gemini-transcribe-wrapper

A free video transcription CLI using gemini-3.5-transcribe that outputs .diarized.srt, .srt, and .txt files.

Quick Start

Prerequisites

Install the tool

(Supports Python 3.10–3.13; Python 3.12 is recommended)

The wrapper is best run via uvx (one-shot, no install step — recommended for free-tier multi-key usage where each run spreads load differently):

Linux / macOS:

# Set your multiple free-tier API keys in shell variables first:
export key1=AIzaSyA...
export key2=AIzaSyB...

# Then run any number of input files in one go:
uvx --python 3.12 --from gemini-transcribe-wrapper@latest gtw --gemini-api-keys $key1;...;$key10 *.mp4

For a persistent install (so you can run gtw directly without uvx ...):

export GEMINI_API_KEY=your_key_here
uv tool install --python 3.12 gemini-transcribe-wrapper@latest
gtw -v

Windows (Command Prompt) — persistent install:

set GEMINI_API_KEY=your_key_here
uv tool install --python 3.12 gemini-transcribe-wrapper@latest
gtw -v

Transcribe for free

# Recommended — multi-key (10 free-tier keys for active/cooldown pool):
uvx --python 3.12 --from gemini-transcribe-wrapper@latest gtw --gemini-api-keys $key1;...;$key10 *.mp4

# Single-key (if you only have one free-tier key or use a paid tier):
gtw sample.mp4   # with `GEMINI_API_KEY` set
# or
gtw --gemini-api-keys YOUR_API_KEY sample.mp4

Output (default: --no-diarize — no speaker labels, fewer API calls):

sample.transcript.json
sample.srt
sample.txt

For speaker-diarized output, opt in with --diarize:

gtw --diarize sample.mp4

Output (with --diarize):

sample.diarized.transcript.json
sample.diarized.srt
sample.srt
sample.txt

What are improved by this project?

1. Transcription Quality & Usability

  • Raw AI Output to Ready-to-Use Subtitles: Converts JSON transcription output directly into formatted .srt (with natural timestamp alignment and line breaking), readable .txt paragraphs, and (with --diarize) .diarized.srt files in a single run.
  • Korean Transcription Error Correction: Automatically post-processes common Gemini Korean misrecognitions (e.g. correcting erroneous romanized "su" into "수" in patterns like "~할 su 있다/없다", "~할 su밖에", "~할 su도", "~할 su가" with proper Korean spacing and particle attachment).
  • Fast Speaker Labeling: Allows iterative speaker renaming (--speakers 'spk:0=Host;spk:1=Guest') instantly without re-calling the API by reusing saved transcripts.

2. Overcoming Free-Tier Limits & Constraints

  • Audio Length Limit Bypass: Handles audio files of any length by auto-splitting into safe units (59-min logical units for --no-diarize, 29-min chunks for --diarize) and transparently stitching timestamps together.
  • Rate Limit Throttling (Max 2 RPM): Applies a monotonic rate limiter (default 60s interval) across all chunks and multi-file batches to prevent 429 rate-limit errors.
  • Daily Quota Tracking: Tracks daily Pacific-time API usage locally (~/.cache/gemini-transcribe-wrapper/usage-<sha256(key)[:12]>.json) with masked key logging (e.g. API call attempts today 2026-08-30 (PT) with key 'AIza****abcd': attempted 3 (free tier limit: ~25)).
  • Free-Tier-Friendly Defaults: --no-diarize is the default to maximize audio duration per API call and minimize API consumption.
  • Multi-Key Round-Robin + Active/Cooldown Pool: Pass several keys with --gemini-api-keys=KEY1;KEY2;.... The wrapper keeps a separate _active_pool (round-robin target) and _cooldown_pool (keys that hit 429). On a 429 the key is moved into the cooldown pool immediately — no same-key retry. When the active pool drains, the wrapper sleeps _COOLDOWN_SECS (10 min default) and reactivates every cooldown key in batch, then retries the chunk. With 16–20 free-tier keys (2 Gmail accounts × 10 projects each) you can run continuously even when most keys have hit the daily cap. See Multi-Key Strategy for sizing guidance.
  • Graceful 429 Abort (single key): On HTTP 429 (rate limit or quota exhausted) when running with a single key, calculates the exact sleep seconds until the Pacific midnight reset and aborts the batch immediately (exit code 2) to prevent wasting quota.
  • Custom Vocabulary File (--custom-vocabulary-file): Register company-internal / frequently-misrecognized terms in a plain text file (one per line) and the wrapper biases the transcript toward those terms as a post-recognition step. Up to 1000 words are accepted by the model; Google recommends ≤100 lines for best results. Missing file → warning + silently ignored. See Custom Vocabulary for details.
  • Multi-Language Hint (--language-codes): Forward a comma-separated list of BCP-47 codes (default ko-KR,en-US) to Gemini as language_codes. Pass an empty string (--language-codes="") to enable Gemini's auto language detection for mixed-language content. See Language Hints for details.

