Edge Tts

by aahl47edd621dff4No license162 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 weeks ago

Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.

Instructions onlyDesign & Creative
AI-generated overview

Generates text-to-speech audio files from text using the uvx edge-tts command, with voice, rate, pitch and subtitle options.

What it does
This skill instructs an agent to run the uvx edge-tts command to convert supplied text into spoken audio, writing an mp3 media file to a temporary directory. It documents options for adjusting rate, volume and pitch, selecting a specific neural voice, and writing subtitles alongside the audio. It also lists available voices across several languages and shows how to retrieve the full voice list.
When to use it
Use it when a user asks for audio or voice output, when content should be listened to rather than read, or when a specific voice, speed, pitch or output format is requested for speech.
Requirements
Requires the uvx tool with the edge-tts package available, plus network access to Microsoft Edge's neural TTS service. It ships no scripts; it is instructions only.

Edge-TTS

Generate high-quality text-to-speech audio using Microsoft Edge's neural TTS service via the uvx edge-tts command. Supports multiple languages, voices, adjustable speed/pitch, and subtitle generation.

Usage

shell
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3
# With subtitlesuvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --write-subtitles -

Changing rate(speed), volume and pitch

shell
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --rate=+50%uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --volume=+50% --pitch=-50Hz

Changing the voice

shell
uvx edge-tts --text "{msg}" --write-media {tempdir}/{filename}.mp3 --voice zh-CN-XiaoxiaoNeural

Available voices

Name                               Gender    ContentCategories      VoicePersonalitiesen-GB-LibbyNeural                  Female    General                Friendly, Positiveen-GB-RyanNeural                   Male      General                Friendly, Positiveen-GB-SoniaNeural                  Female    General                Friendly, Positiveen-GB-ThomasNeural                 Male      General                Friendly, Positiveen-HK-SamNeural                    Male      General                Friendly, Positiveen-HK-YanNeural                    Female    General                Friendly, Positiveen-US-AnaNeural                    Female    Cartoon, Conversation  Cuteen-US-AndrewMultilingualNeural     Male      Conversation, Copilot  Warm, Confident, Authentic, Honesten-US-AndrewNeural                 Male      Conversation, Copilot  Warm, Confident, Authentic, Honesten-US-AriaNeural                   Female    News, Novel            Positive, Confidenten-US-AvaMultilingualNeural        Female    Conversation, Copilot  Expressive, Caring, Pleasant, Friendlyen-US-AvaNeural                    Female    Conversation, Copilot  Expressive, Caring, Pleasant, Friendlyen-US-BrianMultilingualNeural      Male      Conversation, Copilot  Approachable, Casual, Sincereen-US-BrianNeural                  Male      Conversation, Copilot  Approachable, Casual, Sincereen-US-ChristopherNeural            Male      News, Novel            Reliable, Authorityen-US-EmmaMultilingualNeural       Female    Conversation, Copilot  Cheerful, Clear, Conversationalen-US-EmmaNeural                   Female    Conversation, Copilot  Cheerful, Clear, Conversationalen-US-EricNeural                   Male      News, Novel            Rationalen-US-GuyNeural                    Male      News, Novel            Passionen-US-JennyNeural                  Female    General                Friendly, Considerate, Comforten-US-MichelleNeural               Female    News, Novel            Friendly, Pleasanten-US-RogerNeural                  Male      News, Novel            Livelyen-US-SteffanNeural                Male      News, Novel            Rationalfr-FR-DeniseNeural                 Female    General                Friendly, Positivefr-FR-HenriNeural                  Male      General                Friendly, Positivezh-CN-XiaoxiaoNeural               Female    News, Novel            Warmzh-CN-YunjianNeural                Male      Sports,  Novel         Passionzh-CN-liaoning-XiaobeiNeural       Female    Dialect                Humorouszh-CN-shaanxi-XiaoniNeural         Female    Dialect                Brightzh-HK-HiuGaaiNeural                Female    General                Friendly, Positivezh-HK-WanLungNeural                Male      General                Friendly, Positivezh-TW-HsiaoChenNeural              Female    General                Friendly, Positivezh-TW-YunJheNeural                 Male      General                Friendly, Positive

Retrieve all available voices using shell commands:

shell
uvx edge-tts --list-voices

Source and attribution

Source:aahl/skillsinskills/edge-ttsat commit47edd62

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal