azure-speech
Use Microsoft Azure Speech in Foundry Tools for media-production speech workflows: speech-to-text, fast and batch transcription, diarization, captions/subtitles, real-time transcription, text-to-speech neural and HD voices, SSML, custom/personal voices, text-to-speech avatars, speech/video translation, localization, quotas, regions, privacy, consent, rights, and production QA.
Profile →npx skills add calesthio/generative-media-skills --skill azure-speech --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Use Microsoft Azure Speech in Foundry Tools for media-production speech workflows: speech-to-text, fast and batch transcription, diarization, captions/subtitles, real-time transcription, text-to-speech neural and HD voices, SSML, custom/personal voices, text-to-speech avatars, speech/video translation, localization, quotas, regions, privacy, consent, rights, and production QA.
How it works
Treat Azure Speech as a family of related services, not one model. Select the narrowest official capability that matches the job, then verify region, quota, language, pricing, and access status before committing.
- Identify the user’s job (e.g., real-time captions, fast transcription, batch transcription, TTS with specific voice, or video translation).
- Choose the appropriate Azure Speech capability (speech-to-text, text-to-speech, speech translation, custom speech, custom voice, personal voice, video translation, or avatar outputs).
- For each job, apply the production routing rules: real-time STT through Speech SDK/CLI/REST for live tasks; fast transcription for quick single-file transcripts; batch transcription for many files or long material with diarization; TTS with chosen voice and SSML for narration; batch synthesis for long-form audio; speech translation or LLM Speech for translation needs; video localization if applicable; text-to-speech avatar only when deliverable includes an avatar.
- Use diarization labels (Guest1/Guest2) as output annotations, not as identity recognition, and map labels as needed in editorial workflow.
- For captions/subtitles, generate two passes: transcription/timing, then caption formatting; QA for line length, reading speed, punctuation, and speaker labels.
- For SSML, control prosody with SSML tags, but test locale/region/voice/SSML compatibility; manage pronunciation with lexicons/phonemes; separate voices per turn when multiple voices are used.
When to use it
Use Azure Speech when transcription, captions, narration, avatars, or translation are required in media-workflows and when region, quota, and access specifics must be verified before use. Do not use diarization to identify individuals; use it for draft segmentation only. Use batch transcription or batch synthesis for long-form content or large catalogs, and reserve real-time paths for live scenarios.
What it can touch
- Tools: claude-code, codex, copilot, cursor
- Data touchpoints: transcripts, captions, subtitles, SSML, voice selections, and output audio/files stored in Azure/at specified storage outputs; diarization labels are outputs of transcription processes.
Caveats
- Facts verified against Microsoft Azure documentation as of 2026-07-10; regional availability, quotas, and access can change and must be rechecked before production use.
- Diarization labels are not speaker identity and are not consistent across files; use manual mapping if real identities are required.
- Batch processing may start slowly during peak hours; jobs are best-effort and may take up to 24 hours to complete.
- Some voices and SSML features may have limited support depending on language, region, and endpoint; test exact locale and SSML tags before deployment.
# Azure Speech for media production agents Use this skill when Azure Speech in Foundry Tools is a candidate provider for transcription, captions, subtitles, narration, synthetic voices, avatar speech, speech translation, video localization, or production speech QA. Treat Azure Speech as a family of related services, not one model. Select the narrowest official capability that matches the job, then
What does the azure-speech skill do?
Use Microsoft Azure Speech in Foundry Tools for media-production speech workflows: speech-to-text, fast and batch transcription, diarization, captions/subtitles, real-time transcription, text-to-speech neural and HD voices, SSML, custom/personal voices, text-to-speech avatars, speech/video translation, localization, quotas, regions, privacy, consent, rights, and production QA.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill azure-speech --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.