Results for “transcript”

Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

The English summary is being prepared. Showing the original description.

Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

The English summary is being prepared. Showing the original description.

Visualises RNA-modification data with transcript-feature metagene plots (Guitar GuitarPlot with 5'UTR / CDS / 3'UTR scaling; MetaPlotR; deepTools `computeMatrix scale-regions`), peak-centred heatmaps (ComplexHeatmap; deepTools plotHeatmap), IP-vs-input paired browser tracks (bigWig of log2 IP/input via deepTools `bamCompare`; ggcoverage; pyGenomeTracks; Gviz; IGV / UCSC track hubs), DRACH sequence-logo plots (ggseqlogo; MEME), 5'UTR / CDS / 3'UTR stacked-bar feature-distribution summaries, and volcano / MA plots for differential modification. Establishes stop-codon enrichment in the metagene plot as the biological QC anchor for any MeRIP dataset (Dominissini 2012 *Nature* 485:201; Meyer 2012 *Cell* 149:1635 — concurrent founding papers from different labs both showed this independently). Use when producing the canonical metagene plot with stop-codon enrichment as a QC anchor, building paired IP/input genome-browser tracks at single-locus resolution, plotting peak-centred heatmaps clustered by condition, summarising peak distribution across transcript features for figure 1, generating DRACH motif logos as sanity checks on the peak set, rendering volcano plots of differential m6A, or reproducing the Dominissini 2012 / Meyer 2012 stop-codon enrichment plot.

The English summary is being prepared. Showing the original description.

Aligns and QCs methylated-RNA-immunoprecipitation (MeRIP / m6A-seq) IP and input libraries using STAR or HISAT2 splice-aware mapping, samtools sort/index, IP/input matched-pair tracking, antibody-lot metadata recording, replicate concordance via deepTools multiBamSummary + plotCorrelation, IP enrichment QC via plotFingerprint and per-transcript IP/input ratio distributions, library-complexity saturation curves via PreSeq c_curve / lc_extrap, and the explicit do-NOT-deduplicate convention for standard non-UMI MeRIP. Use when preparing paired IP and input BAM files for exomePeak2 / MeTPeak / MACS3 peak calling, evaluating MeRIP replicate concordance and IP enrichment, deciding whether to deduplicate (standard MeRIP typically NOT — see Tips), choosing genome-vs-transcriptome alignment for downstream peak vs m6Anet workflows, recording antibody clone and lot metadata for downstream cross-batch reconciliation, detecting failed IPs via saturation curves and IP/input distribution shape, or generating IP-over-Input bigWig tracks for downstream visualisation.

The English summary is being prepared. Showing the original description.

Detects m6A modifications from Oxford Nanopore direct-RNA-sequencing (ONT DRS) signal data using m6Anet (Hendra 2022 *Nat Methods* 19:1590; multiple-instance-learning neural network over DRACH 5-mer signal). Covers the required upstream pipeline (Dorado / Guppy basecalling -> minimap2 transcriptome alignment with `-ax map-ont -uf -k14 --secondary=no` -> nanopolish eventalign with `--scale-events --signal-index` (m6Anet-required) plus `--summary` / `--threads` housekeeping -> m6anet dataprep -> m6anet inference), per-site vs per-read probability interpretation including the `mod_ratio` per-site stoichiometry column, the DRACH-only modeling constraint, minimum-coverage thresholds (20-50 reads per site for stable probability estimates), multi-condition comparison via xPore (Pratanwanich 2021 *Nat Biotechnol* 39:1394), Nanocompore (Leger 2021 *Nat Commun* 12:7198), ELIGOS (Jenjaroenpun 2021 *NAR* 49:e7), and Dorado native modification calling (RNA004 chemistry, 2024+), reference-transcriptome version pinning, the cDNA-vs-DRS chemistry distinction (cDNA-Nanopore CANNOT be used for modification detection), and orthogonal validation against MeRIP / GLORI. Use when calling m6A from ONT DRS without immunoprecipitation, choosing m6Anet vs xPore vs Nanocompore vs ELIGOS vs Dorado native, interpreting per-site `probability_modified` vs `mod_ratio` vs per-read modification probabilities, comparing methylation between conditions from ONT data, deciding between m6Anet for known DRACH sites and Dorado/Remora for genome-wide screening, pinning RNA002 vs RNA004 chemistry and basecaller model versions, or troubleshooting eventalign / dataprep failures.

The English summary is being prepared. Showing the original description.

Calls m6A peaks from MeRIP-seq / m6A-seq paired IP-vs-input data using exomePeak2 (transcript-aware, GC-bias-corrected Poisson GLM; Liu 2022 *NAR Genom Bioinform* 4:lqac046), MeTPeak (HMM over sliding windows; Cui 2016 *Bioinformatics* 32:i378), MACS3 / MACS2 with --nomodel --broad --keep-dup all (genome-wide broad alternative), and DRACH motif enrichment confirmation via HOMER or ggseqlogo as a sanity check (NOT a filter). Covers BED12 vs narrowPeak output formats, exonic vs intronic peak handling, multi-tool reconciliation (intersection vs union; cross-caller IDR-equivalent), the m6A-vs-m6Am ambiguity at 5'UTR peaks that antibody-based methods cannot resolve, and orthogonal-validation routes (miCLIP / GLORI / m6A-SAC-seq / m6Anet). Use when calling peaks from paired IP/input genome BAMs, choosing exomePeak2 (transcript-aware default) vs MACS3 (broad genomic) vs MeTPeak (HMM-smoothed low-coverage), confirming DRACH enrichment as a sanity check on the peak set as a whole, reconciling differing peak sets across tools, validating MeRIP peaks against orthogonal single-base methods, interpreting peaks at the 5' end where m6Am contamination is possible, or recommending a multi-tool consensus strategy.

