skills.rest
calesthio
calesthioCOMMUNITY
Explore all skills by this author →
𝕏@calesthioailabsGitHub

azure-text-to-speech

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

55.1k|6.9k|Updated Mar 29, 2026
Search Tags:#text-to-speech#Azure#video production#narration#VoiceOver#ssml#neural voices
One-click install
npx skills add https://github.com/calesthio/OpenMontage --skill azure-text-to-speech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-text-to-speech
Source: https://github.com/calesthio/OpenMontage/tree/main/.agents/skills/azure-text-to-speech
Command: npx skills add https://github.com/calesthio/OpenMontage --skill azure-text-to-speech

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Producing voiceover narration for video projects requires either recording human voice talent or wiring up a speech synthesis service; this Skill turns plain script text into neural narration audio through Azure AI Speech without manual SSML authoring or audio engineering.

Core Features & Use Cases

  • Neural TTS Synthesis: Converts text segments into MP3 or WAV narration using Azure multilingual neural voices with SSML rate, pitch, and style control.
  • Curated Voice Aliases: Accepts short aliases like andrew, ava, or guy mapped to Azure voice short names, plus any valid Azure voice name verbatim.
  • Provider Fallback Chain: Integrates with the OpenMontage tts_selector and falls back to elevenlabs_tts, openai_tts, or the offline piper_tts when Azure is unavailable.
  • Use Case: Given a video script split into sections, generate one narration segment per section at a slightly slowed rate, then feed the WAV output into the audio_mixer stage for final mixing.

Quick Start

Ask the agent to generate narration for your script segment using the azure_tts tool with the andrew voice at rate -4% and save it as an MP3 in your project's audio assets folder.

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 narration audio with Azure text-to-speech?▼

Call the azure_tts tool with text, a voice alias like andrew, an output path, and an output format of mp3 or wav. The tool synthesizes the segment through the Azure REST /cognitiveservices/v1 endpoint and reports per-call cost.

What Azure credentials are needed for text-to-speech?▼

Set AZURE_SPEECH_KEY plus either AZURE_SPEECH_REGION or AZURE_TTS_ENDPOINT from a Speech resource in the Azure portal. The same key and region also unlock Azure speech-to-text, so one resource covers both directions.

Azure TTS vs ElevenLabs vs Piper for video narration?▼

Azure neural TTS is the preferred cloud option for high-quality multilingual narration when AZURE_SPEECH_KEY is configured. ElevenLabs is the choice for voice cloning, while piper_tts remains the default offline path and final fallback.

Does Azure text-to-speech support non-English voices?▼

Yes, any valid Azure voice short name such as de-DE-KatjaNeural can be passed directly. The Multilingual voices handle non-English text well when the locale parameter matches the text's language.

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

The synchronous REST endpoint caps a single request at 10 minutes of audio. The recommended pattern is one call per script section, which keeps segments aligned to scene timings and cheap to regenerate.

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 so the pipeline cost tracker can accumulate spending.

Related Skills

Explore More Content & Communication Skills→
paolomozpaolomoz
3

infographic-video

Convert meeting summaries into narrated videos with AI-generated infographics.

Community
Advanced
RonanCodesRonanCodes

audio-mix

Layer narrator, music, and timed sound effects into MP3 or WAV audio files.

Community
Intermediate
LazyIsEfficientLazyIsEfficient
15

elevenlabs-tts

Convert text to speech and generate MP3 narration files.

Official
Intermediate
guia-matthieuguia-matthieu
145

voice-design

Select and design AI voices for content creation using ElevenLabs and Qwen3-TTS.

Community
Intermediate