Name: deepgram-python-conversational-stt
Rating: 88.8 (1 reviews)
Author: deepgram

deepgram-python-conversational-stt

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.connect(...)`, Flux models, end-of-turn detection. Use `deepgram-python-speech-to-text` for standard v1 ASR, `deepgram-python-voice-agent` for full-duplex interactive assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", "listen.v2", "flux-general-en", "flux-general-multi".

1.19x

Quality

82%

Does it follow best practices?

Impact

100%

1.19x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

100%

26%

Live Transcription Client for Customer Support Monitoring

v2 client path, Flux model, string sample_rate, stream close

Criteria

Without context

With context

v2 client path

100%

Flux model used

100%

model param present

100%

sample_rate as string

100%

No language param

100%

v2 close stream

33%

100%

ListenV2CloseStream import

100%

v2 type imports

100%

EventType import

100%

conn.on() handlers

100%

API key from env

100%

13%

Conversation Turn Boundary Detector for Interview Coaching App

Dual-format message handling and 80ms chunk streaming

Criteria

Without context

With context

Typed object branch

100%

Dict fallback branch

100%

Dict type check

100%

turn_index access

100%

80ms chunk size

28%

100%

v2 client path

100%

Flux model

100%

v2 stream close

70%

100%

start_listening called

100%

No language param

100%

Async Multilingual Audio Transcription Service

Multilingual flux-general-multi with containerized audio

Criteria

Without context

With context

flux-general-multi model

100%

language_hint used

100%

No language param

100%

Omit encoding for WAV

100%

v2 client path

100%

Async client used

100%

v2 type imports

62%

100%

v2 stream close

60%

100%

API key from env

100%

sample_rate string type

100%

Repository: deepgram/deepgram-python-sdk
Commit: 16b9839

Evaluated: about 17 hours ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Live Transcription Client for Customer Support Monitoring Conversation Turn Boundary Detector for Interview Coaching App Async Multilingual Audio Transcription Service

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.