Documentation & Guides

Relevant Repositories

License

MIT

Project links

Data verified by PyPI on Sep 2, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.1.10)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for tayaee from gravatar.com tayaee

Credits

Author: tayaee

GitHub Statistics

Data verified by PyPI on Sep 2, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python >=3.10

Tags

diarization gemini speech-to-text srt stt subtitles transcription

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gemini_transcribe_wrapper-0.0.67.tar.gz (93.5 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gemini_transcribe_wrapper-0.0.67-py3-none-any.whl (71.9 kB view details)

Uploaded Python 3

File details

Details for the file gemini_transcribe_wrapper-0.0.67.tar.gz.

File metadata

File hashes

Hashes for gemini_transcribe_wrapper-0.0.67.tar.gz
Algorithm Hash digest
SHA256 f4b5e96e051e77be59fbf2d254ef87c10affa45babee308f40c1aedad258795a
MD5 d5476fca91634d0bfdb0d3d1152f5c22
BLAKE2b-256 90f167348bbff80193801435629e5e60e0369f94e4b7b2bce2a44135eee997cd

See more details on using hashes here.

Provenance

The following attestation bundles were made for gemini_transcribe_wrapper-0.0.67.tar.gz:

Publisher: publish.yml on tayaee/gemini-transcribe-wrapper

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file gemini_transcribe_wrapper-0.0.67-py3-none-any.whl.

File metadata

File hashes

Hashes for gemini_transcribe_wrapper-0.0.67-py3-none-any.whl
Algorithm Hash digest
SHA256 3bb36f44a29d8a502768c7ccbb0b9c987931a9cee14c7a5d2f1420991be207ac
MD5 68fe7943e2815238e619d15762946f88
BLAKE2b-256 58b6738cca2a89a143a85a3f0f33279e7c53ced0e213d285c81d0239f9a053d3

See more details on using hashes here.

Provenance

The following attestation bundles were made for gemini_transcribe_wrapper-0.0.67-py3-none-any.whl:

Publisher: publish.yml on tayaee/gemini-transcribe-wrapper

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.10

2 files

0.1.9

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

0.1.4

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

0.0.69

2 files

0.0.68

2 files

This release

0.0.67 This release

2 files

0.0.66

2 files

0.0.65

2 files

0.0.64

2 files

0.0.63

2 files

0.0.62

2 files

0.0.61

2 files

0.0.60

2 files

0.0.59

2 files

0.0.58

2 files

0.0.57

2 files

0.0.56

2 files

0.0.55

2 files

0.0.54

2 files

0.0.53

2 files

0.0.52

2 files

0.0.51

2 files

0.0.50

2 files

0.0.49

2 files

0.0.48

2 files

0.0.47

2 files

0.0.46

2 files

0.0.45

2 files

0.0.44

2 files

0.0.43

2 files

0.0.42

2 files

0.0.41

2 files

0.0.40

2 files

0.0.39

2 files

0.0.38

2 files

0.0.37

2 files

0.0.35

2 files

0.0.34

2 files

0.0.32

2 files

0.0.31

2 files

0.0.30

2 files

0.0.29

2 files

0.0.28

2 files

0.0.27

2 files

0.0.26

2 files

0.0.25

2 files

0.0.24

2 files

0.0.23

2 files

0.0.22

2 files

0.0.21

2 files

0.0.20

2 files

0.0.19

2 files

0.0.18

2 files

0.0.17

2 files

0.0.16

2 files

0.0.15

2 files

0.0.14

2 files

0.0.13

2 files

0.0.12

2 files

0.0.11

2 files

0.0.10

2 files

0.0.9

2 files

0.0.8

2 files

0.0.7

2 files

0.0.6

2 files

0.0.5

2 files

0.0.4

2 files

0.0.3

2 files

0.0.2

2 files

0.0.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page