Tasks and inputs
StepAudio 3 ASR Max 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 8, 2026
StepAudio 3 ASR Max transcribes audio into incremental and final text, with contextual handling of names and specialist vocabulary.
The specification score summarizes recorded features and limits. It is not a benchmark result.
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
StepAudio 3 ASR Max transcribes audio into incremental and final text, with contextual handling of names and specialist vocabulary.
StepAudio 3 ASR Max is a speech-recognition service. The publisher describes support for Chinese, English, dialects, mixed-language speech and specialist vocabulary. Its output is transcription text, making it suitable for subtitles, meeting records and a searchable spoken-content archive.
The documented API accepts audio in an HTTP request and returns recognition events over Server-Sent Events. Incremental text and the final transcript serve different purposes: show provisional text in a live interface, then save the completed result. This output stream should not be confused with a bidirectional realtime voice conversation.
Use recordings from the domain the application serves, including proper names, abbreviations, quiet passages and self-corrections. Compare the transcript with a reference made from the actual audio. Report missed or substituted terms separately from punctuation differences, since a plausible-looking transcription can still change the meaning.
The model guide and central rate card currently show different hourly figures. This listing leaves a single definitive rate unset and links both documents so the account’s billing terms can be confirmed. Audio-duration billing also does not belong in ordinary text-token price columns. Include failed submissions and retranscription in a production cost estimate.
Model documentation · Model documentation · Model documentation
Compare the model on the work you need to complete.
StepAudio 3 ASR Max 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.
Microsoft
MAI-Transcribe-2-Streaming transcribes live audio with intermediate and final segments through Microsoft Foundry’s speech services.
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.