# suno-ai/bark

🔊 Text-Prompted Generative Audio Model

Repository: https://github.com/suno-ai/bark
Canonical: https://ross.abutalabs.com/products/suno-ai-bark
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-08-19T07:45:36+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 88
- inputs: {"age_days": 1244, "days_push": 744, "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 39249, forks 4671 (observed 2026-08-28T04:12:07.798617+00:00)

## What it is
Bark is Suno's open-source transformer-based text-to-audio model that generates highly realistic multilingual speech, music, background noise, sound effects, and nonverbal sounds like laughing and sighing. It is distributed as a Python library with pretrained checkpoints ready for inference and licensed under MIT for commercial use.

## Use cases
- generate realistic speech from text prompts
- create multilingual text-to-speech voiceovers
- generate sound effects and background noise from text
- produce audio with laughing, sighing, and other nonverbal cues
- build voice prompt-based audio generation pipelines
- run text-to-speech inference on GPU or CPU

## When to choose
- you need expressive, generative speech beyond conventional TTS
- you want multilingual speech plus music and sound effects from one model
- you need an MIT-licensed TTS model for commercial use
- you want pretrained checkpoints for research or inference

## When to avoid
- you need deterministic, predictable TTS output that strictly follows the prompt
- you need production-grade long-form narration with strict voice consistency
- you cannot run GPU inference and need fast, low-latency synthesis
- you need a text-to-music model rather than general audio generation

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, audio-processing, machine-learning, llm-inference
- domain: speech-processing, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: text-to-audio, generative-audio, voice-cloning, sound-effects, transformer-model, audio, gpu

## Member repositories
- suno-ai/bark (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:07.798617+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 2026-08-29T16:24:17.081758+00:00, confidence not recorded.
  - readme: https://github.com/suno-ai/bark (fetched 2026-08-28T04:12:07.798617+00:00, sha 5be224a107fb)
  - registry_pypi: https://pypi.org/pypi/bark/json (fetched 2026-08-29T07:46:49.231961+00:00, sha 6e1e8bfb4407)
- Data as of 2026-08-30T08:39:29.467469+00:00.