Skip to main content

stt-integration

Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.

跳到安装

来源信息

仓库
rapidaai/voice-ai
最近来源活动
2026年8月23日 07:23
检测到的 SKILL.md 语言
英语
星标
733
分支
120

安装方式

默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。

检查来源文件

决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。

文件资源管理器
6 个文件

正在显示 SKILL.md

SKILL.md
来源说明 · 只读预览
name
stt-integration
description
Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.
# STT Integration Skill ## Mission Integrate STT providers that emit consistent interim/final transcripts, word interruption packets, and `stt_latency_ms` metrics. ## Inputs expected from user 1. Ingestion transport: WS, SDK callbacks, or HTTP chunks. 2. Interim transcript requirements. 3. Language/model constraints. If missing: - Use nearest transport baseline and preserve packet semantics. ## Hard boundaries In scope: - `api/assistant-api/internal/transformer/<provider>/stt.go` (+ helpers) - `api/assistant-api/internal/transformer/transformer.go` - optional contract updates: `api/assistant-api/internal/type/stt_transformer.go`, `packet.go` - provider STT metadata and UI components Out of scope: - TTS-only internals - telephony internals - EOS/VAD algorithms ## Packet contract Input: - `UserAudioPacket` Required outputs: - `SpeechToTextPacket` interim/final - `InterruptionPacket{Source:"word"}` when available - `ConversationEventPacket{Name:"stt", ...}` - `MessageMetricPacket{Name:"stt_latency_ms"}` once per utterance ## Implementation workflow 1. Pick baseline (`deepgram`, `assembly-ai`, `azure`, `google`, `aws`, `sarvam`). 2. Implement provider package under transformer. 3. Register in STT factory switch. 4. Wire UI provider model/language config. 5. Validate transcript ordering and context consistency. 6. Add provider + integration tests. ## Governed lifecycle - Classify work as Fast, Standard, or Governed using `DEVELOPMENT_PROCESS.md`; use the full gated lifecycle only for Governed work. - This skill operates only in its assigned phase and path ownership; it may not approve its own plan or code review. - Governed implementation starts only from a coordinator-attested approved plan; Fast and Standard work follows its lighter documented lifecycle. - Return changed-file and verification evidence to the coordinator, then route the complete verified diff to the read-only `code-reviewer`. ## Validation commands - `go test ./api/assistant-api/internal/transformer/... -run TestSTT` - `go test ./api/assistant-api/internal/transformer/<provider>/...` - `cd ui && yarn test providers` - `./skills/stt-integration/scripts/validate.sh --check-diff --provider <provider>` ## References - `references/checklist.md` - `references/stt-checklist.md` - `examples/sample.md`
在 GitHub 查看