'voice' 검색 결과

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn text into standalone speech audio with HeyGen's Starfish model for narration, voiceovers, or podcasts. Choose voices by language or gender, adjust speed and pitch, and add pauses when the selected voice supports them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate narration from a script
• Create speech audio for podcasts
• Find voices by language or gender

Build real-time voice assistants in .NET with Azure AI. Covers two-way audio communication, text and audio responses, detecting when a speaker finishes, and calling functions to connect conversations with external services.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a real-time voice assistant in .NET
• Configure voices and detect when speakers finish
• Connect voice conversations to external services

Build real-time voice applications in Python with Azure AI Voice Live. Covers two-way audio streaming, transcripts, conversation history, and handling interruptions, with examples for authentication and configuring when the assistant responds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a voice assistant in Python
• Display transcripts during voice conversations
• Stop an audio response when the user interrupts

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Examine recorded calls and voicemails for signs of AI-generated speech. Extract acoustic features, classify samples with machine learning, and prepare reports with confidence scores and sound visualizations to support voice impersonation investigations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating calls impersonating executives
• Checking suspicious voicemails
• Comparing suspect recordings with genuine voice samples

Apply existing brand guidelines to emails, proposals, presentations, and social posts. The skill keeps terminology and brand personality consistent, adjusts tone for the audience and context, and explains the choices behind the resulting content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting sales emails in the brand's voice
• Aligning proposal and presentation wording
• Rewriting LinkedIn posts to match brand guidelines

Choose payment reminders based on days relative to an invoice’s due date, with clear escalation stages and contact limits. Identify invoices that need human review and stop reminders once payment is recorded.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a reminder based on days past due
• Check contact intervals before sending reminders
• Identify overdue invoices needing human review

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

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

Write Gmail messages and replies using a saved profile of the user's email style. Read the full conversation, check wording against the profile, and save a draft after approval for the user to review and send.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a reply in your usual email style
• Write a new email from a saved voice profile
• Save an approved reply as a Gmail draft

Generate narration with ElevenLabs from a script file or typed text. Select locally stored voice profiles, adjust voice settings for each request, and save the resulting audio to a chosen file.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating narration from a script file
• Switching between saved voice profiles
• Adjusting speech speed for a single recording

Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when user asks to clone a voice, train a custom voice model, or synthesize speech with a cloned voice. iFlytek Voice Clone tts(声音复刻) — train a custom voice model from audio samples and synthesize speech with the cloned voice. Supports the full workflow: get training text → create task → upload audio → submit training → poll results → synthesize with cloned voice. Pure Python stdlib, no pip dependencies.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Extract invoices, receipts, credit notes, statements, PDFs, images, docs, and spreadsheet-like invoice exports into a reviewable table with field confidence, line items, approval decisions, and CSV/JSON export. Use when the user invokes /kelly-invoice-sheet or $kelly-invoice-sheet, asks for "Invoice转表格", invoice OCR, receipt-to-spreadsheet, invoice data extraction, bookkeeping import prep, or a Lido-style Extract Data workflow with a Busabase-backed App-in-Skill UI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create a single-page, printable HTML invoice with sender and recipient details, itemized charges, tax, totals, and payment instructions. Follow the supplied design settings to arrange branding, dates, payment terms, and a signature line.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an invoice for freelance design work
• Showing line items, a retainer, and tax together
• Preparing a printable invoice with payment instructions

Turn text into speech with Venice.ai for narration, voiceovers, and conversational agents. The skill covers speech models, voices, output formats, and streaming, which delivers audio progressively as it is produced.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating narration from written text
• Preparing voiceovers
• Giving conversational agents a voice

Generate multilingual narration with fish.audio, reuse a previously created voice model, and adjust emotion, pace, and volume. Start with a short voice sample before producing the full audio file.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create multilingual video narration
• Reuse a voice created in the playground
• Add laughter or whispers to narration

Generate narration, dialogue, sound effects, and music with ElevenLabs APIs for videos, podcasts, and games. The skill covers voice settings, pronunciation, pauses, voice cloning, and using measured audio lengths to synchronize scenes in Remotion, a video creation framework.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating narration for videos or podcasts
• Generating sound effects from written descriptions
• Composing instrumental background music

Guide web app testing with screen readers such as VoiceOver, NVDA, and JAWS. Check forms, dialogs, keyboard navigation, and spoken update notifications to identify accessibility problems across desktop and mobile browser combinations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking form labels and error announcements
• Testing dialog focus behavior
• Verifying announcements for changing content

Prepare overdue invoice reminders using accounting records and recent payment data. Adjust each message to the customer's payment history, flag possible payments for checking, and send through PayPal or queue email drafts after approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking which customers have overdue invoices
• Adjusting reminders to each customer's payment history
• Checking for recent payments before sending reminders

Analyze sent Gmail messages to document writing habits, including greetings, phrasing, formatting, and changes in tone by audience. Build or refresh a profile for email-draft-in-voice, then check it against actual replies from separate threads.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a writing profile from sent Gmail messages
• Document tone differences by recipient
• Prepare a profile for email-draft-in-voice

Create a printable, single-page A4 invoice with sender and billing details, itemized charges, tax breakdowns, totals, and payment instructions. The layout includes invoice dates and deadlines, with print styling that preserves color contrast.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing an A4 invoice for printing
• Listing quantities, unit prices, and amounts
• Presenting tax breakdowns and totals

Turn rambling dictation or transcribed voice memos into concise prompts for Claude Code. Remove filler and repetition, then organize the project context, goal, constraints, and expected deliverables while preserving the original requirements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning transcribed voice memos into prompts
• Organizing requirements from long dictation
• Removing repeated phrases and filler words

Match TRES ledger transactions to ERP invoices/bills (AP/AR) and optionally sync them to the connected ERP (Xero, QuickBooks Online, NetSuite). Trigger this skill whenever the user wants to match, link, close, reconcile, or sync an invoice or bill against a blockchain transaction — even if they don't say "skill" or use those exact words. Trigger phrases include: "match this invoice to a transaction", "match a bill to tx", "close invoice INV-123", "close bill 9988", "link this tx to a bill", "pay this invoice from this transaction", "set up this tx as AP", "set up this tx as AR", "sync this transaction as AP/AR", "match AP/AR", "find the invoice/bill for this hash", "what bill does this tx pay". Trigger ONLY for explicit AP/AR matching/closing intent — do NOT trigger for general transaction explanations (use tres-tx-story), for ingesting an explorer link into the ledger (use tres-explorer-tx-to-ledger), or for ERP connection setup itself (use tres-settings-management).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.