pypi.org "transcription" keyword
livekit-plugins-smallestai 1.8.11
Agent Framework plugin for speech synthesis and recognition with Smallest AI.80 versions - Latest release: 5 days ago - 11.9 thousand downloads last month - 15,096 stars on GitHub - 1 maintainer
kinocut 2.0.0 💰
Trusted, guardrailed video editing for AI agents. FFmpeg, Hyperframes, repurposing tools, Python ...25 versions - Latest release: about 2 hours ago - 8.85 thousand downloads last month - 262 stars on GitHub - 1 maintainer
mediasense 0.5.2
Let Claude listen to audio and watch video: transcribe voice messages, podcasts and recordings wi...4 versions - Latest release: about 3 hours ago - 0 downloads last month - 1 stars on GitHub - 1 maintainer
gaik 0.8.12
General AI Kit - Reusable AI/ML components for Python84 versions - Latest release: about 4 hours ago - 1.3 thousand downloads last month - 101 stars on GitHub
vision-agents-plugins-mistral 0.6.9
Mistral Voxtral STT integration for Vision Agents34 versions - Latest release: 3 months ago - 213 downloads last month - 8,199 stars on GitHub - 2 maintainers
vision-agents-plugins-deepgram 0.6.9
Deepgram STT and TTS integration for Vision Agents62 versions - Latest release: 3 months ago - 1.21 thousand downloads last month - 8,199 stars on GitHub - 2 maintainers
vision-agents-plugins-moonshine 0.1.11
Moonshine STT integration for Vision Agents10 versions - Latest release: about 1 year ago - 331 downloads last month - 8,199 stars on GitHub - 2 maintainers
vision-agents-plugins-assemblyai 0.6.9
AssemblyAI streaming STT integration for Vision Agents27 versions - Latest release: 3 months ago - 148 downloads last month - 8,199 stars on GitHub - 2 maintainers
crisperwhisper 2.1.0
Fast inference for CrisperWhisper speech recognition models9 versions - Latest release: about 7 hours ago - 6.61 thousand downloads last month - 1,476 stars on GitHub - 1 maintainer
scriptivox 0.1.0
Official Python SDK for the Scriptivox transcription API: upload, transcribe, wait, export SRT/VT...1 version - Latest release: about 10 hours ago - 1 maintainer
Top 9.5% on pypi.org
13 versions - Latest release: over 1 year ago - 1 dependent repositories - 1.62 thousand downloads last month - 2,048 stars on GitHub - 1 maintainer
diart 0.9.2 💰
A python framework to build AI for real-time speech13 versions - Latest release: over 1 year ago - 1 dependent repositories - 1.62 thousand downloads last month - 2,048 stars on GitHub - 1 maintainer
scribed 0.0.9
One facade over many speech-to-text (ASR) engines, plus a ledger to help you choose between them.9 versions - Latest release: 15 days ago - 64 downloads last month - 0 stars on GitHub - 1 maintainer
tippiti 1.0.2
Official Python client for the Tippiti API – the transcription and dictation platform for physici...2 versions - Latest release: 7 months ago - 69 downloads last month - 0 stars on GitHub - 1 maintainer
transcribe-anything 4.1.2
Uses Whisper AI to transcribe speech from video and audio files. Also accepts URLs for YouTube, R...113 versions - Latest release: about 2 months ago - 1 dependent package - 1 dependent repositories - 497 downloads last month - 1,483 stars on GitHub - 1 maintainer
pipecat-local-stt-server 0.5.1
Standalone local WebSocket transcription (STT) server, client, and pluggable ASR backends for the...9 versions - Latest release: 11 days ago - 42 downloads last month - 8 stars on GitHub - 1 maintainer
dienr 0.1.0
Deconvolution of Isoform Expression from Nascent RNAs1 version - Latest release: about 15 hours ago - 1 maintainer
notepipe 0.6.0
