Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

gemma speach model use

未关闭
#215 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
30/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
dart, flutter
领域
mobile

调研方向

Start by reading the linked flutter_gemma_speech package documentation and the project's existing local-model integration points. Clarify which platforms and speech models this issue should cover before implementing the text-to-speech and speech-to-speech support. Done means the agreed speech flows work on the selected platforms and are verified with tests or a manual run.

由索引模型根据 Issue 内容生成。

描述

enhancement good first issue

here we will try to support the text to speach and speach to speach speaking also for the local models

🖼️ Multimodal Support: Text + Image input with Gemma 4, Gemma3n, FastVLM, Qwen2-VL, SmolVLM2, and LLaVA-OneVision vision models (Gemma 4 / Gemma3n on all platforms incl. Web; Qwen2-VL / SmolVLM2 / LLaVA-OneVision on Android, iOS, and Desktop; FastVLM on Desktop)
🎙️ Audio Input: Record and send audio messages with Gemma 4 and Gemma3n E2B/E4B models (Android, iOS device, macOS/Windows/Linux via LiteRT-LM — not on Web)
🎤 On-device Speech-to-Text: Opt-in flutter_gemma_speech — transcribe audio fully offline with a selectable ASR model (moonshine, Whisper, Parakeet) via the LiteRT C API (Android, iOS, macOS, Windows, Linux; Web is a follow-on)
🔊 On-device Text-to-Speech: Opt-in flutter_gemma_speech — synthesize speech fully offline with a selectable model (Matcha, Qwen3-TTS, Inflect-Nano-v2; kokoro / supertonic are follow-ons) via the LiteRT C API (Android, iOS, macOS, Windows, Linux; Web is a follow-on)
🗣️ On-device Voice Loop: VoiceSession in flutter_gemma_speech chains STT → LLM → TTS into one push-to-talk turn with barge-in — the full on-device speech-to-speech pipeline. VoiceSession.fromChat(recognizer:, chat:, synthesizer:) streams VoiceEvents from recorded PCM (native only).

主要语言
Dart
星标
2
派生
2
平均合并
1 天 35 分钟
30 天内合并 PR
36

环境准备

  • 没有 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 阅读贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

basictech01/uniun 的其他 Issue

查看 basictech01/uniun 的全部 Issue

相似的 Issue

更多 Dart Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。