---
title: "Custom vocabulary in speech recognition: hotwords, keyterms and prompts"
description: "How custom vocabulary works in speech-to-text: hotwords, keyterms and prompts, with syntax and limits for Phonon, Deepgram, AssemblyAI, OpenAI and Whisper."
canonical: "https://www.fermionresearch.com/speech/custom-vocabulary-speech-recognition/"
source: "Fermion Research"
---

Speech recognition/facts checked 13 November 2026

# Custom vocabulary in speech recognition: hotwords, keyterms and prompts

General models miss the words that matter most to you: names, product codes, drug names, jargon. Every major system now lets you pass a list of terms with the audio; they differ in syntax, limits and price.

[Hotwords in the speech docs](https://www.fermionresearch.com/docs/speech/)

## The short answer

Custom vocabulary means passing a list of words with each request so the recogniser favours them when the audio is close: Phonon-2 calls it hotwords (up to 25 terms), Deepgram calls it keyterm prompting (up to 500 tokens), AssemblyAI calls it keyterms_prompt (up to 1,000 words or phrases on Universal-3.5 Pro), and OpenAI and Whisper use a text prompt. The list biases recognition; it does not retrain the model.

Use it for names and terms the model has rarely heard. Keep the list short and specific to the request, because a long list of common words gives the model more ways to insert a term that was not said.

## How each system exposes it

Syntax, limits and add-on prices from each provider's documentation and pricing page, read 2026-11-13.

| System | Feature | How to pass it | Limit | Extra cost |
| --- | --- | --- | --- | --- |
| Phonon-2 (fermion, self-hosted) | hotwords | --hotwords "Ada, Quillon" or @names.txt; server field hotwords, or the OpenAI prompt field | 25 terms | none (runs on your hardware) |
| Deepgram Nova-3, Flux | keyterm prompting | keyterm= query parameter, repeated once per term | 500 tokens per request | $0.0013 per minute |
| Deepgram Nova-2 and older | keywords | KEYWORD:INTENSIFIER | see Deepgram docs | see Deepgram pricing |
| AssemblyAI Universal-3.5 Pro | keyterms_prompt | JSON list of strings | 1,000 words or phrases, 6 words per phrase | $0.05 per hour |
| AssemblyAI Universal-2 | keyterms prompting | JSON list of strings | 200 terms | $0.05 per hour |
| OpenAI gpt-transcribe | prompt, keywords | request fields | the model's length limit | no add-on listed |
| OpenAI whisper-1, Groq Whisper | prompt | request field | 224 tokens | no add-on listed |
| openai-whisper (open source) | initial_prompt | Python argument or --initial_prompt | text for the first window | none |
| faster-whisper (open source) | hotwords, initial_prompt | Python arguments | not stated | none |

## How biasing works

A speech recogniser builds the transcript one piece at a time, scoring candidate word pieces against the audio. Hotword biasing adds a bonus to pieces that continue a listed term, so when the audio is ambiguous between 'Quill on' and 'Quillon', the listed spelling wins. When the audio clearly says something else, the bonus is not enough and the listed word stays out.

Prompting works differently. Models with a language-model decoder (Whisper, gpt-transcribe, Universal-3.5 Pro) read the prompt as preceding context, which makes the listed spellings more likely in the same way a sentence makes its next word more likely. AssemblyAI's docs say its contextual prompt should describe the audio, not give instructions, and keyterms carry the term list.

Deepgram's docs warn that commas, semicolons or weights inside a keyterm value are accepted without an error but boost nothing: pass one term per keyterm parameter.

## Hotwords with Phonon-2

Phonon-2 takes up to 25 names and terms per request on every engine (Apple silicon, CPU on Linux, Windows and macOS, and the CUDA image). --hotword-lambda sets how hard the listed words pull (default 2.0). Without hotwords the transcript is unchanged, and hotwords sent with one server request do not affect other requests. Hotwords are not yet available on Phonon-2.5.

```text
fermion transcribe phonon-2 call.wav --hotwords "Ada, Quillon, Okonkwo"
fermion transcribe phonon-2 call.wav --hotwords @names.txt

# Python
import fermion
speech = fermion.load_speech("phonon-2")
text, decode_s, audio_s = speech.transcribe("call.wav", hotwords=["Ada", "Quillon", "Okonkwo"])

# Server: an explicit field, or the OpenAI prompt field read as a vocabulary list
curl -s http://127.0.0.1:8000/v1/audio/transcriptions -F file=@call.wav -F model=phonon-2 -F "hotwords=Ada, Quillon, Okonkwo"
```

## Questions

## Related

- [Speech recognition docs](https://www.fermionresearch.com/docs/speech/)
- [Server reference](https://www.fermionresearch.com/docs/server-reference/)
- [Hotword biasing (glossary)](https://www.fermionresearch.com/glossary/hotword-biasing/)
- [Phonon-2](https://www.fermionresearch.com/models/phonon-2/)
- [On-device speech recognition for regulated teams](https://www.fermionresearch.com/deploy/on-device-speech-recognition/)

## Sources and method

- Phonon-2 hotwords: /docs/speech/ and /docs/server-reference/ (fermion-research package documentation), read 2026-11-13.
- Deepgram keyterm prompting: developers.deepgram.com/docs/keyterm; add-on price: deepgram.com/pricing; read 2026-11-13.
- AssemblyAI keyterms and prompt: assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting; add-on prices and limits: assemblyai.com/pricing; read 2026-11-13.
- OpenAI prompt and keywords: developers.openai.com/api/docs/guides/speech-to-text, read 2026-11-13. Groq prompt limit: console.groq.com/docs/speech-to-text, read 2026-11-13.
- openai-whisper initial_prompt: github.com/openai/whisper (whisper/transcribe.py); faster-whisper hotwords: github.com/SYSTRAN/faster-whisper (faster_whisper/transcribe.py); read 2026-11-13.

Canonical: https://www.fermionresearch.com/speech/custom-vocabulary-speech-recognition/

Source: [https://www.fermionresearch.com/speech/custom-vocabulary-speech-recognition/](https://www.fermionresearch.com/speech/custom-vocabulary-speech-recognition/)
