@rimelabs/sdk 0.1.0-alpha.6 → 0.1.0-alpha.8

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [0.1.0-alpha.8](https://github.com/rimelabs/rime-sdk/compare/typescript-v0.1.0-alpha.7...typescript-v0.1.0-alpha.8) (2026-10-08)
+
+
+### Features
+
+* add voice examples and automate example dependency updates ([#22](https://github.com/rimelabs/rime-sdk/issues/22)) ([dea7044](https://github.com/rimelabs/rime-sdk/commit/dea7044831058ebee9ae536e8d822a4d7fabbd3d))
+
+## [0.1.0-alpha.7](https://github.com/rimelabs/rime-sdk/compare/typescript-v0.1.0-alpha.6...typescript-v0.1.0-alpha.7) (2026-10-07)
+
+
+### Bug Fixes
+
+* publish npm releases under the latest tag ([#20](https://github.com/rimelabs/rime-sdk/issues/20)) ([40cf8a4](https://github.com/rimelabs/rime-sdk/commit/40cf8a44720be24cd42acc5f9f97f1269b786e3e))
+
 ## [0.1.0-alpha.6](https://github.com/rimelabs/rime-sdk/compare/typescript-v0.1.0-alpha.5...typescript-v0.1.0-alpha.6) (2026-10-07)
 
 

package/README.md

@@ -10,7 +10,7 @@ Requires Node.js 22 or later. This alpha package uses ESM and includes TypeScrip
 types. Browser use is not supported.
 
 ```sh
-npm install @rimelabs/sdk@next
+npm install @rimelabs/sdk
 export RIME_API_KEY="your-api-key"
 ```
 
@@ -19,70 +19,51 @@ does not load `.env` files.
 
 ## TTS quick start
 
-Save this as `speech.mjs` and run `node speech.mjs`:
+Save playable speech with the
+[WAV example](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/tts/save.ts).
+After the [example setup](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md#nodejs), run from the repository root:
 
-```javascript
-import { writeFile } from "node:fs/promises";
-import { Rime } from "@rimelabs/sdk";
-
-const client = new Rime();
-try {
-  const audio = client.tts.stream("Hello. This is Rime.");
-  await writeFile("speech.pcm", audio);
-  console.log(audio.requestId);
-} finally {
-  await client.close();
-}
+```sh
+npm --prefix examples/typescript run tts:save
 ```
 
-Output is raw mono 24 kHz signed little-endian PCM16, with no WAV header.
-The default model is Coda. Select Mist v3 with `new Rime({ model: "mistv3" })`.
+Open `examples/typescript/speech.wav` in your audio player. To hear streamed text
+as it arrives, run `npm --prefix examples/typescript run tts:play`, open the printed
+local URL, and press **Start**. **Stop** cancels generation and playback.
 
-For streamed text, voices, audio formats, and cancellation, read the
-[TTS guide](https://github.com/rimelabs/rime-sdk/blob/main/typescript/docs/tts.md).
-Runnable scripts are in the [examples](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md).
+Replace the example's async text source with your LLM's text stream. The SDK
+handles sentence boundaries. Coda is the default; select Mist v3 with
+`new Rime({ model: "mistv3" })`.
+The [TTS guide](https://github.com/rimelabs/rime-sdk/blob/main/typescript/docs/tts.md)
+covers voices, formats, and cancellation.
 
 ## Prism quick start
 
-Set `PRISM_URL` to your deployment's full `wss://host/v1/realtime` endpoint.
-Supply `PRISM_VOICE` unless the deployment has a default voice.
-
-```javascript
-import { Rime, RimeRealtimeError } from "@rimelabs/sdk";
-
-const client = new Rime();
-const deadline = setTimeout(() => void client.close(), 60_000);
-let reading;
-try {
-  const session = await client.realtime.connect({
-    endpoint: process.env.PRISM_URL,
-    voice: process.env.PRISM_VOICE,
-  });
-  reading = (async () => {
-    for await (const { payload } of session.events) {
-      if (payload.kind === "text.delta") process.stdout.write(payload.delta);
-      if (payload.kind === "error") throw new RimeRealtimeError(payload.error);
-      if (payload.kind === "response.ended") {
-        if (payload.status !== "completed")
-          throw new Error(`Response ${payload.status}`);
-        return;
-      }
-    }
-    throw new Error("Session closed before the response ended");
-  })();
-  await Promise.all([reading, session.sendText("Hello!")]);
-} finally {
-  clearTimeout(deadline);
-  await client.close();
-  await reading?.catch(() => {});
-}
+Start a voice conversation in your browser. The Node.js server uses the SDK;
+the browser captures your microphone and plays replies. Use headphones, and
+speak during a reply to interrupt it. The API key stays on the local server.
+
+Set `PRISM_URL` to your deployment's full WebSocket URL ending in `/v1/realtime`.
+Set `PRISM_VOICE` unless that deployment has a default. Obtain these values from
+your deployment operator; the TTS endpoint does not serve Prism.
+
+After the [example setup](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md#nodejs), run from the repository root:
+
+```sh
+npm --prefix examples/typescript run prism:voice
+```
+
+Open the printed local URL and press **Start**. Without a microphone, send the
+included speech recording and save `reply.wav`:
+
+```sh
+npm --prefix examples/typescript run prism:recorded
 ```
 