Extensible engine and CLI that turns video and audio into Markdown notes13 versions - Latest release: 7 days ago - 0 downloads last month - 3 stars on GitHub - 1 maintainer
notepipe-asr-speech-swift 0.1.3
Speech recognition adapter for notepipe on Apple silicon, using speech-swift (MLX and Core ML)4 versions - Latest release: 8 days ago - 0 downloads last month - 3 stars on GitHub - 1 maintainer
audio8bit 0.0.3
Turn a song into an 8-bit / chiptune arrangement of its melody (vocal or instrumental)4 versions - Latest release: 4 months ago - 69 downloads last month - 90 stars on GitHub - 1 maintainer
dtelecom-stt 0.2.0
Python SDK for dTelecom real-time speech-to-text with x402 micropayments2 versions - Latest release: 9 months ago - 23 downloads last month - 1 stars on GitHub - 1 maintainer
transcripy 1.0.0
Local transcription of voicebot calls and phone recordings into timed speaker turns.1 version - Latest release: about 20 hours ago - 0 stars on GitHub - 1 maintainer
voxscriber 0.3.0
Local speaker diarization using Parakeet or MLX Whisper (macOS) or faster-whisper (Linux/CUDA) an...29 versions - Latest release: about 21 hours ago - 130 downloads last month - 5 stars on GitHub - 1 maintainer
arcmira 0.6.3
YouTube transcript search and monitoring for your AI: exact quotes, full transcripts and speakers.13 versions - Latest release: about 23 hours ago - 670 downloads last month - 1 stars on GitHub - 1 maintainer
maivi 0.4.0 💰
Maivi - My AI Voice Input: Real-time voice-to-text with hotkey support4 versions - Latest release: about 1 year ago - 12 downloads last month - 296 stars on GitHub - 1 maintainer
content-cli 0.8.5 💰
Command-line client for the Content engine (talks to /api/v1).18 versions - Latest release: about 2 months ago - 401 downloads last month - 18 stars on GitHub - 1 maintainer
content-sdk 0.8.5 💰
Official Python SDK for the Content engine (the one API client: sync + async).18 versions - Latest release: about 2 months ago - 670 downloads last month - 18 stars on GitHub - 1 maintainer
content-mcp 0.8.5 💰
Official MCP server for the Content engine (agentic facade over the SDK).18 versions - Latest release: about 2 months ago - 702 downloads last month - 18 stars on GitHub - 1 maintainer
whisper-haystack 2.0.0
Haystack integration for whisper3 versions - Latest release: 23 days ago - 5.44 thousand downloads last month - 212 stars on GitHub - 1 maintainer
funasr-haystack 1.0.0
FunASR speech-to-text transcriber for Haystack3 versions - Latest release: 23 days ago - 137 downloads last month - 212 stars on GitHub - 1 maintainer
voice-transcriber-mcp 2.1.0
MCP server for transcribing Google Chat voice messages using Groq Whisper API3 versions - Latest release: 8 months ago - 358 downloads last month - 0 stars on GitHub - 1 maintainer
batchalign 0.10.10
TalkBank CHAT processing pipeline319 versions - Latest release: 1 day ago - 2.85 thousand downloads last month - 2 stars on GitHub - 1 maintainer
whosaid 1.36.2
Local, speaker-attributed transcription for Apple Silicon — who said what, on your Mac, nothing l...46 versions - Latest release: 1 day ago - 152 downloads last month - 6 stars on GitHub - 1 maintainer
paraspeakrs 0.12.0
Speaker-aware meeting transcription: Parakeet INT8 ASR with speakrs diarization11 versions - Latest release: 1 day ago - 894 downloads last month - 1 maintainer
criticus 2.0.2
A suite of tools for transcribing, collating and creating an apparatus criticus. See also www.apa...41 versions - Latest release: over 1 year ago - 1 dependent repositories - 203 downloads last month - 27 stars on GitHub - 1 maintainer
fitini 0.2.1
Fitini — Les murs ont des oreilles4 versions - Latest release: 1 day ago - 0 downloads last month - 1 maintainer
