Audio and Voice Skills for Transcription
Audio and voice skills cover work that runs in both directions: speech to text and text to speech. On the input side, that means transcription, summarization of recorded conversations, and audio processing such as cleanup or format handling. On the output side, it means generating speech for voiceovers, plus dubbing and translation where a track is re-voiced into another language. The ranked list below is ordered by observed search demand, with skills that match this topic directly placed first and a cap on how many entries any single publisher can hold. Use it by scanning for the sub-topic that matches your task, then reading each skill's own documentation to confirm it handles your audio format, language, and workflow before you load it into an agent.
8 to start with39 top options
Start with these.
Audio work runs both directions: speech to text (transcribe, summarize) and text to speech (voiceover, dubbing).
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect
transcribe
OfficialTranscribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
- Rank 02View Agent SkillDirect
speech-to-text
Transcribes audio to text using ElevenLabs Scribe v2 with 90+ languages, speaker diarization, and word-level timestamps.
Needs (stated): API key · Network access
9,737 · popularity - Rank 03View Agent SkillDirect
speech
OfficialUse when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
- Rank 04View Agent SkillDirect
text-to-speech
Converts text to speech using ElevenLabs voice AI, supporting 70+ languages, multiple models, voice settings, and voiceovers.
Needs (stated): API key · Network access
13,871 · popularity - Rank 05View Agent SkillDirect
azure-ai-transcription-py
Official| Azure AI Transcription SDK for Python. Use for real-time and batch speech-to-text transcription with timestamps and diarization. Triggers: "transcription", "speech to text", "Azure AI Transcription", "TranscriptionClient".
- Rank 06View Agent SkillDirect
azure-speech-to-text-rest-py
Official|- Azure Speech to Text REST API for short audio (Python). Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK. Triggers: "speech to text REST", "short audio transcription", "speech recognition REST API", "STT REST", "recognize speech REST". DO NOT USE FOR: Long audio (>60 seconds), real-time streaming, batch transcription, custom speech models, speech translation. Use Speech SDK or Batch Transcription API instead.
- Rank 07View Agent SkillDirect
openai-whisper-api
Transcribes audio via the OpenAI Audio Transcriptions API using curl, supporting gpt-4o-transcribe, mini, diarize, and whisper-1 models.
Needs (stated): Node.js
3,262 · popularity - Rank 08View Agent SkillDirect
openai-whisper
Local speech-to-text with the Whisper CLI, transcribing audio without an API key.
4,700 · popularity
Explore 31 more Agent Skills
- Rank 09View Agent SkillDirect
whisper
OpenAI's Whisper speech recognition model for transcription, translation to English, and language identification across 99 languages.
Needs (stated): Python
1,467 · popularity - Rank 10View Agent SkillDirect
tts
Converts text into speech audio with Kokoro local and Noiz cloud backends, supporting voice cloning, timeline-accurate dubbing, and per-segment voice control.
4,224 · popularity - Rank 11View Agent SkillDirect
edge-tts
Text-to-speech conversion using uvx edge-tts to generate audio from text, with multiple languages, voices, and adjustable speed/pitch.
7,847 · popularity - Rank 12View Agent SkillDirect
qianwen-audio-tts
Synthesizes speech from text with Qwen TTS models, supporting voiceovers, narration, and multiple TTS backends.
Needs (stated): Python
5,056 · popularity - Rank 13View Agent SkillDirect
qwencloud-audio-tts
Synthesizes speech from text with Qwen TTS models, supporting voiceovers, narration, and multiple TTS backends.
Needs (stated): Python
1,539 · popularity - Rank 14View Agent SkillDirect
Transcription Automation
Automates audio/video transcription, meeting notes, subtitle generation, and content processing with diarization and multiple output formats.
4,365 · popularity - Rank 15View Agent SkillDirect
audio-transcription
Transcribes local or remote audio into durable text and timestamp artifacts through PostPlus, with subtitle-ready outputs.
1,297 · popularity - Rank 16View Agent SkillDirect
speech-recognition
Transcribes speech to text using Apple's Speech framework, covering live microphone and recorded audio recognition on iOS/macOS.
3,477 · popularity - Rank 17View Agent SkillDirect
fish-audio
Generates AI text-to-speech audio, uses saved voices, or creates one-shot voice clones via the AceDataCloud Fish Audio API.
4,116 · popularity - Rank 18View Agent SkillDirect
sherpa-onnx-tts
Local text-to-speech via sherpa-onnx, running offline with no cloud dependency.
3,201 · popularity - Rank 19View Agent SkillDirect
sag
ElevenLabs text-to-speech with a mac-style say UX, supporting voices, models, and expressive audio tags.
Needs (stated): API key
3,142 · popularity - Rank 20View Agent SkillDirect
dubbing
Dubs audio and video into other languages using the ElevenLabs Dubbing API, preserving original speakers' voices with editable transcripts.
Needs (stated): API key · Network access
2,538 · popularity - Rank 21View Agent SkillDirect
layer-audio
Generates audio with Layer: sound effects, music, and text-to-speech voiceover, with guidance on prompts and delivery.