-This example prints text and discards audio. The
-[Realtime guide](https://github.com/rimelabs/rime-sdk/blob/main/typescript/docs/realtime.md)
-covers audio input, tools, playback reports, and cancellation. Runnable
-[Prism examples](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md#nodejs)
-save audio and handle tools. TTS settings do not apply to Prism sessions.
+Run `prism:voice-tools` for the same conversation with a demo order lookup.
+The [Realtime guide](https://github.com/rimelabs/rime-sdk/blob/main/typescript/docs/realtime.md)
+covers audio, tools, playback reports, errors, and optional typed input.
+TTS settings do not configure Prism sessions.
 
 ## License
 

package/docs/realtime.md

@@ -4,10 +4,16 @@ Keep one event consumer running while your application sends input, runs tools,
 and plays audio. The SDK manages the protocol state. Your application owns
 microphone capture, tool execution, and playback.
 
-Start with the [package quick start](../README.md#prism-quick-start), or run the
-[typed-turn example](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/realtime/typed-turn.mjs).
-The [example setup](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md#nodejs)
-lists the commands and environment variables. This API requires Node.js 22 or later.
+Start with the [voice conversation](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/realtime/voice.ts)
+for microphone input, playback, and caller interruption. The
+[recorded-speech example](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/realtime/recorded.ts)
+saves a spoken reply without audio hardware. See the
+[example setup](https://github.com/rimelabs/rime-sdk/blob/main/examples/README.md)
+for commands, device requirements, and the voice tool example.
+
+Typed turns remain useful for connection checks and mixed text/voice applications.
+The live examples keep the session open after normal cancellation and report
+playback from the output clock. Saving a file is not playback.
 
 ## Connect
 
@@ -174,8 +180,8 @@ nonnegative milliseconds. The SDK waits for generation completion and supplies
 the server's drain token.
 
 Saving audio does not establish playback. Reports are optional. If you cannot
-measure playback, omit them and let the server use its estimate. The examples
-have no player and omit these reports.
+measure playback, omit them and let the server use its estimate. The recorded and typed examples have no player and omit these reports.
+The voice examples report actual playback.
 
 ## Timeouts and failures
 
@@ -185,8 +191,8 @@ tool readiness, and waiting for generation to end before a playback report.
 Once a request is submitted, `requestS` bounds its write and acknowledgment.
 
 These limits do not bound the entire conversation or generation after creation.
-Set an application deadline and close the session when it expires. Both examples
-use a 60-second deadline.
+Set an application deadline and close the session when it expires. The recorded and typed examples use a 60-second deadline. Voice conversations
+run until stopped or the connection fails.
 
 `RealtimeAdmissionTimeout` means readiness expired with no request outstanding;
 the session remains usable. An unknown request outcome closes the connection and

package/docs/tts.md

@@ -4,6 +4,10 @@ You supply text; the SDK handles sentence boundaries and streams audio back.
 Your application owns playback. Start with the [package quick start](../README.md),
 or run the [streaming example](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/tts/stream.mjs).
 
+For a playable file, use [save speech](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/tts/save.ts).
+For immediate playback and cancellation, use [stream and play](https://github.com/rimelabs/rime-sdk/blob/main/examples/typescript/tts/play.ts).
+Both accept the same SDK text stream; device dependencies stay in the examples.
+
 ## Stream incoming text
 
 An async text source can supply text as it arrives:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rimelabs/sdk",
-  "version": "0.1.0-alpha.6",
+  "version": "0.1.0-alpha.8",
   "description": "Rime streaming TTS and Prism realtime SDK for Node.js",
   "license": "MIT",
   "repository": {
@@ -34,7 +34,7 @@
     "check": "tsc -p tsconfig.json --noEmit",
     "test": "npm run build && node --test tests/*.test.mjs",
     "prepack": "npm run build",
-    "lint": "prettier --check src tests ../examples/typescript/tts ../examples/typescript/realtime"
+    "lint": "prettier --check src tests ../examples/typescript/tts ../examples/typescript/realtime ../examples/typescript/common ../examples/typescript/browser ../examples/typescript/tests"
   },
   "dependencies": {
     "@bufbuild/protobuf": "^2.11.0",