linkdigest-mcp 0.2.5
抖音、小红书、TikTok、YouTube、X 链接转 AI 可读文本 — Python SDK, CLI and stdio MCP server for the hosted LinkDig...6 versions - Latest release: 1 day ago - 0 downloads last month - 2 stars on GitHub - 1 maintainer
disfluency-restoration 0.1.1
Word-level forced alignment for RSML transcripts using wav2vec2 / MMS CTC models.1 version - Latest release: 1 day ago - 1 maintainer
hushscript 1.1.2
The official Python SDK for the Hushscript transcription API.4 versions - Latest release: 1 day ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
transcribe-cpp 0.4.1
Python bindings for transcribe.cpp23 versions - Latest release: 19 days ago - 2.01 thousand downloads last month - 2,150 stars on GitHub - 1 maintainer
transcribe-cpp-native 0.4.1
Prebuilt native library for transcribe-cpp (speech-to-text, ggml)23 versions - Latest release: 19 days ago - 2.95 thousand downloads last month - 2,150 stars on GitHub - 1 maintainer
omi-sdk 0.2.1 💰
Python SDK for Omi wearable device7 versions - Latest release: about 1 year ago - 1.18 thousand downloads last month - 13,934 stars on GitHub - 1 maintainer
omi-cli 0.2.3 💰
Command-line interface for Omi — talk to memories, conversations, action items, and goals from yo...5 versions - Latest release: 6 months ago - 72 downloads last month - 13,934 stars on GitHub - 1 maintainer
jinfer 0.4.0a1
Local AI inference: chat, vision, audio, embeddings, reranking, speech, transcription. One shared...1 version - Latest release: 1 day ago - 146 stars on GitHub - 1 maintainer
coro-asr 1.7.2
Coro: OpenAI-compatible ASR + speaker-diarization server with pluggable backends.19 versions - Latest release: 1 day ago - 381 downloads last month - 8 stars on GitHub - 1 maintainer
amanuensis 0.2.0b2
Turn photographs and scans of historical documents into data with Gemini2 versions - Latest release: 1 day ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
crispasr 0.8.53
Lightweight on-device speech recognition via ggml — Python bindings for CrispASR (Whisper, Qwen3-...31 versions - Latest release: 1 day ago - 2.81 thousand downloads last month - 793 stars on GitHub - 1 maintainer
distillo 0.2.0 💰
Distill lectures, courses and podcasts into the few key points worth learning, each linked to the...1 version - Latest release: 1 day ago - 1 maintainer
anyscribe 0.18.2
CLI tool to download, transcribe, and convert video/audio to structured markdown11 versions - Latest release: 1 day ago - 189 downloads last month - 2 stars on GitHub - 1 maintainer
panoscribe 0.10.1
Extract complete video transcripts — speech AND on-screen text — from TikTok, YouTube, Instagram ...9 versions - Latest release: 1 day ago - 101 downloads last month - 8 stars on GitHub - 1 maintainer
vidyom 0.0.1
Open-source AI-powered video workflow engine. Name reserved for the Vidyom Python AI worker; no f...1 version - Latest release: 1 day ago - 1 maintainer
earshot-cli 0.5.0
旁听剪藏:跨平台桌面端系统声录制 → 本地转写 → 投递知识库(默认 ExoMind,可插拔)7 versions - Latest release: 1 day ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
shadow-clerk 0.8.0
Real-time audio recording and transcription tool for web meetings9 versions - Latest release: 2 days ago - 132 downloads last month - 4 stars on GitHub - 1 maintainer
subtitlemaker 0.2.0
Generate subtitles from audio and video files using faster-whisper.4 versions - Latest release: 2 days ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
funasr-torch 0.1.6
FunASR: A Fundamental End-to-End Speech Recognition Toolkit9 versions - Latest release: 5 days ago - 37 downloads last month - 20,925 stars on GitHub - 1 maintainer
Top 9.1% on pypi.org
30 versions - Latest release: 4 days ago - 1 dependent repositories - 4.74 thousand downloads last month - 20,925 stars on GitHub - 1 maintainer
funasr-onnx 0.4.9
FunASR: A Fundamental End-to-End Speech Recognition Toolkit30 versions - Latest release: 4 days ago - 1 dependent repositories - 4.74 thousand downloads last month - 20,925 stars on GitHub - 1 maintainer
loqalkit 1.13.0
Unified language SDK — detection, transcription, romanization, translation, TTS routing17 versions - Latest release: 2 days ago - 47 downloads last month - 1 maintainer
tts-mcp-server 0.1.1
TTS MCP server: text-to-speech, AI voiceover, voice cloning and SRT/VTT subtitles for Claude, Cur...1 version - Latest release: 2 days ago - 1 maintainer
holdspeak 0.4.0
Voice typing for macOS and Linux - hold a hotkey, speak, release. Local & private.5 versions - Latest release: 4 months ago - 27 downloads last month - 249 stars on GitHub - 1 maintainer
miragea-voice-mcp 0.1.0
MCP server that gives Claude, Cursor and other AI agents a voice: generate voiceovers, multi-spea...1 version - Latest release: 2 days ago - 1 maintainer
myvoicemaker 0.1.1
Official Python SDK for the VoiceMaker API2 versions - Latest release: 5 months ago - 85 downloads last month - 1 maintainer
mlx-qwen3-asr 0.4.4 💰
Qwen3-ASR speech recognition on Apple Silicon via MLX17 versions - Latest release: about 2 months ago - 4.6 thousand downloads last month - 242 stars on GitHub - 1 maintainer
muscriptor 0.4.0
Music transcription to MIDI and sheet music using a transformer language model6 versions - Latest release: 21 days ago - 4.52 thousand downloads last month - 1,916 stars on GitHub - 1 maintainer
subaligner 0.3.15
Automatically synchronize and translate subtitles, or create new ones by transcribing, using pre-...38 versions - Latest release: 5 months ago - 1 dependent repositories - 233 downloads last month - 509 stars on GitHub - 1 maintainer
watch-skill 1.4.3 💰
Give any agent a video input: watch, index, ask, and iterate on video via MCP, CLI, REST, and Pyt...6 versions - Latest release: 2 months ago - 2.1 thousand downloads last month - 561 stars on GitHub - 1 maintainer
Top 7.4% on pypi.org
156 versions - Latest release: 3 days ago - 5 dependent packages - 1 dependent repositories - 273 thousand downloads last month - 20,925 stars on GitHub - 1 maintainer
funasr 1.4.24
OpenAI-compatible speech recognition toolkit with WebSocket streaming, vLLM acceleration, and lla...156 versions - Latest release: 3 days ago - 5 dependent packages - 1 dependent repositories - 273 thousand downloads last month - 20,925 stars on GitHub - 1 maintainer
video-edit-cli 0.1.2
Headless, project-agnostic video-editing CLI with atomic subcommands for AI agents.3 versions - Latest release: 4 months ago - 81 downloads last month - 3 stars on GitHub - 1 maintainer
forgefile 0.2.0
Python client for the ForgeFile REST API — translate, transcribe, convert, OCR, summarize and rew...2 versions - Latest release: 2 months ago - 80 downloads last month - 0 stars on GitHub - 1 maintainer
tldw-server 0.1.46
A comprehensive research assistant and media analysis platform - Too Long; Didn't Watch Server6 versions - Latest release: about 1 month ago - 588 downloads last month - 1,468 stars on GitHub - 1 maintainer
gigastt 2.22.0
On-device Russian speech-to-text (GigaAM v3) — Python bindings (no cloud, no API keys)7 versions - Latest release: about 1 month ago - 189 downloads last month - 80 stars on GitHub - 1 maintainer
hidock-python 0.1.0
Python library and CLI for HiDock P1 recordings and device management1 version - Latest release: 3 days ago - 1 maintainer
llm-real-video 0.4.0
