MAI-Transcribe 1.5 is Microsoft's fast transcription model powered by Azure AI Speech. It supports 100+ BCP-47 locales with automatic language detection, automatic punctuation, and duration-based per-second billing. Uses the Azure Speech fast transcription API (v2025-10-15).
Modalities
Price
$0.36/hour
Released
Jun 2, 2026
Create an API key from your OpenRouter dashboard and set it as an environment variable:
Use microsoft/mai-transcribe-1.5 with the OpenRouter API:
OpenRouter provides a speech-to-text API that transcribes audio into text. Send base64-encoded audio with a model, and receive the transcribed text in JSON.
The generation ID is returned in the X-Generation-Id response header for tracking.
For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.
Transcribes audio into text. Accepts base64-encoded audio input and returns the transcribed text.
https://openrouter.ai/api/v1/audio/transcriptionsBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsmicrosoft/mai-transcribe-1.5| Name | Type | Default | Description |
|---|---|---|---|
max_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |
temperature | float | 1 | This setting influences the variety in the model's responses. |
top_p | float | 1 | This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. |
max_completion_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |