“whisper”的搜索结果

语音转文字 (ASR) (语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。) Master OS — automated mastery of 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on 语音转文字 (ASR / 语音识别 / Speech-to-Text) 应用工程 (从业者视角) — 选型、集成、优化语音转文字能力，尤其面向移动端、低成本、快速识别的场景。覆盖: (a) 引擎/API 地图 — 云端 API(OpenAI gpt-4o-transcribe / Whisper API、Deepgram、AssemblyAI、Google / Azure / AWS Transcribe、讯飞、字节火山、阿里、腾讯、百度) vs 开源模型(Whisper / faster-whisper / whisper.cpp / distil-whisper、NVIDIA NeMo Parakeet / Canary、阿里 FunASR / Paraformer / SenseVoice、Moonshine、Vosk、Kaldi / k2 / icefall) vs 端侧·移动 SDK(whisper.cpp + CoreML / Metal、iOS Speech framework、Android SpeechRecognizer、Picovoice、SenseVoice 端侧); (b) 准确率(WER / CER) × 延迟(RTF / 流式) × 成本 三角权衡与选型决策树; (c) 成本优化 playbook — 端侧免费 / 批量折扣 / VAD 裁静音 / 量化(int8 / ggml) / 蒸馏 / 自托管 break-even; (d) 移动端集成 — 端侧 vs 云、流式 vs 批量、断点检测(endpointing)、隐私 / 离线; (e) 后处理 — 标点 / 数字规整(ITN) / 说话人分离(diarization) / 时间戳。学派分歧: 云 API vs 端侧自托管、通用大模型(Whisper) vs 专用流式(RNN-T / Conformer)、闭源 API vs 开源、准确率派 vs 成本派、英文优先 vs 中文 ASR(FunASR / SenseVoice / 讯飞)。不含: 文字转语音(TTS / 语音合成，方向相反)、声纹识别 / 说话人验证为主业、语音 agent / 对话式 AI、ASR 模型训练科研深水区。 problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「语音转文字」「语音识别」「asr」「speech to text」「stt」

中文简介正在准备中。当前显示原文说明。

Transcribe audio files locally with the Whisper command-line tool, without an API key. Export text or translated subtitles, and choose smaller or larger models to balance processing speed and transcription accuracy.

中文简介正在准备中。当前显示英语简介。

• Transcribing an MP3 recording into a text file
• Creating translated subtitles from an M4A file
• Choosing a model for speed or accuracy

使用whisper在本地转录音频文件，保存为文本或生成翻译字幕，无需API密钥。可选择不同大小的模型，根据任务需求平衡处理速度与准确度。

• 将录音转录为可阅读的文本
• 根据音频制作翻译字幕
• 按速度或准确度需求选择模型

Add burned-in captions to a finished video using Whisper timings from its own audio. Choose paper, bold, or clean styling, and optionally use narration text to preserve intended spelling. Outputs include the captioned video and an SRT file.

中文简介正在准备中。当前显示英语简介。

• Adding captions to a finished video
• Restyling captions for social media shorts
• Preserving brand names and numbers from a narration script

Prepare video clips with yt-dlp, whisper, and ffmpeg, covering downloads, speech transcription, subtitle files, trimming, and vertical formatting. Also includes methods for adding generated speech and sending finished videos through messaging APIs.

中文简介正在准备中。当前显示英语简介。

• Turning longer videos into vertical clips
• Creating and embedding subtitles from speech
• Adding narration made with text-to-speech

Inspect video content locally by extracting frames with ffmpeg and transcribing speech with Whisper. The skill produces timestamped image paths, transcript segments, and video details in JSON, giving an agent material for visual review without requiring API keys.

中文简介正在准备中。当前显示英语简介。

• Reviewing scenes and speech in a local video
• Transcribing video audio without API keys
• Extracting frames at scene changes or regular intervals

Turn audio and video into text with Whisper, including Japanese and other supported languages. This skill covers transcription, English translation, timestamped subtitles, model selection, and batch processing, with guidance on hardware needs and recognition limitations.

中文简介正在准备中。当前显示英语简介。

• Transcribing recorded meetings
• Creating subtitles for videos
• Translating multilingual recordings into English text

Answer questions about videos from URLs or local files using timestamped visual and spoken evidence. Choose extracted frames and transcripts, or let Gemini view the full video with a configured API key.

中文简介正在准备中。当前显示英语简介。

• Summarizing a video's visuals and speech
• Finding timestamps relevant to a question
• Checking a specific section of a long video

Transcribes local audio and video to txt, srt, vtt and json with timestamps using whisper.cpp, and proves which backend ran. Trigger to transcribe, caption or subtitle a recording, meeting, podcast or video locally; to pick a Whisper model for this GPU or estimate a batch; when a transcript is empty, cut short or repeating; when Whisper ran on the CPU or a pasted log must prove the GPU ran; when it shares the GPU with LM Studio or ComfyUI; or say whisperrunner (audit, check, plan, run, status, refresh). Never a cloud API or a download. Voice-overs are comfyrunner's; clips and burned-in captions obsrunner's; game audio soundsmith's; summarising transcripts lmstudiorunner's.