The English summary is being prepared. Showing the original description.

Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization.

The English summary is being prepared. Showing the original description.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

The English summary is being prepared. Showing the original description.

Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (no timestamps).

The English summary is being prepared. Showing the original description.

Turn notes, fragments, or transcripts into an article through a paragraph-by-paragraph discussion. Compare opening options, establish what readers need to know, and save agreed sections in a separate document while preserving the original material.

• Turning scattered notes into an article
• Building a readable article from a transcript
• Comparing opening angles before drafting

Turn notes, transcripts, or research into polished articles, guides, tutorials, and newsletters. Use supplied writing examples or brand guidance to maintain a consistent voice, organize a clear argument, and support factual claims with provided evidence.

• Turning notes or transcripts into finished articles
• Writing articles in an established brand voice
• Drafting practical guides and tutorials

Turn facts into question-and-answer cards and review them at intervals based on your answers. Create quizzes from YouTube transcripts, organize cards into collections, and import or export CSV files, with card data stored locally.

• Save facts as flashcards
• Review cards when they are due
• Test recall with a YouTube quiz

Turn YouTube transcripts into summaries, timestamped chapters, X threads, blog posts, or selected quotes. Provide a video link or ID, and the skill retrieves available subtitles and organizes their content into the format you request.

• Getting a quick overview of a long video
• Creating timestamped chapters and chapter summaries
• Turning video content into X threads or blog posts

Turn chat transcripts or screenshots into animated message overlays. Configure app-style containers, avatars, nicknames, and device frames, then prepare transparent videos or editable project files for short clips, demonstrations, and story reenactments.

• Animated chat scenes for short videos
• Message overlays for product demonstrations
• Chat-based story reenactments

Turn agent activity and transcript token counts into a cost report organized around completed outcomes. Separate estimates from measured spending, examine waste and rework, and export readable HTML with supporting JSON, CSV, and evidence.

• Reviewing weekly agent spending and completed work
• Comparing costs per completed outcome
• Investigating the cost of loops and rework

Convert articles, reports, or documentation into an English or Chinese podcast with two conversational hosts. Create a dialogue script, generate speech, and combine it into an MP3 with a readable transcript.

• Turning an article into a conversational podcast
• Adapting a report for listening
• Explaining technical documentation through dialogue

Search local session histories across Codex, Claude Code, OpenCode, and other coding agents. Find earlier requests, inspect transcripts and child sessions, and reconstruct past work using recorded evidence, with filters for dates, projects, platforms, and models.

• Finding work done a few days ago
• Checking whether a migration was already completed
• Reviewing tasks delegated to child agents

Recover context from local coding-agent transcripts and produce a checkpoint covering the objective, completed work, blockers, and next step. Explicit import requests support read-only recovery, with continuation governed by the current workspace rules and the user's request.

• Recover context using a session ID
• Summarize unfinished work from local logs
• Review JSONL exports or Markdown handoffs

Add synchronized subtitles and text effects to an existing single-speaker video. Choose from 35 visual styles, including readable lower captions and words placed behind the person, with local transcription, subject cutout, previews, and final video compositing.

• Add readable subtitles to an explainer video
• Place an emphasized word behind the speaker
• Create themed caption effects for social videos

Turn interviews, surveys, support conversations, and public reviews into evidence-based customer insights. Identify recurring problems, buying triggers, and customer language, then build research reports, quote collections, or personas and plan interviews or surveys to fill gaps.

• Analyze customer interview transcripts
• Find recurring themes in reviews and support tickets
• Build customer personas from research evidence

Predict spatial gene expression from H&E-stained tissue images using DeepSpot-M. Query a released panel of about 19,000 genes and combine predictions from small image tiles into slide-wide maps for research analysis.

• Mapping predicted marker-gene expression across a tumor section
• Predicting expression across slides without matching gene-expression assays
• Adding predicted expression to a histology image analysis pipeline

Helps build Python workflows that extract information from documents, images, audio, and video using Azure AI Content Understanding. Covers document text, timed transcripts, video frames, and invoice fields for search and automated processing.

• Preparing document content for AI search
• Transcribing audio with timestamps
• Extracting transcripts and key frames from video

Build real-time voice assistants in JavaScript or TypeScript using Azure AI Voice Live. Covers two-way audio streaming, authentication, speech turn detection, transcription events, and calling application functions during conversations in Node.js or browsers.

• Build a voice assistant in Node.js
• Stream microphone audio from a browser
• Configure speech boundaries and transcription events

Build Java applications that exchange live audio with AI assistants using Azure AI VoiceLive. The skill covers authentication, streaming sessions, speech detection, voice selection, transcription, and handling responses over WebSocket, a persistent two-way connection.

• Implementing a real-time voice assistant in Java
• Configuring speech detection and interruptions
• Adding transcription and noise reduction