Audience
Developers and product teams building live transcription, voice-agent, virtual-assistant, contact-center, or live-captioning applications.
About Voxtral Mini Transcribe Realtime 3
Voxtral Mini Transcribe Realtime 3 is a speech-to-text model delivered through Mistral’s API for applications that need live transcription. It streams audio over WebSocket and returns transcript events while a person is speaking, with configurable streaming delays. Developers can use it to add real-time captions, voice-assistant input, or transcription to voice-agent workflows. The model provides turn detection, speaker diarization, and context biasing for domain-specific vocabulary, and supports transcription across 45 languages and dialects. Applications can connect to its real-time endpoint and receive transcription events as audio arrives, rather than waiting for an entire recording to finish. Voxtral Mini Transcribe Realtime 3 is part of Mistral’s Voxtral audio model family.
Other Popular Alternatives & Related Software
Chirp 3
Google Cloud's Text-to-Speech API introduces Chirp 3, enabling users to create personalized voice models using their own high-quality audio recordings. This feature facilitates the rapid generation of custom voices, which can be utilized to synthesize audio through the Cloud Text-to-Speech API, supporting both streaming and long-form text. Access to this voice cloning capability is restricted to allow-listed users due to safety considerations; interested parties should contact the sales team to be added to the allowed list. Instant Custom Voice creation and synthesis are supported in various languages, including English (US), Spanish (US), and French (Canada), among others. It is available in multiple Google Cloud regions, and supported output formats include LINEAR16, OGG_OPUS, PCM, ALAW, MULAW, and MP3, depending on the API method used.
Learn more
Scribe
ElevenLabs has introduced Scribe, an advanced Automatic Speech Recognition (ASR) model designed to deliver highly accurate transcriptions across 99 languages. Scribe is engineered to handle diverse real-world audio scenarios, providing features such as word-level timestamps, speaker diarization, and audio-event tagging. Benchmark tests, including FLEURS and Common Voice, demonstrate Scribe's superior performance over leading models like Gemini 2.0 Flash, Whisper Large V3, and Deepgram Nova-3, achieving the lowest word error rates in languages such as Italian (98.7%) and English (96.7%). Notably, Scribe also significantly reduces errors in languages that have been traditionally underserved, including Serbian, Cantonese, and Malayalam, where other models often exhibit error rates exceeding 40%. Developers can integrate Scribe through ElevenLabs' speech-to-text API, receiving structured JSON transcripts that include detailed annotations.
Learn more
Speechmatics
Best-in-Market Speech-to-Text & Voice AI for Enterprises.
Speechmatics delivers industry-leading Speech-to-Text and Voice AI for enterprises needing unrivaled accuracy, security, and flexibility. Our enterprise-grade APIs provide real-time and batch transcription with exceptional precision—across the widest range of languages, dialects, and accents.
Powered by Foundational Speech Technology, Speechmatics supports mission-critical voice applications in media, contact centers, finance, healthcare, and more. With on-prem, cloud, and hybrid deployment, businesses maintain full control over data security while unlocking voice insights.
Trusted by global leaders, Speechmatics is the top choice for best-in-class transcription and voice intelligence.
🔹 Unmatched Accuracy – Superior transcription across languages & accents
🔹 Flexible Deployment – Cloud, on-prem, and hybrid
🔹 Enterprise-Grade Security – Full data control
🔹 Real-Time & Batch Processing – Scalable transcription
Learn more
Voxtral Transcribe 2
Voxtral Transcribe 2 is a next-generation family of speech-to-text models from Mistral AI that delivers ultra-low-latency, high-quality audio transcription and speaker diarization with broad language support. The suite includes Voxtral Mini Transcribe V2, optimized for batch transcription with features such as word-level timestamps, context biasing, and support for 13 languages, and Voxtral Realtime, designed specifically for live, streaming speech recognition with latency configurable down to sub-200 ms for real-time applications. Both models achieve state-of-the-art transcription accuracy while running efficiently and economically, with Mini Transcribe V2 offering leading performance and low error rates, and Realtime available as open source under the Apache 2.0 license so developers can deploy it on edge devices or in private environments.
Learn more
Pricing
Starting Price:
$0.008/min
Pricing Details:
Usage-based pricing is $0.008 per minute of realtime transcription audio.
Company Information
Mistral AI
Founded: 2023
France
docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0
Videos and Screen Captures
Other Useful Business Software
Fully Managed MySQL, PostgreSQL, and SQL Server
Cloud SQL handles your database ops end to end, so you can focus on your app.
Product Details
Platforms Supported
Cloud
On-Premises
Training
Documentation
Support
Online
