# Camb-ai/MARS5-TTS

MARS5 speech model (TTS) from CAMB.AI

Repository: https://github.com/Camb-ai/MARS5-TTS
Canonical: https://ross.abutalabs.com/products/mars5-tts
Homepage: https://www.camb.ai
Language: Jupyter Notebook
License: AGPL-3.0
License Family: copyleft
Topics: prosody, speech, speech-synthesis, text-to-speech, voice-cloneai, voice-cloning
Last push: 2024-08-01T10:42:51+00:00

## Health v2 (maintenance only)
Score: 14/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 58
- inputs: {"age_days": 821, "days_push": 762, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2817, forks 246 (observed 2026-08-28T04:07:23.885827+00:00)

## What it is
MARS5 is an open-source English text-to-speech model from CAMB.AI that uses a two-stage AR-NAR pipeline to generate expressive speech with strong prosody. It supports voice cloning from a short (2-12 second) reference audio clip, with optional 'deep clone' mode using a reference transcript for improved quality.

## Use cases
- clone a voice from a short audio sample
- generate expressive speech with natural prosody
- synthesize sports commentary or anime-style speech
- control pauses and emphasis via punctuation and capitalization
- run text-to-speech locally in Python or Colab

## When to choose
- you need high-quality English TTS with expressive prosody
- you want open-source voice cloning from a few seconds of reference audio
- you want fine-grained prosody control through text formatting

## When to avoid
- you need multilingual speech synthesis beyond English
- you need a production-grade hosted API with SLAs
- you cannot run GPU inference or accept AGPL-3.0 licensing

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning
- domain: speech-processing, machine-learning
- platform: python, cross-platform
- tags: voice-cloning, text-to-speech, prosody, speech-synthesis, ar-nar-pipeline, english-only, audio, gpu

## Member repositories
- Camb-ai/MARS5-TTS (main) score 14

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:23.885827+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 2026-08-30T08:13:01.741219+00:00, confidence not recorded.
  - readme: https://github.com/Camb-ai/MARS5-TTS (fetched 2026-08-28T04:07:23.885827+00:00, sha 4d369eac41e8)
  - homepage: https://www.camb.ai (fetched 2026-08-29T09:54:02.587563+00:00, sha 58cd2aff96c1)
  - site_page: https://www.camb.ai/features/text-to-speech (fetched 2026-08-29T09:54:02.590376+00:00, sha 2fd42b34c619)
  - site_page: https://www.camb.ai/features/voice-library (fetched 2026-08-29T09:54:02.592352+00:00, sha 3dd3aef9f484)
  - site_page: https://www.camb.ai/features/translation (fetched 2026-08-29T09:54:02.594047+00:00, sha 8ac04674c015)
  - site_page: https://www.camb.ai/features/subtitles-captions (fetched 2026-08-29T09:54:02.595590+00:00, sha 0ff4f3d3bc8f)
  - site_page: https://www.camb.ai/features/image-translation (fetched 2026-08-29T09:54:02.597128+00:00, sha b48d5dc33674)
  - site_page: https://docs.camb.ai (fetched 2026-08-29T09:54:02.598669+00:00, sha 44ac27da61bd)
  - site_page: https://docs.camb.ai/introduction (fetched 2026-08-29T09:54:02.601944+00:00, sha 4dfef67f148a)
  - site_page: https://www.camb.ai/pricing (fetched 2026-08-29T09:54:02.600122+00:00, sha 85acaf7971d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.