skills.rest
zamansepeti43
zamansepeti43COMMUNITY
Explore all skills by this author →
GitHub

azure-text-to-speech

Generate neural narration audio from text using Azure AI Speech REST text-to-speech.

Updated Sep 1, 2026
Search Tags:#azure#text-to-speech#audio generation#voiceover#narration#ssml#neural voices
One-click install
npx skills add https://github.com/zamansepeti43/c-rak-agent --skill azure-text-to-speech-zamansepeti43
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-text-to-speech
Source: https://github.com/zamansepeti43/c-rak-agent/tree/main/video-engine/.agents/skills/azure-text-to-speech
Command: npx skills add https://github.com/zamansepeti43/c-rak-agent --skill azure-text-to-speech-zamansepeti43

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Producing high-quality voiceover narration for video projects requires either recording human voice talent or relying on robotic-sounding local synthesis. This Skill converts plain text into natural neural speech audio through the Azure AI Speech REST endpoint, giving OpenMontage pipelines a cloud TTS option with multilingual voices and SSML prosody control. ## Core Features & Use Cases - Neural Voice Synthesis: Generate narration with multilingual Azure neural voices (Andrew, Brandon, Ava, Guy, Jenny) via the synchronous /cognitiveservices/v1 endpoint, with no token exchange or job polling. - SSML Prosody Control: Adjust rate, pitch, and express-as styles (narration-professional, calm, newscast) per segment for consistent voiceover delivery. - Pipeline Integration: Works through the azure_tts tool with automatic fallback to elevenlabs_tts, openai_tts, or the offline piper_tts default when Azure is unavailable. - Use Case: A video editor needs narration for a 10-scene explainer video. They generate one MP3 segment per script section with a slightly slowed rate, then feed the WAV versions into the audio mixer for final assembly. ## Quick Start Set the AZURE_SPEECH_KEY and AZURE_SPEECH_REGION environment variables, then ask the agent to generate narration audio for your script text using the andrew voice saved as an MP3 file.

Frequently Asked Questions about azure-text-to-speech

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate text-to-speech audio with Azure AI Speech?▼

Set AZURE_SPEECH_KEY and AZURE_SPEECH_REGION, then call the azure_tts tool with text, a voice alias like andrew, and an output path. The synchronous REST endpoint returns MP3 or 48kHz WAV audio without token exchange or job polling.

What voices are available in Azure neural text-to-speech?▼

Curated aliases include andrew, brandon, ava, guy, and jenny, mapping to Azure neural voices like en-US-AndrewMultilingualNeural. Any valid Azure voice short name such as de-DE-KatjaNeural can also be passed directly.

Azure TTS vs piper TTS: which should I use for narration?▼

Azure TTS provides higher-quality cloud neural voices and is preferred when AZURE_SPEECH_KEY is configured. Piper TTS remains the default offline path and the fallback when Azure is unavailable or no key is set.

Does Azure text-to-speech support languages other than English?▼

Yes, the Multilingual neural voices handle non-English text well. Set the locale parameter to match the text's language so the generated SSML uses correct pronunciation and prosody.

How much does Azure neural text-to-speech cost?▼

Azure neural TTS Standard tier bills roughly $16 per 1M characters, about $0.015 for a 150-word narration segment. The tool reports per-call cost_usd for the cost tracker.

What are the limits of the Azure TTS synchronous endpoint?▼

The synchronous endpoint caps a single request at 10 minutes of audio. Generate one segment per script section rather than one large paragraph, which keeps segments aligned to scene timings and cheap to regenerate.

Related Skills

Explore More Content & Communication Skills→
calesthiocalesthio
55.1k

azure-text-to-speech

Generate neural narration audio from text using Azure AI Speech REST text-to-speech.

Community
Intermediate
Samuelca6399Samuelca6399

video-audio-design

Add narration, SFX, and music to Remotion videos with frame-accurate mixing.

Community
Advanced
rrbandarrbanda

azure-speech-to-text-rest-py

Transcribe short audio under 60 seconds to text via Azure REST API.

Community
Intermediate
Deskaunedsei1983Deskaunedsei1983

sherpa-onnx-tts

Generate local offline speech from text using sherpa-onnx voice models.

Community
Intermediate