中文简介正在准备中。当前显示原文说明。

Clean spoken recordings by transcribing words, identifying filler and false starts, and joining cuts with short audio fades. Preview proposed edits, reduce breaths, repair noise-gate clicks, and optionally use Cleanvoice for additional cloud processing.

中文简介正在准备中。当前显示英语简介。

• Removing filler words and long silences from a podcast
• Reviewing proposed edits before applying them
• Repairing clicks caused by a noise gate

Creates original-language, translated, and bilingual SRT subtitle files from YouTube links, local videos, or other supported media. Uses platform captions when available, falls back to Whisper transcription, and provides subtitle output for short vertical videos.

中文简介正在准备中。当前显示英语简介。

• Creating translated subtitles from a YouTube video
• Transcribing a local video into subtitles
• Producing bilingual SRT files

Turn recorded audio and video into text or timestamped subtitles with Whisper. This skill covers transcription across 99 languages, language detection, translation into English, batch processing, and model selection for available computing resources.

中文简介正在准备中。当前显示英语简介。

• Transcribe recorded meetings
• Turn podcasts into text
• Generate SRT or VTT subtitles for videos

Premiere Pro 動画編集ワークフローを Claude Code で自動化するスキル集。/cut は Premiere Pro XML の無音・雑音区間をジェットカット、/srt は WAV+Premiere XML から日本語テロップ用 SRT を並列Whisper→LLM意味区切り→全体アライメントSRT の3ステップ(v6)で生成、/srt-fast は改行工程まで3チャンク並列化した高速版、/telop-check は書き出し済みMP4を全編スキャンしてテロップの数字表記・誤字脱字・い抜き・ら抜き・固有名詞ミスを検出する。faster-whisper / ffmpeg / Premiere Pro を要するローカル実行型。日本語トーク動画のショート / ロング編集向け。

中文简介正在准备中。当前显示原文说明。

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models with word-level timestamps.

中文简介正在准备中。当前显示原文说明。

将音频文件发送到OpenAI语音转写API，并将结果保存为文本或JSON。可指定模型和语言，也可为发言添加说话人标签，便于区分录音中的不同说话人。

• 将会议录音转为文字
• 区分访谈中的说话人
• 将转写结果保存为JSON

Turn audio or video recordings into Markdown documents with transcripts and summaries. Use it for meeting notes, speaker identification, subtitle files, or batch transcription when several recordings need to become readable documentation.

中文简介正在准备中。当前显示英语简介。

• Create meeting notes from recordings
• Summarize long lectures or talks
• Identify speakers in recorded conversations

Transcribe audio files through 9Router using models from providers such as OpenAI, Groq, and Deepgram. Receive plain text, structured results with timestamps, or SRT and VTT subtitles, depending on the selected model’s support.

中文简介正在准备中。当前显示英语简介。

• Transcribing recorded meetings or interviews
• Creating SRT or VTT subtitles from audio
• Getting transcriptions with timestamps

Transcribe speech from audio or video into SRT, ASS, TXT, or JSON files. Adjust Chinese line breaks, create styled subtitles sized for the video, and optionally burn subtitles into a new video file.

中文简介正在准备中。当前显示英语简介。

• Generate subtitle files from recorded video
• Transcribe speech from audio recordings
• Burn subtitles into a video

When you want to extract content from a video — YouTube, Loom, Vimeo, Riverside, Zoom recording, local MP4, X/IG video, anything yt-dlp supports. Three depth modes user picks per invocation — transcript (just words, fast/free), visual (transcript + ffmpeg frame extraction + Claude vision pass on key moments), multimodal (Gemini native video ingestion if $GEMINI_API_KEY set, else dense Claude vision). Uses local Whisper for transcription (MLX-Whisper on Apple Silicon, faster-whisper elsewhere), falls back to platform-provided transcripts when available (Loom, Riverside, YouTube auto-subs). Saves to ~/Documents/videos/<source>-<slug>-<date>/ and optionally captures summary to second-brain raw/ as call-/meeting-/note-. Triggers on "/watch-video <url>," "watch this video," "transcribe this loom," "analyze this video," "summarize this recording," "key moments from this," "what happened in this video." This skill replaces and broadens the prior youtube-transcript skill.

中文简介正在准备中。当前显示原文说明。

Use the faster-whisper package for CTranslate2-backed Whisper transcription, model selection, CPU/CUDA setup, audio utilities, VAD, timestamps, and conversion guidance.

中文简介正在准备中。当前显示原文说明。

Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.

中文简介正在准备中。当前显示原文说明。

Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.

中文简介正在准备中。当前显示原文说明。

Use when the user wants local voice transcription instead of OpenAI Whisper API. Switches to whisper.cpp running on Apple Silicon. WhatsApp only for now. Requires voice-transcription skill to be applied first.

中文简介正在准备中。当前显示原文说明。

Transcribes audio/video files to text. Uses Whisper (openai-whisper) or Vosk (offline) as optional backend — both are detected via presence check. Without backend: placeholder mode with dummy output (dry-run).

中文简介正在准备中。当前显示原文说明。