mai-voiceSynthesize speech with Microsoft's MAI-Voice-1 voices via Azure AI Speech REST API.
Install via ClawdBot CLI:
clawdbot install robotsbuildrobots/mai-voiceRequires:
Grade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://{AZURE_SPEECH_REGION}.tts.speech.microsoft.com/cognitiveservices/v1Calls external URL not in known-safe list
https://learn.microsoft.com/en-us/azure/ai-services/speech-service/mai-voicesAI Analysis
The skill's external API call (Azure Speech Service) is explicitly documented and directly serves the stated purpose of speech synthesis. The required credentials are for the legitimate Azure service, and there are no hidden instructions, credential harvesting patterns, or obfuscation of behavior.
Audited Apr 16, 2026 · audit v1.0
Generated Oct 9, 2026
Indie game studios can dynamically generate expressive dialogue lines for non-player characters without hiring voice actors for every iteration. Using MAI-Voice-1 styles like excitement or empathy, developers prototype tavern chatter, quest briefings, or combat taunts directly from script text files.
Online course creators can produce fast, consistent narration for onboarding modules, compliance training, or language lessons by feeding lesson scripts into the script. The Azure region parameter helps teams stay compliant with data residency expectations while previewing natural MAI voices.
Newsletter writers and niche media publishers can convert daily written briefs into short MP3 audio posts for commuters and subscribers. With voice selection and optional emotional styling, a one-person content operation can ship a branded audio feed every morning.
Support teams can generate voice replies to tickets or knowledge-base articles for visually impaired users or customers who prefer audio explanations. A secure backend service calls the Azure Speech REST API only when a user requests an audio summary, avoiding pre-generating thousands of static files.
IoT and hardware teams building smart speakers, kiosks, or in-car assistants can quickly evaluate MAI-Voice-1 voices against their product UX before committing to a full TTS contract. Because access uses the standard Azure Speech endpoint and key, existing Azure infrastructure can be reused for early testing.
A lightweight SaaS platform charges customers per character synthesized while pooling Azure Speech API keys. The wrapper manages key rotation, retries, and output formatting, especially useful for small teams that do not want to configure Azure directly.
A productized service that provides ready-made audio content for a specific niche, such as daily meditations, local news briefs, or language drills. Operations are script-driven and use MAI-Voice-1 with consistent voices and styles to produce a high volume of episodes rapidly.
A consulting or managed-service offering that helps large organizations integrate the Azure Speech REST API behind their own VNet and security controls. It includes key management, region selection, SSML template libraries, and monitoring for preview API changes.
💬 Integration Tip
Set AZURE_SPEECH_KEY and AZURE_SPEECH_REGION as environment variables and verify that your Speech resource is in eastus, since MAI-Voice-1 preview access is currently limited; use the included speak.sh script with --text-file for batch generation to avoid shell escaping issues.
Scored Oct 9, 2026
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.