MCP.Market

azure-speech-to-text skill

by calesthio·calesthio/OpenMontage·78k stars·AGPL-3.0

Transcribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio/video to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.

A100/100content scan

Is the azure-speech-to-text skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-10-25.

No findings.

Install the azure-speech-to-text skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/calesthio/OpenMontage.git /tmp/OpenMontage
mkdir -p ~/.claude/skills
cp -r /tmp/OpenMontage/.claude/skills/azure-speech-to-text ~/.claude/skills/azure-speech-to-text
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Azure AI Speech — Speech-to-Text

Transcribe audio to text with Azure Fast Transcription — synchronous, word-level timestamps, speaker diarization, and multi-language identification. In OpenMontage this is exposed through the azurestt tool (capability=analysis, provider=azure). It is an optional cloud STT provider — when AZURESPEECHKEY is configured, prefer it for cloud transcription. The local transcriber tool (faster-whisper) remains the default offline path** and the fallback when Azure is unavailable.

Docs: Fast Transcription · Speech service overview

Why Fast Transcription (not Batch)

Azure exposes three STT surfaces. OpenMontage uses Fast Transcription because the pipeline transcribes local audio files:

Fast Transcription needs no Blob storage, no SAS URLs, and no native SDK — just requests and the two env vars.

Setup

Create a Speech resource in the Azure portal; copy the key and region from its Keys and Endpoint page.

export AZURE_SPEECH_KEY=your_speech_resource_key
export AZURE_SPEECH_REGION=eastus          # your resource's region
# export AZURE_SPEECH_ENDPOINT=https://...  # optional: overrides region

azurestt reports AVAILABLE once AZURESPEECHKEY plus either AZURESPEECHREGION or AZURESPEECH_ENDPOINT are set.

Using it in a pipeline

Prefer azurestt over transcriber unless the run must be offline. Its output matches the transcriber schema exactly, so it is a drop-in for subtitlegen and any stage that consumes a transcript.

from tools.tool_registry import registry
registry.discover()
stt = registry._tools["azure_stt"]

result = stt.execute({
    "input_path": "projects/my-video/assets/audio/narration.mp3",
    # "language": "en",          # ISO 639-1 or BCP-47 ("en-US"); omit for auto-ID
    # "diarize": True,           # speaker labels, no HuggingFace token needed
    # "max_speakers": 4,
    "output_dir": "projects/my-video/artifacts",
})
if result.success:
    segs = result.data["segments"]          # [{id,start,end,text,words:[...]}]
    words = result.data["word_timestamps"]  # flat [{word,start,end,probability}]

If azure_stt is unavailable (no key) or errors, fall back to transcriber (local whisper) — its execute signature and output are identical.

Parameters that matter

when you know the language; it is faster and more accurate than auto-ID.

  • language — pass an ISO code ("en") or a full locale ("en-US"). Pin it

identification across this shortlist. Narrow it to the languages you actually expect; a huge list slows detection and invites misclassification.

  • candidatelocales** — when language is omitted, Azure runs language

podcasts). Set max_speakers to the real upper bound.

  • diarize / maxspeakers** — enable for multi-speaker audio (interviews,
  • profanityfilter** — None | Masked (default) | Removed | Tags.

Response shape (mapped to the transcriber schema)

The raw Azure response (phrases[] with offsetMilliseconds / words[]) is converted to seconds and the OpenMontage transcript schema:

{
  "segments": [
    {"id": 0, "start": 0.0, "end": 2.4, "text": "Hello world",
     "speaker": 1,
     "words": [{"word": "Hello", "start": 0.0, "end": 0.5, "probability": 0.98}]}
  ],
  "word_timestamps": [{"word": "Hello", "start": 0.0, "end": 0.5, "probability": 0.98}],
  "language": "en-US",
  "duration_seconds": 2.4,
  "provider": "azure"
}

Note: Fast Transcription has no per-word confidence, so each word carries the phrase confidence in probability.

Limits & tips

jobs, use Azure Batch Transcription instead.

  • Single file up to ~2 hours / a few hundred MB per request. For longer or bulk

you only need speech — smaller upload, same result.

  • Send clean audio (16 kHz+ mono is plenty). Transcode video to audio first if

the first and last cues against the source audio.

  • Verify timing: word timestamps drive subtitle cues in subtitle_gen. Spot-check

More skills from calesthio/OpenMontage

  • A3d-asset-generationGenerate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.
  • AacestepAI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, or musical composition tasks.
  • AacestepAI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, or musical composition tasks.
  • AagentsBuild voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.
  • AagentsBuild voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.
  • Aai-video-genGenerate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, Kling official direct API, and the Gemini API (Gemini Omni Flash).
  • Aai-video-genGenerate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax, Gemini Omni). Supports gateways: HeyGen API, fal.ai API, and the Gemini API (Gemini Omni Flash).
  • Aatlas-cloudGenerate or edit images and videos through the Atlas Cloud gateway. Use for Atlas-hosted Seedance 2.5/2.0, Gemini Omni Flash, MiniMax H3, Seedream 5.0, GPT Image 2, Nano Banana 2, or when one ATLASCLOUD_API_KEY should access multiple media model families.
  • Cavatar-videoCreate AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.
  • Cavatar-videoCreate AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API. Use when: (1) Choosing a specific avatar and voice for a video, (2) Writing exact scripts for an avatar to speak, (3) Building multi-scene videos with different backgrounds per scene, (4) Creating transparent WebM videos for compositing, (5) Using talking photos as video presenters, (6) Integrating HeyGen avatars with Remotion, (7) Batch video generation with exact specs, (8) Brand-consistent production videos with precise control.
  • Aazure-speech-to-textTranscribe audio to text using Azure AI Speech (Fast Transcription REST API). Use when converting audio/video to text, generating subtitles, or processing spoken content in OpenMontage. Optional cloud STT provider — preferred when AZURE_SPEECH_KEY is configured; the local faster-whisper `transcriber` is the default offline path.
  • Aazure-text-to-speechGenerate neural narration audio using Azure AI Speech (REST text-to-speech). Use when synthesizing voiceovers or narration in OpenMontage. Optional cloud TTS provider — preferred when AZURE_SPEECH_KEY is configured; the local piper_tts remains the default offline path. Shares one Speech resource with azure_stt.

All agent skills → · MCP servers