source/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-02-08 21:09:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore(voice-call): release 0.1.0

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-13 11:08:27 +00:00
parent d36a004468
commit 119e53967b
2 changed files with 14 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
extensions/voice-call/CHANGELOG.md
View File

@@ -3,17 +3,18 @@
## 0.1.0
### Highlights
- Initial release of the @clawdbot/voice-call plugin.
- First public release of the @clawdbot/voice-call plugin.
### Changes
- Providers: Twilio (Programmable Voice + Media Streams), Telnyx (Call Control v2), and mock dev provider.
- Outbound calls: notify mode with auto-hangup + conversation mode for multi-turn calls.
- Inbound calls: policies (disabled/allowlist/open), allowlist matching, and inbound greeting.
- Webhooks: local server with configurable bind/port/path plus publicUrl override.
- Exposure: ngrok and Tailscale (serve/funnel) tunnel helpers; dev-only signature bypass for ngrok free tier.
- Streaming: OpenAI Realtime STT with media stream WebSocket + partial/final transcripts.
- Speech: OpenAI TTS (model/voice/instructions) with Twilio <Say> fallback.
- Tooling: `voice_call` tool with action-based API for initiate/continue/speak/end/status.
### Features
- Providers: Twilio (Programmable Voice + Media Streams), Telnyx (Call Control v2), and mock provider for local dev.
- Call flows: outbound notify vs. conversation modes, configurable auto‑hangup, and multi‑turn continuation.
- Inbound handling: policy controls (disabled/allowlist/open), allowlist matching, and inbound greeting.
- Webhooks: built‑in server with configurable bind/port/path plus `publicUrl` override.
- Exposure helpers: ngrok + Tailscale serve/funnel; dev‑only signature bypass for ngrok free tier.
- Streaming: OpenAI Realtime STT over media WebSocket with partial + final transcripts.
- Speech: OpenAI TTS (model/voice/instructions) with Twilio `<Say>` fallback.
- Tooling: `voice_call` tool actions for initiate/continue/speak/end/status.
- Gateway RPC: `voicecall.initiate|continue|speak|end|status` (+ legacy `voicecall.start`).
- CLI: `clawdbot voicecall` commands (call/start/continue/speak/end/status/tail/expose).
- RPC: gateway methods (`voicecall.initiate|continue|speak|end|status` + legacy `voicecall.start`).
- Persistence: JSONL call logs with `voicecall tail` for live inspection.
- Observability: JSONL call logs and `voicecall tail` for live inspection.
- Response controls: `responseModel`, `responseSystemPrompt`, and `responseTimeoutMs` for auto‑responses.

2
extensions/voice-call/package.json
View File

@@ -1,6 +1,6 @@
{
"name": "@clawdbot/voice-call",
"version": "0.0.1",
"version": "0.1.0",
"type": "module",
"description": "Clawdbot voice-call plugin",
"dependencies": {