Alias for claude-real-video — let any LLM actually watch a video (scene-aware frames + transcript).1 version - Latest release: 4 months ago - 30 downloads last month - 2,295 stars on GitHub - 1 maintainer
claude-real-video 0.10.7
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, f...45 versions - Latest release: about 2 months ago - 3.39 thousand downloads last month - 2,295 stars on GitHub - 1 maintainer
oatschema-adapters 0.2.0
Export OATS (Open Annotation Task Schemas) records to standard formats, and parse them back.2 versions - Latest release: 3 days ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
yapsnap 0.2.0
Snap any video URL or local audio/video into a plaintext transcript. Auto-detects the spoken lang...8 versions - Latest release: about 2 months ago - 192 downloads last month - 363 stars on GitHub - 1 maintainer
lma-sdk
Reserved placeholder package for AWS Live Meeting Assistant internal SDK1 version - Latest release: 5 months ago - 7 downloads last month - 168 stars on GitHub - 1 maintainer
lma-load-simulator
Reserved placeholder package for AWS Live Meeting Assistant internal load simulator1 version - Latest release: 5 months ago - 11 downloads last month - 168 stars on GitHub - 2 maintainers
lma-cli
Reserved placeholder package for AWS Live Meeting Assistant internal CLI1 version - Latest release: 5 months ago - 9 downloads last month - 168 stars on GitHub - 1 maintainer
wave-av-sdk
Official WAVE SDK for Python - 33 API modules for streaming, production, analytics, and more2 versions - Latest release: 2 months ago - 75 downloads last month - 0 stars on GitHub - 1 maintainer
speechmatics-sdk
Speechmatics Python SDK - Complete package for all Speechmatics APIs2 versions - Latest release: 12 months ago - 13 downloads last month - 20 stars on GitHub - 1 maintainer
deepctl 0.4.0
Official Deepgram CLI for speech recognition and audio intelligence35 versions - Latest release: 21 days ago - 864 downloads last month - 13 stars on GitHub - 1 maintainer
realtimestt 1.1.2 💰
A fast Voice Activity Detection and Transcription System55 versions - Latest release: 2 months ago - 1 dependent repositories - 19.5 thousand downloads last month - 10,234 stars on GitHub - 1 maintainer
whisper-local 0.24.0
Free, open-source, fully offline AI dictation for Windows and macOS. Hold a hotkey, speak, get te...19 versions - Latest release: 4 days ago - 997 downloads last month - 119 stars on GitHub - 1 maintainer
cactus-compute-test 2.5.0
On-device AI inference — LLM, vision, speech, embeddings, and RAG6 versions - Latest release: 6 months ago - 33 downloads last month - 14,518 stars on GitHub - 1 maintainer
syncalong 2.0.1
Forced-alignment library and CLI that timestamps lyrics against an audio file, exporting LRC4 versions - Latest release: 4 months ago - 480 downloads last month - 5 stars on GitHub - 1 maintainer
alldayrec 0.4.0
AllDayRec: an open-source Plaud for your whole day, so your agent knows you. Record with your own...3 versions - Latest release: 14 days ago - 0 downloads last month - 11 stars on GitHub - 1 maintainer
yazses 2.51.0
Local, offline-by-default voice dictation for Linux, macOS, and Windows — hold a key, speak, release66 versions - Latest release: 4 days ago - 1.56 thousand downloads last month - 30 stars on GitHub - 1 maintainer
mindquest 0.4.0
mindquest: An AI-powered platform that creates fun, educational podcasts for children aged 6–12 b...4 versions - Latest release: 9 months ago - 11 downloads last month - 1,006 stars on GitHub - 1 maintainer
whisperflow 1.4.0
