The short answer
For transcription alone, Phonon-2.5 has a lower English word error than all three open Voxtral models in the Open ASR Leaderboard snapshot: 5.06 % (Phonon-2.5 English 4.82 %) against 5.21 % for Voxtral Small 24B, 5.63 % for Voxtral Mini 3B and 6.12 % for Voxtral Mini 4B Realtime. Choose Voxtral when you want one model that also understands audio (questions, summaries, function calls), or Mistral's hosted transcription with diarization.
The averages hide a split: Voxtral Small 24B is lower on LibriSpeech, SPGISpeech and VoxPopuli, and Phonon is far lower on AMI meeting audio, which carries the average.
Side by side
Voxtral facts from Mistral's Hugging Face model cards and docs.mistral.ai, read 2026-11-13. Hosted prices from OpenRouter, read 2026-11-11.
| Phonon-2.5 | Voxtral Mini 3B (2507) | Voxtral Mini 4B Realtime (2602) | |
|---|---|---|---|
| Model type | Open weights on Hugging Face | Open weights | Open weights |
| Size | 156 MB download (Phonon-2.5 English: 158 MB) | About 9.5 GB of GPU memory in bf16 (Mistral's card) | 4B parameters; a single GPU with 16 GB or more |
| Languages | 25 European languages (Phonon-2.5 English: English only) | 8 | 13 |
| English word error, seven Open ASR sets | 5.06 % (Phonon-2.5 English: 4.82 %) | 5.63 % | 6.12 % |
| Hosted price per audio hour | No per-hour fee when self-hosted | $0.06 (DeepInfra) | Hosted as Voxtral Mini Transcribe Realtime |
| Where it runs | Your hardware: CPUs (Linux x86-64 and arm64, Windows x86-64), Apple silicon, NVIDIA GPUs, Android | GPU with vLLM or Transformers | GPU with vLLM; Transformers 5.2+ |
| Streaming | Yes, live WebSocket from fermion serve | No | Yes, delay configurable from 80 ms to 2.4 s |
| Diarization | No | No (Mistral's hosted batch model has it) | No |
| Word timestamps | Yes (--json output) | Hosted batch model only | No |
English, set by set
Voxtral Small 24B is the closest on average (5.21 %), lower than Phonon-2.5 on four sets. Phonon's lead comes from AMI, where every Voxtral model is above 13 % and Phonon-2.5 is 9.12 %.
| Test set | Phonon-2.5 | Phonon-2.5 English | Voxtral Small 24B | Voxtral Mini 3B | Voxtral Mini 4B Realtime |
|---|---|---|---|---|---|
| LibriSpeech clean | 1.60 | 1.64 | 1.23 | 1.48 | 1.62 |
| LibriSpeech other | 3.41 | 3.56 | 2.80 | 3.63 | 4.94 |
| AMI | 9.12 | 8.76 | 13.19 | 13.57 | 13.34 |
| Earnings-22 | 6.72 | 6.22 | 7.07 | 7.66 | 9.31 |
| GigaSpeech | 8.04 | 7.99 | 8.33 | 8.70 | 8.80 |
| SPGISpeech | 3.31 | 3.31 | 1.84 | 2.15 | 2.23 |
| VoxPopuli | 3.23 | 2.28 | 2.00 | 2.22 | 2.60 |
| Average of the seven | 5.06 | 4.82 | 5.21 | 5.63 | 6.12 |
Hosted Voxtral
Mistral's current hosted transcription models are Voxtral Mini Transcribe 3, Voxtral Small Transcribe 3 and Voxtral Mini Transcribe Realtime 3. Mistral's transcription docs list speaker diarization, word timestamps, context biasing and recordings up to 3 hours for the batch model, and 13 languages. OpenRouter lists Voxtral Mini Transcribe 3.0 at $0.21 and Voxtral Small Transcribe 3.0 at $0.24 per audio hour. These hosted models have no row in our leaderboard snapshot, so no accuracy figure is given for them.
Where each is the better choice
- Voxtral: questions and summaries about audio, function calling from voice, long recordings in one call (30 minutes for Mini 3B), lower word error on SPGISpeech and VoxPopuli (and on LibriSpeech for Voxtral Small 24B), and hosted diarization.
- Phonon-2.5: meetings (AMI), 25 European languages including the Baltic and smaller Slavic languages, no GPU needed, and a 156 MB download against several gigabytes.
pip install fermion-research
fermion transcribe phonon-2.5 interview.wav --json
fermion serve phonon-2.5 # POST /v1/audio/transcriptions, GET /v1/audio/streamQuestions
- Is Phonon-2.5 more accurate than Voxtral?
- On the Open ASR Leaderboard's seven English sets, Phonon-2.5's average (5.06 %) is lower than Voxtral Small 24B (5.21 %), Voxtral Mini 3B (5.63 %) and Voxtral Mini 4B Realtime (6.12 %). Voxtral models are lower on SPGISpeech and VoxPopuli (Voxtral Small 24B also on LibriSpeech); Phonon is much lower on AMI.
- Can Phonon-2.5 answer questions about audio like Voxtral?
- No. Phonon-2.5 is a transcription model. Voxtral Mini 3B also answers questions, summarises and calls functions from audio.
- Does Voxtral need a GPU?
- Mistral's cards describe GPU serving: about 9.5 GB of GPU memory for Voxtral Mini 3B in bf16 and a GPU with 16 GB or more for Voxtral Mini 4B Realtime. Phonon-2.5 runs on a CPU.
- Which languages does Voxtral support?
- Mistral's card lists 8 languages for Voxtral Mini 3B and 13 for Voxtral Mini 4B Realtime and the hosted transcription models. Phonon-2.5 covers 25 European languages.
- Which is better for live transcription?
- Both stream. Voxtral Mini 4B Realtime has a configurable delay from 80 ms to 2.4 s on a GPU; Phonon streams over a WebSocket from fermion serve on CPU or GPU.
Related
Sources and method
- Voxtral Mini 3B: huggingface.co/mistralai/Voxtral-Mini-3B-2507, read 2026-11-13. Voxtral Mini 4B Realtime: huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602, read 2026-11-13.
- Hosted models and features: docs.mistral.ai/capabilities/audio_transcription and docs.mistral.ai/getting-started/models, read 2026-11-13. Prices: OpenRouter model pages, read 2026-11-11.
- Rival English word error: Open ASR Leaderboard, seven English sets, snapshot 2026-09-25 (huggingface.co/spaces/hf-audio/open_asr_leaderboard).
- Phonon-2.5 and Phonon-2.5 English: Fermion Research measurement, Phonon-2.5 release post (2026-10-22), Open ASR Leaderboard scoring code, full test sets of the same seven sets.
Canonical: https://www.fermionresearch.com/models/phonon-2-5/vs-voxtral/