Tasks and inputs
Muse Voice Transcribe 1.0 is listed for Automatic speech recognition, Speaker Diarization. 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
Muse Voice Transcribe turns live audio or recorded files into text, with speaker labels, turn timestamps and support for 25 languages.
Pricing conditions: $0.18 per hour of processed audio, metered in whole seconds. Streaming, file transcription and zero data retention have the same rate. This is audio-duration billing, not token billing.
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
Muse Voice Transcribe produces a text transcript from audio. It supports 25 languages with code-switching, speaker labels and turn-level timestamps. That interface suits dictation, meeting transcripts, captions and voice applications that need text before a separate assistant processes it. It does not generate a spoken reply.
Live audio uses the realtime ASR WebSocket endpoint; an existing recording uses the file transcription endpoint. The integration can provide language and vocabulary hints for names, products and domain terms. Word-level timestamps, sound-event labels and emotion detection are not supplied by this model, so a downstream workflow should not depend on those fields.
The first-party rate is $0.18 per processed audio hour. Streaming and non-streaming requests have the same rate, and zero data retention has price parity with Standard mode. Keep the measured audio duration and the chosen response format alongside the transcript. A text summarization step after transcription is a separate model operation and may have separate costs.
Use recordings from the languages and microphones you expect to support. Check proper names, spoken numbers and speaker changes. For live audio, measure the delay before a stable completed turn and include silence and interruptions. Review transcription quality separately from the quality of any later summary.
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 meta models, browse model tasks, or compare two models with the same acceptance criteria.
Compare the model on the work you need to complete.
Muse Voice Transcribe 1.0 is listed for Automatic speech recognition, Speaker Diarization. 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.