WhisperFlow: Real-Time Transcription Powered by OpenAI Whisper15 versions - Latest release: 10 days ago - 165 downloads last month - 1,006 stars on GitHub - 1 maintainer
notewise 1.8.1
A terminal-native CLI that turns YouTube videos and playlists into hierarchical Markdown study no...18 versions - Latest release: 4 days ago - 639 downloads last month - 10 stars on GitHub - 1 maintainer
leduftw-subtitler 1.1.0
Subtitles for any video, in any language.4 versions - Latest release: 4 days ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
stt-ru 0.4.0
Russian speech recognition: Python library, CLI, web service and Docker image2 versions - Latest release: 5 days ago - 0 downloads last month - 352 stars on GitHub - 1 maintainer
machinera 0.2.4
Python client for the Machinera API4 versions - Latest release: 5 days ago - 389 downloads last month - 0 stars on GitHub - 1 maintainer
cactus-engine 2.2.2
On-device AI inference — LLM, vision, speech, embeddings, and RAG1 version - Latest release: 5 days ago - 0 downloads last month - 6,182 stars on GitHub - 1 maintainer
audio-transcriber 2.3.12
Transcribe your .wav .mp4 .mp3 .flac files to text or record your own audio!147 versions - Latest release: 4 days ago - 1 dependent package - 622 downloads last month - 3 stars on GitHub - 1 maintainer
apple-llm 0.3.0
Free local LLM on your Mac: Apple Intelligence's on-device Foundation Models and Private Cloud Co...2 versions - Latest release: 5 days ago - 171 downloads last month - 30 stars on GitHub - 1 maintainer
speechmatics-tts 0.2.0
Speechmatics TTS API Client2 versions - Latest release: 4 days ago - 1.15 thousand downloads last month - 20 stars on GitHub - 1 maintainer
swan-vis 3.2
swan is a tool for visualizing and analyzing transcript isoforms14 versions - Latest release: over 3 years ago - 1 dependent repositories - 39 downloads last month - 69 stars on GitHub - 1 maintainer
speechmatics-batch 1.2.0
Speechmatics Batch API Client15 versions - Latest release: 4 days ago - 62 thousand downloads last month - 20 stars on GitHub - 1 maintainer
speechmatics-rt 1.3.0
Speechmatics Real-Time API Client22 versions - Latest release: 4 days ago - 238 thousand downloads last month - 20 stars on GitHub - 1 maintainer
entune 0.5.1
Dictation with your choice of speech model and a personal dictionary that selects corrections in ...11 versions - Latest release: about 1 month ago - 418 downloads last month - 9 stars on GitHub - 1 maintainer
Related Keywords
whisper
300
speech-to-text
287
audio
183
ai
130
python
117
cli
109
asr
109
video
104
subtitles
85
stt
83
speech-recognition
71
mcp
64
voice
58
youtube
56
llm
55
speech
55
diarization
54
openai
54
srt
53
tts
52
faster-whisper
44
translation
43
api
40
ffmpeg
39
claude
35
dictation
33
speaker-diarization
30
ocr
29
macos
29
summarization
29
text-to-speech
29
model-context-protocol
27
sdk
27
real-time
27
mlx
26
meeting
25
claude-code
24
yt-dlp
24
nlp
24
subtitle
22
offline
22
mcp-server
21
streaming
20
parakeet
20
apple-silicon
18
markdown
17
gemini
17
ai-agents
17
audio-processing
16
whisperx
16
realtime
16
music
16
agents
16
fastapi
16
vtt
16
podcast
16
captions
16
automation
15
voice-recognition
15
video-processing
15
deepgram
15
local-first
15
linguistics
15
rag
14
pyannote
14
transcript
14
ASR
14
multimodal
13
accessibility
13
multilingual
13
automatic-speech-recognition
13
privacy
12
obsidian
12
pdf
12
websocket
12
on-device
12
chinese
12
meeting-notes
12
self-hosted
12
ollama
12
tui
12
text
11
tiktok
11
voice-ai
11
STT
11
machine-learning
11
linux
11
groq
11
voice-activity-detection
10
ai-agent
10
codex
10
notes
10
instagram
10
AI
10
whisper-ai
10
video-analysis
10
speech recognition
10
pytorch
10
vad
10
anthropic
10