# Installer speech avec Homebrew

Consultez les chemins d'installation, exécutables, métadonnées et notes de sécurité de speech pour les workflows d'agents IA.

## installation

```sh
sudo av install brew:speech
```

Commandes d'installation supplémentaires:

### macOS

- Homebrew (100%):

```sh
brew install speech
```

  Preuve: local Homebrew formula metadata

## Faits du paquet

- **Clé du paquet:** brew:speech
- **Gestionnaire de paquets:** Homebrew
- **Page du gestionnaire de paquets:** <https://formulae.brew.sh/formula/speech>
- **Version:** 0.0.21
- **Résumé source:** On-device speech toolkit for Apple Silicon: ASR, TTS, VAD, diarization
- **Page d'accueil:** <https://soniqo.audio>
- **Dépôt:** <https://github.com/soniqo/speech-swift>
- **Docs amont:** <https://github.com/soniqo/speech-swift#readme>
- **Licence:** Apache-2.0
- **Archive source:** <https://github.com/soniqo/speech-swift/archive/refs/tags/v0.0.21.tar.gz>
- **Dernière mise à jour:** 2026-06-17T17:20:31Z
- **Généré:** 2026-07-08T18:08:21+00:00

## exécutables

- speech (cli)
- speech-server (cli)
- speech (alias)
- speech-server (alias)

## Comportement d'installation

- hook post-installation: non défini
- Bouteille: disponible sur arm64_sequoia, arm64_tahoe

## Version et fraîcheur

- page générée: 2026-07-08
- version du gestionnaire: 0.0.21
- gestionnaire mis à jour: 2026-06-17
- données locales: OK
- dépôt amont: https://github.com/soniqo/speech-swift
- dernière version détectée: v0.0.21 (à jour)
## Historique du projet et usages

speech is the Homebrew-facing CLI for Speech Swift, a young Apple Silicon speech toolkit that packages local ASR, TTS, VAD, diarization, and related speech models behind Swift, MLX, and CoreML.

### Historique du projet

The official repository was created in February 2026 and describes Speech Swift as AI speech models for Apple Silicon, powered by MLX Swift and CoreML, for Mac and iOS speech recognition, synthesis, and understanding. The README emphasizes local execution with no cloud service, API keys, or off-device data transfer.

### Historique d'adoption

The project moved quickly through 0.0.x releases in 2026. Its v0.0.20 release notes say the CLI binary was renamed from audio to speech specifically to make room for an eventual Homebrew formula, which ties the package name directly to command-line distribution concerns.

### Modes d'utilisation

The README presents the toolkit as both Swift package modules and command-line demos; release notes show Homebrew-style usage such as upgrading the speech formula or building the release binary from source. Package users care because it turns large on-device speech models into a normal installable CLI on Apple Silicon.

### Pourquoi les passionnés de paquets s'y intéressent

For package maintainers, speech is interesting because it represents the 2020s shift from cloud speech APIs to local ML runtimes installed with ordinary package managers. Its formula name, binary rename, model assets, and Apple Silicon focus are all practical packaging concerns rather than just library metadata.

### Chronologie

- 2026: soniqo/speech-swift repository created on GitHub.
- 2026: v0.0.20 renamed the CLI binary from audio to speech for Homebrew packaging.
- 2026: v0.0.21 release notes continued documenting CLI and Homebrew upgrade usage.

### Related projects

- MLX Swift and CoreML provide the local Apple Silicon execution backends used by Speech Swift.
- Speech Swift wraps several speech model families, including ASR, TTS, VAD, and diarization components.

### Sources

- <https://api.github.com/repos/soniqo/speech-swift>
- <https://github.com/soniqo/speech-swift>
- <https://github.com/soniqo/speech-swift/releases>


## Notes de sécurité

Aucun manifest local de gestion des secrets correspondant n'a été trouvé pour speech. Les métadonnées de paquet Nucleus restent publiées ici afin que la couverture future dispose d'une URL stable.


## Détails de la base source

- **Source Database:** Homebrew formula API
- **Tap:** homebrew/core
- **Full Name:** speech
- **Version Scheme:** 0
- **Revision:** 0
- **Head Version:** HEAD
- **Requirements:** arch, macos, xcode
- **Bottle Stable Root URL:** <https://ghcr.io/v2/homebrew/core>
- **Deprecated:** no
- **Disabled:** no
- **Keg Only:** no
- **URL Keys:** head, stable


## Liens liés

- [Networking and protocol packages](https://www.automicvault.com/fr/pkg/networking-protocol-tools/) - Matched network, protocol, or remote-service metadata.
- [Media and graphics packages](https://www.automicvault.com/fr/pkg/media-graphics-tools/) - Matched media, image, audio, video, or graphics metadata.
- [speech-tools](https://www.automicvault.com/fr/pkg/brew/speech-tools/) - Package name indicates the same formula family.
- [whisperkit-cli](https://www.automicvault.com/fr/pkg/brew/whisperkit-cli/) - Local package facts share a topical domain. Shared terms: apple, device, on-device, silicon, speech.
- [whisper-cpp](https://www.automicvault.com/fr/pkg/brew/whisper-cpp/) - Local metadata places this package in an adjacent workflow. Shared terms: server, speech, vad.

## Combined YAML source

View the package source record on GitHub. [combined/speech.yml](https://github.com/automic-vault/db/blob/main/combined/speech.yml)


## Sources

- Nucleus package database
- package-page enrichment
- curated package history
- package version freshness
- package relationship graph
- cross-ecosystem install command graph