CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-python-speech-to-text

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribe_url` / `transcribe_file` (REST) and `client.listen.v1.connect` (WebSocket). Use this skill for basic ASR; use `deepgram-python-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-python-conversational-stt` for turn-taking v2/Flux, and `deepgram-python-voice-agent` for full-duplex assistants. Triggers include "transcribe", "live transcription", "speech to text", "STT", "listen endpoint", "nova-3", "listen.v1".

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Excellent reference skill: executable code for every common path, dense non-obvious gotchas, and clean separation of overview from external detail. The only soft spot is the absence of an explicit validate/retry loop in the streaming workflow, which is minor given the skill's nature.

DimensionReasoningScore

Conciseness

Lean throughout — quick starts and the interim/final flag-semantics bullets are dense and assume competence; no space wasted explaining what a WebSocket or SDK is. 'request= accepts raw bytes or an iterator of bytes' is exactly the kind of non-obvious detail that earns its tokens.

5 / 5

Actionability

Copy-paste-ready, executable code for every common case — REST URL, REST file, live WebSocket with real handlers, AsyncDeepgramClient, and the deferred-callback webhook pattern — each with concrete params and exact method names.

5 / 5

Workflow Clarity

The WebSocket example is a clear, ordered sequence (open → register handlers → start_listening in a thread → send chunks → send_finalize → close) with key checkpoints like 'send_finalize before exiting or the last partial is dropped'. It lacks an explicit validate→fix→retry feedback loop, but the skill is not a destructive/batch operation, so no cap applies.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep references out to reference.md, the canonical OpenAPI/AsyncAPI URLs, Context7, product docs, and named example/test files in the repo — the body stays an overview while detail lives elsewhere.

5 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A model description: concrete capabilities, explicit use-when guidance with natural trigger terms, and crisp boundary-setting against sibling skills. Both the 'what' and 'when' are answered with no fluff.

DimensionReasoningScore

Specificity

Names the domain plus concrete actions and API surfaces — 'transcribe_url / transcribe_file (REST) and client.listen.v1.connect (WebSocket)' for 'prerecorded or live audio transcription' — with comprehensive, non-generic coverage.

5 / 5

Completeness

Explicitly answers both 'what' (Deepgram STT v1 transcription via REST and WSS, specific methods) and 'when' ('Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Lists natural terms a user would say plus synonyms and specifics — 'transcribe', 'live transcription', 'speech to text', 'STT', 'listen endpoint', 'nova-3', 'listen.v1' — comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche (basic ASR) and actively steers three sibling skills (audio-intelligence, conversational-stt, voice-agent) to their own triggers, minimizing wrong-skill activation.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
deepgram/deepgram-python-sdk
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.