs (skills.sh)
- Ranked #9,069 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-speech-to-textAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 32 |
|---|---|
| repo stars | ★ 454 |
| Last updated | August 3, 2026 |
| Repository | deepgram/deepgram-python-sdk ↗ |
What it does
Transcribe prerecorded or live audio with Deepgram Speech-to-Text v1 (/v1/listen) from Python via REST (transcribe_url/transcribe_file) or WebSocket streaming.
Who is it for?
Straightforward audio transcription in Python, batch or live
Skip if: Summaries/sentiment/diarization, turn-taking, or full voice agents
When should I use this skill?
Calling client.listen.v1.media or client.listen.v1.connect
What you get
A working Deepgram v1 transcription call over REST or WebSocket.
- Python transcription client (REST or streaming)
By the numbers
- Auth header is 'Token <key>', not 'Bearer'
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
REST or WebSocket - which do I use?
REST for complete files/URLs; WebSocket for continuous live streaming.
What auth header does Deepgram use?
Authorization: Token <api_key>, not Bearer.