# 0nutation/SpeechGPT

SpeechGPT Series: Speech Large Language Models

Repository: https://github.com/0nutation/SpeechGPT
Canonical: https://ross.abutalabs.com/products/0nutation-speechgpt
Homepage: https://0nutation.github.io/SpeechGPT.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2024-07-22T10:08:09+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 86
- inputs: {"age_days": 1205, "days_push": 772, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1401, forks 97 (observed 2026-08-28T04:04:37.257477+00:00)

## What it is
SpeechGPT is a series of speech large language models that can perceive and generate speech, supporting cross-modal instruction following and speech dialogue. It includes SpeechGPT and SpeechGPT-Gen, along with related components like SpeechTokenizer and the SpeechInstruct dataset.

## Use cases
- build a voice chatbot that listens and speaks
- transcribe speech to text with an LLM
- generate natural-sounding speech from text
- research multimodal speech language models
- run speech-to-speech conversation experiments

## When to choose
- you need an open speech LLM for research on cross-modal conversation
- you want both speech understanding and generation in one model
- you need a speech tokenizer for speech language model pipelines

## When to avoid
- you need a production-grade low-latency voice assistant
- you only need simple ASR or TTS without LLM integration
- you lack GPU resources for large model inference

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, tts, llm-inference, machine-learning, chatbot
- domain: speech-processing, large-language-models, artificial-intelligence
- platform: python
- tags: speech-llm, multimodal, speech-generation, research, speech-tokenizer, natural-language-processing, gpu, linux

## Member repositories
- 0nutation/SpeechGPT (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:37.257477+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:00.606301+00:00, confidence not recorded.
  - readme: https://github.com/0nutation/SpeechGPT (fetched 2026-08-28T04:04:37.257477+00:00, sha 13b1e564927a)
  - homepage: https://0nutation.github.io/SpeechGPT.github.io/ (fetched 2026-08-29T11:53:14.034541+00:00, sha f6c3560322fe)
- Data as of 2026-08-30T08:39:29.467469+00:00.