浏览技能
找到 5,167 个技能
norman-monthly-reconciliation
由 stanlee000 提供
Perform a complete monthly financial reconciliation - review all transactions, match invoices, check outstanding.
her-voice
由 matusvojtek 提供
Give your agent a voice.
dellight-cro-revenue-ops
由 arthurelgindell 提供
DELLIGHT.AI is an AI startup in DIFC, Dubai.
siliconflow-tts-gen
由 lilei0311 提供
Text-to-Speech using SiliconFlow API (CosyVoice2)
documents-ai
由 dbirulia 提供
Real-time OCR and data extraction API by Veryfi.
feishu-minutes
由 autogame-17 提供
Fetch info, stats, transcript, and media from Feishu.
hebrew-nikud
由 shaharsha 提供
Hebrew nikud (vowel points) reference for AI agents.
akaunting
由 liekzejaws 提供
Interact with Akaunting open-source accounting software via REST API.
eachlabs-voice-audio
由 eftalyurtseven 提供
TTS, STT, voice conversion using ElevenLabs, Whisper, RVC.
eternal-haven-lore-pack
由 deepseekoracle 提供
Eternal Haven Chronicles lore + mythic persona pack.
freshbooks-cli
由 haseebuchiha 提供
FreshBooks CLI for managing invoices, clients, and billing.
lnbits
由 talvasconcelos 提供
Manage LNbits Lightning Wallet (Balance, Pay, Invoice)
chichi-speech
由 hudeven 提供
A RESTful service for high-quality text-to-speech using Qwen3.
deepdub-tts
由 yuval-deepdub 提供
Generate speech audio using Deepdub and attach it as a MEDIA.
clonev
由 instant-picture 提供
Clone any voice and generate speech using Coqui XTTS v2.
cult-of-carcinization
由 loserbcc 提供
Give your agent a voice — and ears.
inworld-tts
由 gugic 提供
Text-to-speech via Inworld.ai API.
addis-assistant-stt
由 dagmawibabi 提供
Provides Speech-to-Text (STT) and text.
deepgram
由 nerkn 提供
— command-line interface for Deepgram speech-to-text.
announcer
由 odrobnik 提供
Announce text throughout the house via AirPlay speakers using Airfoil +.
elevenlabs-transcribe
由 paulasjes 提供
Transcribe audio to text using ElevenLabs.
audio-reply
由 matrixy 提供
Generate audio replies using TTS.
critical-article-writer
由 tomstools11 提供
Generate draft articles, outlines.
audio-gen
由 udiedrichsen 提供
Generate audiobooks, podcasts, or educational audio content.