Voxtral Small 24B 2507
Mistral developed Voxtral Small 24B 2507 as an enhancement to their Small 3 model, specifically designed to handle both text and audio inputs. It is built to perform speech transcription, translation, and audio analysis alongside standard text processing tasks.
Voxtral Small 24B 2507 specs and pricing
- Provider: Mistral
- Released: October 30, 2025
- Context window: 33K tokens
- Max output: 26K tokens
- Input: text, audio, files
- Output: text
- Price: $0.10 input / $0.30 output per 1M tokens
- Tool calling: yes
What Voxtral Small 24B 2507 is good at
- Transcribing spoken audio files into text
- Translating foreign language audio recordings
- Analyzing and summarizing content from audio files
To-dos to try with Voxtral Small 24B 2507
- Transcribe this 30-minute meeting recording and provide a bulleted summary of key decisions.
- Translate the spoken dialogue in this audio file into English text.
- Listen to this audio lecture and extract the main topics discussed.
FAQ
- What is the primary capability of Voxtral Small 24B 2507? The model is designed to process both text and audio, with a specific focus on speech transcription, translation, and audio understanding.
- Who created this model? Voxtral Small 24B 2507 was developed by Mistral.
- How much does Voxtral Small 24B 2507 cost? Voxtral Small 24B 2507 costs $0.10 per million input tokens and $0.30 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.32 credits ($1 = 100 credits).
- What is the context window of Voxtral Small 24B 2507? Voxtral Small 24B 2507 can read up to 33K tokens at once and write up to 26K tokens in one reply.
- Can I use Voxtral Small 24B 2507 without coding? Yes. In todo.is you pick Voxtral Small 24B 2507 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.