CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-js-speech-to-text

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers `client.listen.v1.media.transcribeUrl` / `transcribeFile` (REST) plus `client.listen.v1.createConnection()` / `connect()` (WebSocket). Use `deepgram-js-audio-intelligence` for summarize/sentiment/topics/diarize overlays, `deepgram-js-conversational-stt` for Flux turn-taking on `/v2/listen`, and `deepgram-js-voice-agent` for full-duplex assistants. Triggers include "transcribe", "speech to text", "STT", "listen.v1", "nova-3", "live transcription", and "websocket transcription".

72

Quality

89%

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

86%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.

A tight, executable skill body with concrete examples and a well-structured reference ladder. Workflow sequencing is strong; the only gap is a missing explicit validation checkpoint for the live-socket open/handshake state.

Suggestions

Add a brief validation checkpoint after `waitForOpen()` (e.g. assert the socket is open / handle the case where it failed) before sending media, so the live workflow has an explicit failure-recovery loop.

Trim the inline WSS parameter and client-message lists in 'Key parameters / API surface' since they duplicate `reference.md` and the OpenAPI/AsyncAPI specs already linked.

DimensionReasoningScore

Conciseness

Mostly lean with executable snippets and no padding of basic concepts, but the parameter lists and API-reference section restate API surface that the bundled OpenAPI/reference.md already cover, so a few tokens could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready REST and WebSocket examples drawn from real repo files, plus exact client-message methods, model/language params, and concrete gotchas covering the common cases.

5 / 5

Workflow Clarity

The two-stage WebSocket flow (createConnection -> handlers -> connect -> waitForOpen -> sendMedia -> sendFinalize) is explicitly sequenced with gotchas, but there is no validation/checkpoint for confirming the socket opened before streaming or for handling `Results` parse failures.

4 / 5

Progressive Disclosure

SKILL.md acts as a concise overview with a clearly layered API-reference ladder (in-repo reference.md -> OpenAPI -> AsyncAPI -> Context7 -> product docs), all one level deep and well-signaled; no bundle files exist so structure is on the main file.

5 / 5

Total

18

/

20

Passed

Description

92%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 highly specific, well-scoped description with explicit triggers and clear cross-skill boundaries. It answers both what and when with concrete API surface rather than vague language.

DimensionReasoningScore

Specificity

Names concrete SDK calls (`transcribeUrl`/`transcribeFile`, `createConnection()`/`connect()`) across both REST and WebSocket modes plus cross-skill routing, giving comprehensive coverage of concrete actions.

5 / 5

Completeness

Opens with an explicit 'Use when...' trigger and states precisely what it covers (v1 prerecorded/live transcription) with concrete trigger phrases, answering both what and when.

5 / 5

Trigger Term Quality

Includes natural user phrases ("transcribe", "speech to text", "STT", "live transcription") plus technical tokens ("listen.v1", "nova-3"), but a few natural synonyms ("closed captions", "asr", "real-time transcription") are absent.

4 / 5

Distinctiveness Conflict Risk

Explicitly disambiguates from sibling skills (`deepgram-js-audio-intelligence`, `deepgram-js-conversational-stt`, `deepgram-js-voice-agent`) with version-specific triggers, giving a clear niche and minimal conflict risk.

5 / 5

Total

19

/

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-js-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.