Menu
Synthesize text to speech using Microsoft Edge Read Aloud voices (no API key).
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Bounded auto-iteration for a prompt with explicit stop predicates.
Memory hygiene workflow to classify, deduplicate, and promote durable knowledge across local memory layers.
Bounded simplification pass for a file or hunk that preserves behavior while reducing complexity.
Turn a repeatable workflow into a reusable local SKILL.md with explicit steps, criteria, and safe defaults.
Bounded auto-debug loop for failing build/test commands with evidence-first diagnosis.
Safely update Nexo config files with read-before-write merges, schema-aware mapping, and reload/restart awareness.
| name | Microsoft Edge TTS |
| description | Synthesize text to speech using Microsoft Edge Read Aloud voices (no API key). |
| requires | {"bins":[],"env":[]} |
Use this skill to convert text into spoken audio. Backed by the msedge-tts
extension which uses the free Microsoft Edge Read Aloud backend via the
msedge_tts crate — no API key required.
openai-whisperstatus — returns defaults (voice, audio format, output dir)list_voices — list Edge voices; supports query substring filter and limitsynthesize — write an audio file from text; optional voice, audio_format,
rate, pitch, volume, output_pathDefault voice: en-US-EmmaMultilingualNeural.
Default format: audio-24khz-48kbitrate-mono-mp3.
Default output dir: $TMPDIR/agent-msedge-tts/speech-<timestamp>.mp3.
list_voices with a language query (e.g. "es-", "en-US", "multilingual")
to pick a voice.synthesize with text and the chosen voice. Grab output_path from the
response to send or play the audio.rate, pitch, volume are provider-native integer adjustments (0 = neutral).audio_format (mp3 / wav / webm / ogg / opus / amr).text is rejected.