Tasks and inputs
MAI-Transcribe-2-Streaming is listed for Automatic speech recognition. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
MAI-Transcribe-2-Streaming transcribes live audio with intermediate and final segments through Microsoft Foundry’s speech services.
Pricing conditions: The published introductory rate is $0.54 per hour of audio. The streaming promotion runs through the end of 2026 and the Azure feature is in public preview. Audio-duration billing is separate from language-model tokens.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
MAI-Transcribe-2-Streaming is a speech-to-text model for continuous live audio. It returns revisable intermediate text followed by final segments, rather than waiting for a complete recording. It belongs to Microsoft’s MAI audio family, with access through Foundry’s speech services.
The streaming model is in public preview. Integrations can use an OpenAI Realtime-compatible WebSocket interface or the Azure Speech SDK. Verify the account region, deployment identifier and audio format in the selected service before reproducing a result.
The model page lists an introductory $0.54 per hour of audio. The streaming announcement states that its introductory price lasts through the end of 2026. Evaluate transcription independently of any later extraction, translation or summary, which may use another model and billing unit.
Use reviewed audio from the languages, microphones and noise conditions you expect to receive. Check names, numbers, punctuation and omitted phrases. For streaming, verify that partial revisions do not create duplicate actions and that downstream work waits for a stable segment when correctness depends on the complete utterance.
Record the exact model identifier, deployment route and request settings with each result. Count complete runs, including rejected outputs, retries and tool calls. When the workflow creates files or code, open the files or execute the existing checks before accepting the result. A plausible first response can hide an incomplete final deliverable.
The specifications describe supported interfaces and request capacity. They do not establish a measured quality ranking or a latency guarantee for your account. SyncDev has not independently benchmarked this model. Choose a deployment after testing the languages, input formats and operating conditions that matter to your users.
Explore microsoft models, browse model tasks, or compare two models with the same acceptance criteria.
Compare the model on the work you need to complete.
MAI-Transcribe-2-Streaming is listed for Automatic speech recognition. It accepts audio and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
xAI
Grok Voice Transcribe 2.0 transcribes recorded and streaming audio; the retired 1.0 API name now routes to this revision.
Gemini 3.5 Transcribe Live from Google: Speech transcription model for accurate audio-to-text and captioning workflows.
xAI
Grok Voice STT 1.0 from xAI: Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.
OpenAI
GPT Realtime Whisper from OpenAI: Streaming speech-to-text model for low-latency transcript deltas from live audio.
openai
openai/whisper-large-v3-turbo is a source-linked Hugging Face repository assigned to Automatic speech recognition. Its recorded task interface accepts audio and produces text.
OpenAI
Whisper 3 Large from OpenAI: Open Whisper checkpoint for robust multilingual transcription and captioning.