Capabilities
Explore what MAI-Transcribe 1 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Microsoft Azure
- Product
- Speech-to-Text
- Release Date
- Apr 2, 2026
- Data Policy
- Configurable
- Region
- Unknown
- Input
- Audio
- Output
- Text
Playground
Try MAI-Transcribe 1 by Microsoft Azure. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for MAI-Transcribe 1.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Microsoft Azure | Not specified | Text | $0.0142 / minute | — | azure/mai-transcribe-1:azure |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 300000000 |
| Max seconds | Not specified |
| Formats | wav, mp3, mpeg, mpga, flac |
Provider Notes
azure/speech-realtime bridges the official Speech SDK continuous recognizer behind AudioLab's WebSocket route and switches to ConversationTranscriber for live speaker diarization. It accepts mono PCM16 at the session sample rate, supports up to four candidate locales for at-start language identification or ten for continuous identification, and limits phrase lists to Microsoft's documented 500 phrases. Time segmentation requires a 20–70 second maximum; semantic segmentation has no silence control. The file-only speech-fast API supports translation, prompt arrays, channels, diarization, and phrase lists. MAI Transcribe 1 and 1.5 remain file-only and do not support diarization, translation, or prompt tuning; 1.5 adds phrase lists and readable/verbatim style. Availability varies by Azure region.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=azure/mai-transcribe-1' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | azure/mai-transcribe-1 — Required model identifier. |
locales / channels | View Accepted Values |
diarization.enabled / diarization.max_speakers (speech-fast) | View Accepted Values |
phrase_list.phrases / phrase_list.biasing_weight (speech-fast and MAI 1.5) | View Accepted Values |
profanity_filter_mode | View Accepted Values |
enhanced_mode.task / target_language / prompt (speech-fast) | View Accepted Values |
enhanced_mode.transcribe_style (MAI 1.5) | View Accepted Values |
language_id_mode / word_timestamps / endpoint_id / dictation (realtime) | View Accepted Values |
diarization.diarize_interim_results (realtime) | View Accepted Values |
segmentation_strategy / segmentation silence and maximum time (realtime) | View Accepted Values |
initial_silence_timeout_ms / start_event_sensitivity / stable_partial_result_threshold (realtime) | View Accepted Values |
post_processing=true_text (realtime) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 300000000 |
| Max seconds | Not specified |
| Formats | wav, mp3, mpeg, mpga, flac |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
| MAI-Transcribe 1.5Microsoft Azure | Not specified | $0.0051 / minute | — |
| Speech Fast TranscriptionMicrosoft Azure | Not specified | $0.0051 / minute | — |
| Speech RealtimeMicrosoft Azure | Not specified | $0.0142 / minute | — |
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
| Saaras v4Sarvam AI | Not specified | ₹0.425 / minute | — |
