diff --git a/types/google-cloud__text-to-speech/google-cloud__text-to-speech-tests.ts b/types/google-cloud__text-to-speech/google-cloud__text-to-speech-tests.ts
new file mode 100644
index 0000000000..79c368c8e3
--- /dev/null
+++ b/types/google-cloud__text-to-speech/google-cloud__text-to-speech-tests.ts
@@ -0,0 +1,56 @@
+import textToSpeech from "@google-cloud/text-to-speech";
+
+const client = new textToSpeech.TextToSpeechClient({});
+
+/* listVoices */
+
+client.listVoices({});
+
+client.listVoices({}, (err, res) => {
+    if (res) {
+        res.map(voice =>
+            console.log(
+                voice.language_codes,
+                voice.name,
+                voice.naturalSampleRateHertz,
+                voice.ssmlGender
+            )
+        );
+    }
+});
+
+client.listVoices({ languageCode: "en-GB" }).then(res => {
+    res[0].map(voice =>
+        console.log(
+            voice.language_codes,
+            voice.name,
+            voice.naturalSampleRateHertz,
+            voice.ssmlGender
+        )
+    );
+});
+
+/* synthesizeSpeech */
+
+client.synthesizeSpeech(
+    {
+        input: { text: "Hello world." },
+        audioConfig: { audioEncoding: "MP3" },
+        voice: { name: "Alice" }
+    },
+    (err, res) => {
+        if (res) {
+            console.log(res.audioContent);
+        }
+    }
+);
+
+client
+    .synthesizeSpeech({
+        input: { ssml: "Hello world." },
+        audioConfig: { audioEncoding: "OGG_OPUS" },
+        voice: { name: "Bob", languageCode: "en-GB" }
+    })
+    .then(res => {
+        console.log(res[0].audioContent);
+    });
diff --git a/types/google-cloud__text-to-speech/index.d.ts b/types/google-cloud__text-to-speech/index.d.ts
new file mode 100644
index 0000000000..9e0c80cac2
--- /dev/null
+++ b/types/google-cloud__text-to-speech/index.d.ts
@@ -0,0 +1,123 @@
+// Type definitions for google-cloud__text-to-speech 0.5
+// Project: https://github.com/googleapis/nodejs-text-to-speech
+// Definitions by: Ben James <https://github.com/benhjames>
+// Definitions: https://github.com/DefinitelyTyped/DefinitelyTyped
+
+// TypeScript Version: 2.8
+
+/// <reference types="node" />
+
+export type GoogleError = any;
+
+export type APICallback<T = any> = (
+    err: GoogleError | null,
+    response?: T
+) => void;
+
+export interface PromiseLike<T> extends Promise<T> {
+    /**
+     * Cancel the ongoing promise
+     */
+    cancel(): void;
+}
+
+export interface MethodOverload<T, R> {
+    (data: T, options?: CallOptions): PromiseLike<[R]>;
+    (data: T, options: CallOptions, callback: APICallback<R>): void;
+    (data: T, callback: APICallback<R>): void;
+}
+
+export interface CallOptions {
+    timeout?: number;
+    retry?: any;
+    autoPaginate?: boolean;
+    pageToken?: any;
+    isBundling: boolean;
+    longrunning?: any;
+    promise?: any;
+}
+
+export interface ClientOptionsCredentials {
+    client_email: string;
+    private_key: string;
+}
+
+export interface ClientOptions {
+    credentials?: ClientOptionsCredentials;
+    email?: string;
+    keyFilename?: string;
+    port?: number;
+    projectId?: string;
+    promise?: any;
+    servicePath?: string;
+}
+
+export interface ListVoicesRequest {
+    languageCode?: string;
+}
+
+export type ListVoicesOptions = CallOptions;
+
+export type SsmlVoiceGender =
+    | "SSML_VOICE_GENDER_UNSPECIFIED"
+    | "MALE"
+    | "FEMALE"
+    | "NEUTRAL";
+
+export interface Voice {
+    language_codes: string[];
+    name: string;
+    ssmlGender: SsmlVoiceGender;
+    naturalSampleRateHertz: number;
+}
+
+export type ListVoicesResponse = Voice[];
+
+export type SynthesisInput = { text: string } | { ssml: string };
+
+export interface VoiceSelectionParams {
+    languageCode?: string;
+    name?: string;
+    ssmlGender?: SsmlVoiceGender;
+}
+
+export type AudioEncoding =
+    | "AUDIO_ENCODING_UNSPECIFIED"
+    | "LINEAR16"
+    | "MP3"
+    | "OGG_OPUS";
+
+export interface AudioConfig {
+    audioEncoding: AudioEncoding;
+    effectsProfileId?: string[];
+    pitch?: number;
+    sampleRateHertz?: number;
+    speakingRate?: number;
+    volumeGainDb?: number;
+}
+
+export interface SynthesizeSpeechRequest {
+    input: SynthesisInput;
+    voice: VoiceSelectionParams;
+    audioConfig: AudioConfig;
+}
+
+export type SynthesizeSpeechOptions = CallOptions;
+
+export interface SynthesizeSpeechResponse {
+    audioContent: Buffer;
+}
+
+declare class TextToSpeechClient {
+    constructor(options?: ClientOptions);
+
+    listVoices: MethodOverload<ListVoicesRequest, ListVoicesResponse>;
+    synthesizeSpeech: MethodOverload<
+        SynthesizeSpeechRequest,
+        SynthesizeSpeechResponse
+    >;
+}
+
+declare const TextToSpeech: { TextToSpeechClient: typeof TextToSpeechClient };
+
+export default TextToSpeech;
diff --git a/types/google-cloud__text-to-speech/tsconfig.json b/types/google-cloud__text-to-speech/tsconfig.json
new file mode 100644
index 0000000000..a682d930a1
--- /dev/null
+++ b/types/google-cloud__text-to-speech/tsconfig.json
@@ -0,0 +1,19 @@
+{
+    "compilerOptions": {
+        "module": "commonjs",
+        "lib": ["es6"],
+        "noImplicitAny": true,
+        "noImplicitThis": true,
+        "strictFunctionTypes": true,
+        "strictNullChecks": true,
+        "baseUrl": "../",
+        "typeRoots": ["../"],
+        "types": [],
+        "noEmit": true,
+        "forceConsistentCasingInFileNames": true,
+        "paths": {
+            "@google-cloud/text-to-speech": ["google-cloud__text-to-speech"]
+        }
+    },
+    "files": ["index.d.ts", "google-cloud__text-to-speech-tests.ts"]
+}
diff --git a/types/google-cloud__text-to-speech/tslint.json b/types/google-cloud__text-to-speech/tslint.json
new file mode 100644
index 0000000000..3db14f85ea
--- /dev/null
+++ b/types/google-cloud__text-to-speech/tslint.json
@@ -0,0 +1 @@
+{ "extends": "dtslint/dt.json" }