Azure Speech to Text

Microsoft Azure

Regional English and Swahili transcription.

Pilot betaInvited workspaces · Azure South Africa North

Clear usage rates.

Audio minute≈ UGX 100per minute

Introductory pilot rates · UGX

$0.024 per audio minute, rounded up to whole seconds at $0.0004 per second. Silence and no-match still process billable audio. Dispatched work may be charged if cancelled or interrupted; check receipts before retrying.

A little head start.

90 days of lower rates.

No platform subscription fee. Pay for your usage, within your approved pilot limits.

How the pilot offer works

Rates apply for 90 days from activation in an approved workspace. Rates and usage limits are confirmed before paid use.

Introductory rates are active for new requests, including existing workspaces. Historical usage keeps its original rates. Billing shows your configured rates; no automatic payments.

We’ll give at least 30 days’ notice of changes after your introductory period. Access is invite-only and subject to scheduled compute capacity. USD is the pricing base; local equivalents are approximate.

Check your workspace’s active rates →

Open in Playground View active workspace rates

Requires an invited account and a key enabled for this model.

What you can build.

Capabilities available in the Embiro pilot.

InputAudio

OutputText

Regional English and Swahili transcription
Six tested language locales
JSON or plain-text output
Durable jobs without GPU warm-up

Know the limits.

Audio: Mono PCM16 WAV at 16 kHz, up to 60 seconds
Language: Choose en or sw; no automatic detection
Clip type: Short utterances; long pauses can end recognition early. Use Whisper, Crane or Sunflower for continuous recordings.
Locales: English: en-KE (default), en-NG, en-ZA, en-GB, en-US; Swahili: sw-KE
Not supported: Luganda, diarisation, translation, streaming or audio URLs

Full pilot service notes

Optional regional managed transcription in South Africa North. English or Swahili language required; six tested locales. Mono PCM16 WAV at 16 kHz, up to 60 seconds; JSON or text. No language detection, diarisation, translation or automatic fallback. Audio rounded up to whole seconds; dispatched work may be charged if cancelled or interrupted.

Requests share your workspace’s allowance, rate limit and concurrency limit. Backend capacity varies; some GPU services warm up on demand. Model access does not guarantee immediate capacity.

Make your first request.

Use a server-side workspace API key from Platform → API keys. Examples use https://api.embiro.ai/v1 and the exact pilot model ID.

API model IDazure-speech-to-text

POST/v1/audio/transcriptions

Prepare clip.wav as mono PCM16 WAV at 16 kHz, up to 60 seconds. Choose language en or sw. English defaults to en-KE; set locale to en-NG, en-ZA, en-GB or en-US if appropriate. Swahili uses sw-KE. No automatic detection or cross-model fallback.

# Set EMBIRO_API_KEY in your shell first.
: "${EMBIRO_API_KEY:?Set your workspace API key first}"
curl --fail-with-body --silent --show-error "https://api.embiro.ai/v1/audio/transcriptions" \
  -H "Authorization: Bearer $EMBIRO_API_KEY" \
  -F "model=azure-speech-to-text" \
  -F "language=en" \
  -F "response_format=json" \
  -F "file=@clip.wav;type=audio/wav"

What comes back

A transcript in text. Silent audio may return an empty transcript.

Cold starts, errors and safe retries

Use the Queued job example when a request can wait for compute. Save its ID and poll that job.
For 401/403, check the key and its model permissions. For 400, check the request and format limits.
Respect Retry-After on 429/503. A timeout after dispatch can be ambiguous; check request logs before submitting again.
These examples do not automatically retry paid work. A job retry must reuse the saved idempotency key and identical payload.

Open API reference

Under the hood.

Publisher specifications. These do not override the Embiro service limits above.

Published context: Not specified
Parameters: Not disclosed
Model size: Managed

Regional managed short-audio recognition in South Africa North. English and Swahili; six tested locales. Mono PCM16 WAV at 16 kHz, up to 60 seconds. Language choice required; no detection, diarisation, translation or automatic fallback. Review transcripts for errors.

Read the publisher’s model card

No verified benchmark scores are listed in this catalogue for this model.