# Transcribe or understand speech on device (slim)

> Transcribe or understand speech on device: 1 companies fully do it, 4 with a limit, 90 carry the tag. Every listing in Open-weight models with the reason and a source.

- Full: https://www.anchorterminal.com/niches/open-weights.speech-input/index.md (~3,950 tokens) · this version ~430 tokens · JSON https://www.anchorterminal.com/niches/open-weights.speech-input/index.json · canonical https://www.anchorterminal.com/niches/open-weights.speech-input/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-15
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

One company's docs show a full fit. Full fit: 1 companies, with a limit: 4, tagged: 90. Weight 6, 3 accounts.

Done when: The model takes the audio clip as input and returns a transcript.
yes: gemma-4-e4b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
caveat: apertus-v1-5-8b (ETH Zurich and EPFL (the Swiss National AI Institute, named in the Acceptable Use Policy))
caveat: gemma-4-12b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
caveat: gemma-4-e2b-it (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))
caveat: minicpm-o-4-5 (OpenBMB (named as the MiniCPM-o team on the technical report; the GitHub LICENSE is the unfilled Apache template))
caveat: nemotron-3-nano-omni-30b-a3b-reasoning (NVIDIA Corporation)
caveat: qwen3-omni-30b-a3b-instruct (Alibaba Cloud (carried from the 20 October 2026 pilot; this model's files name no copyright holder))

Data: https://www.anchorterminal.com/api/v1/use-cases/open-weights.speech-input.json
