# Speech & Transcription

[← Back to main list](../README.md#table-of-contents)

**45 skills**

- [addis-assistant-stt](https://clawskills.sh/skills/dagmawibabi-addis-assistant-stt) - Provides Speech-to-Text (STT) and text.
- [agent-voice](https://clawskills.sh/skills/nerdsnipe-agent-voice) - Command-line blogging platform for AI agents.
- [akaunting](https://clawskills.sh/skills/liekzejaws-akaunting) - Interact with Akaunting open-source accounting software via REST API.
- [alexa-cli](https://clawskills.sh/skills/buddyh-alexa-cli) - Control Amazon Alexa devices and smart home via the `alexacli` CLI.
- [announcer](https://clawskills.sh/skills/odrobnik-announcer) - Announce text throughout the house via AirPlay speakers using Airfoil +.
- [assemblyai-transcribe](https://clawskills.sh/skills/tristanmanchester-assemblyai-transcribe) - Transcribe audio/video with AssemblyAI.
- [audio-gen](https://clawskills.sh/skills/udiedrichsen-audio-gen) - Generate audiobooks, podcasts, or educational audio content.
- [audio-reply](https://clawskills.sh/skills/matrixy-audio-reply-skill) - Generate audio replies using TTS.
- [auto-whisper-safe](https://clawskills.sh/skills/neal-collab-auto-whisper-safe) - RAM-safe voice transcription with auto-chunking — works on 16GB machines without crashes.
- [brw-de-ai-ify](https://clawskills.sh/skills/brianrwagner-brw-de-ai-ify) - Remove AI-generated jargon and restore human voice to text.
- [chichi-speech](https://clawskills.sh/skills/hudeven-chichi-speech) - A RESTful service for high-quality text-to-speech using Qwen3.
- [clonev](https://clawskills.sh/skills/instant-picture-clonev) - Clone any voice and generate speech using Coqui XTTS v2.
- [critical-article-writer](https://clawskills.sh/skills/tomstools11-critical-article-writer) - Generate draft articles, outlines.
- [cult-of-carcinization](https://clawskills.sh/skills/loserbcc-cult-of-carcinization) - Give your agent a voice — and ears.
- [deepdub-tts](https://clawskills.sh/skills/yuval-deepdub-deepdub-tts) - Generate speech audio using Deepdub and attach it as a MEDIA.
- [deepgram](https://clawskills.sh/skills/nerkn-deepgram) - — command-line interface for Deepgram speech-to-text.
- [dellight-cro-revenue-ops](https://clawskills.sh/skills/arthurelgindell-dellight-cro-revenue-ops) - DELLIGHT.AI is an AI startup in DIFC, Dubai.
- [documents-ai](https://clawskills.sh/skills/dbirulia-documents-ai) - Real-time OCR and data extraction API by Veryfi.
- [doubao-api-open-tts](https://clawskills.sh/skills/xdrshjr-doubao-api-open-tts) - Text-to-Speech service using Doubao (Volcano Engine)
- [eachlabs-voice-audio](https://clawskills.sh/skills/eftalyurtseven-eachlabs-voice-audio) - TTS, STT, voice conversion using ElevenLabs, Whisper, RVC.
- [easyverein-api](https://clawskills.sh/skills/truefoobar-easyverein-api) - Work with the easyVerein v2.0 REST API.
- [elevenlabs-agents](https://clawskills.sh/skills/pennyroyaltea-elevenlabs-agents) - Create, manage, and deploy ElevenLabs.
- [elevenlabs-transcribe](https://clawskills.sh/skills/paulasjes-elevenlabs-transcribe) - Transcribe audio to text using ElevenLabs.
- [elevenlabs-tts](https://clawskills.sh/skills/shaharsha-elevenlabs-tts) - ElevenLabs TTS - the best ElevenLabs integration for OpenClaw.
- [elevenlabs-voices](https://clawskills.sh/skills/robbyczgw-cla-elevenlabs-voices) - High-quality voice synthesis with 18 personas, 32.
- [eternal-haven-lore-pack](https://clawskills.sh/skills/deepseekoracle-eternal-haven-lore-pack) - Eternal Haven Chronicles lore + mythic persona pack.
- [faster-whisper](https://clawskills.sh/skills/theplasmak-faster-whisper) - Local speech-to-text using faster-whisper.
- [feishu-minutes](https://clawskills.sh/skills/autogame-17-feishu-minutes) - Fetch info, stats, transcript, and media from Feishu.
- [freshbooks-cli](https://clawskills.sh/skills/haseebuchiha-freshbooks-cli) - FreshBooks CLI for managing invoices, clients, and billing.
- [gettr-transcribe-summarize](https://clawskills.sh/skills/kevin37li-gettr-transcribe-summarize) - Download audio from a GETTR post.
- [hebrew-nikud](https://clawskills.sh/skills/shaharsha-hebrew-nikud) - Hebrew nikud (vowel points) reference for AI agents.
- [her-voice](https://clawskills.sh/skills/matusvojtek-her-voice) - Give your agent a voice.
- [inworld-tts](https://clawskills.sh/skills/gugic-inworld-tts) - Text-to-speech via Inworld.ai API.
- [jarvis-voice](https://clawskills.sh/skills/globalcaos-jarvis-voice) - Metallic AI voice persona with TTS and visual transcript styling.
- [kokoro-tts](https://clawskills.sh/skills/edkief-kokoro-tts) - Generate spoken audio from text using the local Kokoro TTS engine.
- [lnbits](https://clawskills.sh/skills/talvasconcelos-lnbits) - Manage LNbits Lightning Wallet (Balance, Pay, Invoice)
- [lnbits-with-qrcode](https://clawskills.sh/skills/jamestsetsekas-lnbits-with-qrcode) - Manage LNbits Lightning Wallet (Balance, Pay, Invoice)
- [miranda-sag](https://clawskills.sh/skills/jeffpignataro-miranda-sag) - ElevenLabs text-to-speech with mac-style say UX.
- [norman-categorize-transactions](https://clawskills.sh/skills/stanlee000-norman-categorize-transactions) - Review and categorize uncategorized bank transactions, match them with invoices, and verify bookkeeping entries.
- [norman-monthly-reconciliation](https://clawskills.sh/skills/stanlee000-norman-monthly-reconciliation) - Perform a complete monthly financial reconciliation - review all transactions, match invoices, check outstanding.
- [ressemble](https://clawskills.sh/skills/adriano-vr-ressemble) - Text-to-Speech and Speech-to-Text integration using Resemble AI HTTP API.
- [siliconflow-tts-gen](https://clawskills.sh/skills/lilei0311-siliconflow-tts-gen) - Text-to-Speech using SiliconFlow API (CosyVoice2)