'%3e%3cpath%20class='st0'%20d='m%201163.3,226.8%20-13.5,24%20c%20-17.8,-13.7%20-44.2,-15.7%20-62,-1%20-28.7,23.7%20-26.7,78.5%2018,78.8%2012.5,0%2023.1,-5.9%2034.5,-9.8%20l%206,23.9%20c%20-10.1,4.7%20-20.4,9.5%20-31.5,11%20-101.2,13.8%20-95.4,-132.3%20-3.9,-139.9%2019.2,-1.6%2036.1,3.4%2052.5,13%20z'%20/%3e%3cpath%20class='st0'%20d='m%201093.4,203.8%20c%20-15.4,4.6%20-29.7,13.1%20-40.5,25%20-2,-24.2%203.4,-73.1%2030.3,-82.7%204,-1.4%2017.7,-4.9%2017.3,2.2%20-0.4,7.1%20-9.9,19.3%20-12.2,25.9%20-4,11.6%20-0.3,19.6%205.2,29.7%20z'%20/%3e%3cpolygon%20class='st0'%20points='1131.4,307.8%201116.4,307.8%201116.4,290.8%201099.4,290.8%201099.4,276.8%201114.9,276.8%201116.4,275.3%201116.4,258.8%201131.4,258.8%201131.4,276.8%201147.4,276.8%201147.4,290.8%201131.4,290.8%20'%20/%3e%3cpolygon%20class='st0'%20points='1186.4,290.8%201186.4,307.8%201171.4,307.8%201171.4,290.8%201155.4,290.8%201155.4,276.8%201171.4,276.8%201171.4,258.8%201186.4,258.8%201186.4,275.3%201187.9,276.8%201203.4,276.8%201203.4,290.8%20'%20/%3e%3cpath%20class='st0'%20d='m%201142.3,156.9%20c%202,3%20-9.3,15.9%20-11.1,19.2%20-5.2,9.8%20-1.7,15.4%202.2,24.7%20-11.3,-1.7%20-21.8,-0.3%20-33,1%202.5,-21.5%2014.6,-52.8%2041.9,-44.9%20z'%20/%3e%3c/g%3e%3c/g%3e%3c/svg%3e){kind=small}
OpenAI hosted
A dedicated profile for OpenAI's hosted service and model-specific rules.
Planned scope →Supported backends
Install supported local runtimes in Freehand, or connect a server you already run. Compare capabilities below; each entry shows which setup is available.
Freehand can install NeMo-Speech.cpp, llama.cpp, and Windows whisper.cpp with a selected model catalog. Other backends need a separately configured service. Local runtimes & models →
Check your release. This catalog includes profiles that may not yet be in your installed version.
| Backend | Transcription | Live dictation | Cleanup | Speech | Guide |
|---|---|---|---|---|---|
Generic OpenAI-compatible Connect OpenAI-compatible services for transcription, cleanup, or text to speech. Connect your own service | Supported | Not supported | Supported | Supported | Setup ↗ |
Speaches Use one speech server for dictation, audio files, and text to speech. Connect your own service | Supported | Not supported | Not supported | Supported | Setup ↗ |
NeMo-Speech.cpp Transcribe with Parakeet or Nemotron and generate speech with MagpieTTS. | Supported | Supported | Not supported | Supported | Setup ↗ |
whisper.cpp Transcribe microphone recordings and audio files with whisper.cpp. | Supported | Not supported | Not supported | Not supported | Setup ↗ |
vLLM Connect speech recognition and text cleanup models through vLLM. Connect your own service | Supported | Supported | Supported | Not supported | Setup ↗ |
llama.cpp Polish completed transcripts with a text model running in llama.cpp. | Not supported | Not supported | Supported | Not supported | Setup ↗ |
vLLM-Omni Generate speech with Qwen3-TTS preset voices, languages, and style instructions. Connect your own service | Not supported | Not supported | Not supported | Supported | Setup ↗ |
Kokoro-FastAPI Generate spoken audio with Kokoro-FastAPI. Connect your own service | Not supported | Not supported | Not supported | Supported | Setup ↗ |
No matching backends. Try another name or capability.
Support is profile-specific. The server version and model still determine what works. Live dictation requires an explicitly qualified model profile.
Transcription includes Voice and audio files. Streamed file results are separate from live microphone dictation. Model profiles →
Detailed capability comparison
Recognition language, vocabulary, cleanup, and speech-generation controls by backend. See the setup guide for model-specific restrictions.
| Backend | Dictation | Audio files | Live dictation | File streaming | STT language | STT context | STT hotwords | STT temperature | Cleanup | Cleanup token limit | Disable reasoning | Speech playback | Voice discovery | Speech language | Speech style | Speaking speed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Generic OpenAI-compatible | Supported | Supported | Not supported | Supported | Supported | Supported | Not supported | Supported | Supported | Supported | Not supported | Supported | Not supported | Not supported | Not supported | Supported |
| Speaches | Supported | Supported | Not supported | Supported | Supported | Supported | Supported | Supported | Not supported | Not supported | Not supported | Supported | Supported | Not supported | Not supported | Supported |
| NeMo-Speech.cpp | Supported | Supported | Supported | Not supported | Supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Supported | Supported | Supported | Not supported | Not supported |
| whisper.cpp | Supported | Supported | Not supported | Not supported | Supported | Supported | Not supported | Supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported |
| vLLM | Supported | Supported | Supported | Supported | Supported | Supported | Not supported | Supported | Supported | Supported | Supported | Not supported | Not supported | Not supported | Not supported | Not supported |
| llama.cpp | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Supported | Supported | Supported | Not supported | Not supported | Not supported | Not supported | Not supported |
| vLLM-Omni | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Supported | Supported | Supported | Supported | Supported |
| Kokoro-FastAPI | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Not supported | Supported | Supported | Not supported | Not supported | Supported |
Planned dedicated profiles
LocalAI
A planned profile for transcription, cleanup, and speech through LocalAI.
Planned scope →openedai-speech
A speech profile for endpoints with server-configured voice aliases.
Planned scope →These dedicated profiles are not available. Some services may work through Generic OpenAI-compatible where their API matches that contract.