1,968 · popularity - Rank 22View Agent SkillPossible
voice-isolator
Removes background noise and isolates vocals/speech from audio using the ElevenLabs Voice Isolator API, useful for cleaning recordings before transcription.
Needs (stated): API key · Network access
5,127 · popularity - Rank 23View Agent SkillPossible
characteristic-voice
Makes generated speech sound more human and emotionally expressive with fillers, emotion tuning, and speaking-style presets.
Needs (stated): Python
2,754 · popularity - Rank 24View Agent SkillPossible
voice-changer
Transforms the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery via ElevenLabs speech-to-speech.
Needs (stated): API key · Network access
4,924 · popularity - Rank 25View Agent SkillPossible
speech-engine
Adds real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine, handling STT, turn-taking, and TTS.
Needs (stated): API key · Network access
4,901 · popularity - Rank 26View Agent SkillPossible
mmx-cli
MiniMax CLI to generate text, images, video, and speech, and to transcribe audio via the MiniMax AI platform.
31,010 · popularity - Rank 27View Agent SkillPossible
gemini-live-api-dev
Builds real-time bidirectional streaming applications with the Gemini Live API, covering audio/video/text streaming, VAD, live transcription, and translation.
9,577 · popularity - Rank 28View Agent SkillPossible
azure-ai
OfficialUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
- Rank 29View Agent SkillPossible
media-use
NotableAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs p
447,090 · popularity - Rank 30View Agent SkillPossible
ai-avatar-video
NotableCreate AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson
142,016 · popularity - Rank 31View Agent SkillPossible
p-video-avatar
Generates talking-head avatar videos from a portrait image with built-in TTS via Pruna P-Video-Avatar and inference.sh CLI.
10,145 · popularity - Rank 32View Agent SkillPossible
videodb
Ingests, indexes, searches, edits, and monitors video and audio with the VideoDB Python SDK, including transcription, subtitles, and dubbing.
8,704 · popularity - Rank 33View Agent SkillPossible
fal-ai-media
Unified media generation via fal.ai MCP covering text-to-image, video, text-to-speech, and video-to-audio.
8,815 · popularity - Rank 34View Agent SkillPossible
transformers-js
Runs ML models in JavaScript/TypeScript including speech recognition and audio classification via Transformers.js pipelines.
Needs (stated): Python · Node.js
1,922 · popularity - Rank 35View Agent SkillPossible
anything2explainer
Notable给一个主题，产出一条黑底 MG 风格（幕底可选星点或点阵波）、有配音字幕章节进度条的科普讲解视频（中文或英文；Remotion 代码动画；时长由用户定，常用 3–5 分钟）。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据，以及一条完整样片（《RAG 与知识库》）作为质量标尺。Turn any topic into a narrated motion-graphics explainer video in Chinese or English, on a black canvas with a star-field or dot-field backdrop, TTS voiceover, subtitles and a chapter progress bar, every frame drawn in code with Remotion. Use when the user asks for an explainer, educational or science-communication video about a topic, or wants an article or document turned into a video.
- Rank 36View Agent SkillPossible
azure-ai-openai-dotnet
Official| Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: "Azure OpenAI", "AzureOpenAIClient", "ChatClient", "chat completions .NET", "GPT-4", "embeddings", "DALL-E", "Whisper", "OpenAI .NET".
Needs (stated): API key
- Rank 37View Agent SkillPossible173,506 · popularity
hyperframes-audio
Notable - Rank 38View Agent SkillPossible
azure-ai-voicelive-py
OfficialBuild 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.
Needs (stated): API key
- Rank 39View Agent SkillPossible
azure-ai-contentunderstanding-py
Official| Azure AI Content Understanding SDK for Python. Use for multimodal content extraction from documents, images, audio, and video. Triggers: "azure-ai-contentunderstanding", "ContentUnderstandingClient", "multimodal analysis", "document extraction", "video analysis", "audio transcription".
Frequently asked questions
- What is the difference between transcription and summarization skills?
- Transcription skills convert speech to text, while summarization skills take that text or an existing transcript and condense it. They are often used together in a pipeline, but they are separate tasks and may live in separate skills.
- Can one skill handle both speech to text and text to speech?
- Audio work runs in both directions, but a given skill usually focuses on one direction: either turning speech into text or turning text into speech. Check the skill's documentation to see which side it covers.
- How is the ranked list ordered?
- The list is ranked by observed search demand, with direct matches for this topic placed first. A cap limits how many skills from any single publisher appear.
- Where does dubbing and translation fit among these skills?
- Dubbing and translation sit on the text-to-speech side, where a track is re-voiced into another language. They build on transcription and translation steps before speech is generated.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for transcribe into ~/.claude/skills/transcribe/ for yourself, or .claude/skills/transcribe/ to share it with a project.
- From the registry — run npx skills add openai/skills@transcribe.
- Or download transcribe from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.
For agents To find skills for a job, install find-skills-for-the-job. It includes this catalog’s topics. npx skills add geekfoxcharlie/find-skills-for-the-job