// Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.
| 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. |
Integrate STT providers that emit reliable interim/final transcripts, interruption signaling, and stt_latency_ms metrics.
If user does not answer:
In scope:
api/assistant-api/internal/transformer/<provider>/stt.go (+ provider option/callback helpers)api/assistant-api/internal/transformer/transformer.goapi/assistant-api/internal/type/stt_transformer.go, packet.goOut of scope:
deepgram, assembly-ai, sarvamazure, google, awsInput:
UserAudioPacketRequired outputs:
SpeechToTextPacket (interim/final)InterruptionPacket{Source:"word"} when provider exposes speech-onset word signalConversationEventPacket{Name:"stt", ...}MessageMetricPacket{Name:"stt_latency_ms"} per utterancego test ./api/assistant-api/internal/transformer/... -run TestSTTgo test ./api/assistant-api/internal/transformer/<provider>/...cd ui && yarn test providers./.claude/skills/stt-integration/scripts/validate.sh --check-diff --provider <provider>Add or modify noise-reduction providers in assistant-api with denoiser factory wiring, packet safety, and UI option compatibility.
Add or modify microphone noise-reduction providers in assistant-api with denoiser factory wiring, packet safety, and option/UI compatibility.
Add or modify end-of-speech integrations in assistant-api with strict separation from VAD internals. Use for transcript/audio/history-aware turn-finalization logic, provider wiring, and EOS UI config.
Add or modify LLM/integration providers in integration-api with caller factory wiring, unified provider routing, streaming behavior, and metric/audit compatibility.
Explain and validate local setup paths for this repo with Docker and without Docker. Use when developers need exact prerequisites, startup commands, health checks, and troubleshooting steps.
Build a code-grounded implementation plan before coding. Use to trace packet flow, factory boundaries, provider config loading, and exact file-level change scope for a requested integration.