Ross ROSS = Recommend OSS · open-source software intelligence for agents

kyutai-labs/hibiki

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk. observed · 2026-08-28

github.com/kyutai-labs/hibiki · Rust · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

28/100

  • Activity 16
  • Release rhythm 35
  • Longevity 41

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 575
  • days_rel: n/a
  • days_push: 505
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1509 stars · 119 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Hibiki is a decoder-only model for streaming (simultaneous) speech-to-speech translation, built on the multistream Moshi architecture. It processes source speech in real time and generates target-language speech with optional voice transfer, along with timestamped text translation.

Use cases

  • translate live speech in real time while the speaker is still talking
  • simultaneous interpretation for meetings or broadcasts
  • generate translated speech preserving the original speaker's voice
  • produce timestamped text transcripts of a translation as audio streams
  • run a speech translation model locally on GPU

When to choose

  • you need low-latency, chunk-by-chunk translation rather than waiting for the utterance to end
  • you want both audio and text output from a single model
  • voice transfer to keep the speaker's voice in the translation matters
  • you need a batch-friendly model with simple temperature sampling inference

When to avoid

  • you only need offline translation of complete recordings with maximum quality
  • your language pair is not supported by the released models
  • you have no GPU and need fast real-time performance
  • you need text-only document translation

Facets

library · maturity active

speech-recognition machine-learning audio-processing llm-inference speech-processing machine-learning python rust cross-platform simultaneous-translation speech-to-speech streaming-translation voice-transfer moshi decoder-only natural-language-processing audio gpu

2 sources

Member repositories

RepositoryRoleHealth v2
kyutai-labs/hibikimain28

For agents

markdown · JSON · MCP: product_card(name="kyutai-labs/hibiki")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem