sarvamai 1.1.2 → 1.1.3-alpha.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/cjs/BaseClient.js +2 -2
- package/dist/cjs/api/resources/textToSpeech/client/Client.d.ts +3 -3
- package/dist/cjs/api/resources/textToSpeech/client/Client.js +3 -3
- package/dist/cjs/api/resources/textToSpeech/client/requests/TextToSpeechRequest.d.ts +13 -15
- package/dist/cjs/api/resources/textToSpeechStreaming/types/TextToSpeechStreamingModel.d.ts +2 -2
- package/dist/cjs/api/resources/textToSpeechStreaming/types/TextToSpeechStreamingModel.js +2 -2
- package/dist/cjs/api/types/ConfigureConnection.d.ts +29 -19
- package/dist/cjs/api/types/ConfigureConnection.js +18 -4
- package/dist/cjs/api/types/TextToSpeechModel.d.ts +1 -1
- package/dist/cjs/api/types/TextToSpeechModel.js +1 -1
- package/dist/cjs/api/types/TextToSpeechSpeaker.d.ts +14 -0
- package/dist/cjs/api/types/TextToSpeechSpeaker.js +14 -0
- package/dist/cjs/version.d.ts +1 -1
- package/dist/cjs/version.js +1 -1
- package/dist/esm/BaseClient.mjs +2 -2
- package/dist/esm/api/resources/textToSpeech/client/Client.d.mts +3 -3
- package/dist/esm/api/resources/textToSpeech/client/Client.mjs +3 -3
- package/dist/esm/api/resources/textToSpeech/client/requests/TextToSpeechRequest.d.mts +13 -15
- package/dist/esm/api/resources/textToSpeechStreaming/types/TextToSpeechStreamingModel.d.mts +2 -2
- package/dist/esm/api/resources/textToSpeechStreaming/types/TextToSpeechStreamingModel.mjs +2 -2
- package/dist/esm/api/types/ConfigureConnection.d.mts +29 -19
- package/dist/esm/api/types/ConfigureConnection.mjs +18 -4
- package/dist/esm/api/types/TextToSpeechModel.d.mts +1 -1
- package/dist/esm/api/types/TextToSpeechModel.mjs +1 -1
- package/dist/esm/api/types/TextToSpeechSpeaker.d.mts +14 -0
- package/dist/esm/api/types/TextToSpeechSpeaker.mjs +14 -0
- package/dist/esm/version.d.mts +1 -1
- package/dist/esm/version.mjs +1 -1
- package/package.json +1 -1
- package/reference.md +3 -3
package/dist/cjs/BaseClient.js
CHANGED
|
@@ -43,8 +43,8 @@ function normalizeClientOptions(options) {
|
|
|
43
43
|
const headers = (0, headers_js_1.mergeHeaders)({
|
|
44
44
|
"X-Fern-Language": "JavaScript",
|
|
45
45
|
"X-Fern-SDK-Name": "sarvamai",
|
|
46
|
-
"X-Fern-SDK-Version": "1.1.
|
|
47
|
-
"User-Agent": "sarvamai/1.1.
|
|
46
|
+
"X-Fern-SDK-Version": "1.1.3-alpha.1",
|
|
47
|
+
"User-Agent": "sarvamai/1.1.3-alpha.1",
|
|
48
48
|
"X-Fern-Runtime": core.RUNTIME.type,
|
|
49
49
|
"X-Fern-Runtime-Version": core.RUNTIME.version,
|
|
50
50
|
}, options === null || options === void 0 ? void 0 : options.headers);
|
|
@@ -16,14 +16,14 @@ export declare class TextToSpeechClient {
|
|
|
16
16
|
*
|
|
17
17
|
* **Available Models:**
|
|
18
18
|
* - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
|
|
19
|
-
* - **bulbul:v3
|
|
19
|
+
* - **bulbul:v3**: Newer model with improved quality
|
|
20
20
|
*
|
|
21
|
-
* **Important Notes for bulbul:v3
|
|
21
|
+
* **Important Notes for bulbul:v3:**
|
|
22
22
|
* - Pitch and loudness parameters are NOT supported
|
|
23
23
|
* - Pace must be between 0.5 and 2.0
|
|
24
24
|
* - Preprocessing is automatically enabled
|
|
25
25
|
* - Default sample rate is 24000 Hz
|
|
26
|
-
* -
|
|
26
|
+
* - Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz
|
|
27
27
|
*
|
|
28
28
|
* @param {SarvamAI.TextToSpeechRequest} request
|
|
29
29
|
* @param {TextToSpeechClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -59,14 +59,14 @@ class TextToSpeechClient {
|
|
|
59
59
|
*
|
|
60
60
|
* **Available Models:**
|
|
61
61
|
* - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
|
|
62
|
-
* - **bulbul:v3
|
|
62
|
+
* - **bulbul:v3**: Newer model with improved quality
|
|
63
63
|
*
|
|
64
|
-
* **Important Notes for bulbul:v3
|
|
64
|
+
* **Important Notes for bulbul:v3:**
|
|
65
65
|
* - Pitch and loudness parameters are NOT supported
|
|
66
66
|
* - Pace must be between 0.5 and 2.0
|
|
67
67
|
* - Preprocessing is automatically enabled
|
|
68
68
|
* - Default sample rate is 24000 Hz
|
|
69
|
-
* -
|
|
69
|
+
* - Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz
|
|
70
70
|
*
|
|
71
71
|
* @param {SarvamAI.TextToSpeechRequest} request
|
|
72
72
|
* @param {TextToSpeechClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -15,26 +15,26 @@ export interface TextToSpeechRequest {
|
|
|
15
15
|
*
|
|
16
16
|
* **Model-specific limits:**
|
|
17
17
|
* - **bulbul:v2:** Max 1500 characters
|
|
18
|
-
* - **bulbul:v3
|
|
18
|
+
* - **bulbul:v3:** Max 2500 characters
|
|
19
19
|
*
|
|
20
20
|
* **Important Note:**
|
|
21
21
|
* - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
|
|
22
22
|
* - This ensures proper pronunciation as a whole number
|
|
23
23
|
*/
|
|
24
24
|
text: string;
|
|
25
|
-
/** The language
|
|
25
|
+
/** The language code in BCP-47 format. This parameter is primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
26
26
|
target_language_code: SarvamAI.TextToSpeechLanguage;
|
|
27
27
|
/**
|
|
28
28
|
* The speaker voice to be used for the output audio.
|
|
29
29
|
*
|
|
30
|
-
* **Default:** Anushka (for bulbul:v2),
|
|
30
|
+
* **Default:** Anushka (for bulbul:v2), Shubh (for bulbul:v3)
|
|
31
31
|
*
|
|
32
32
|
* **Model Compatibility (Speakers compatible with respective model):**
|
|
33
33
|
* - **bulbul:v2:**
|
|
34
34
|
* - Female: Anushka, Manisha, Vidya, Arya
|
|
35
35
|
* - Male: Abhilash, Karun, Hitesh
|
|
36
|
-
* - **bulbul:v3
|
|
37
|
-
* - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan,
|
|
36
|
+
* - **bulbul:v3:**
|
|
37
|
+
* - Shubh (default), Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Ashutosh, Advait, Amelia, Sophia, Anand, Tanya, Tarun, Sunny, Mani, Gokul, Vijay, Shruti, Suhani, Mohit, Kavitha, Rehan, Soham, Rupali
|
|
38
38
|
*
|
|
39
39
|
* **Note:** Speaker selection must match the chosen model version.
|
|
40
40
|
*/
|
|
@@ -42,7 +42,7 @@ export interface TextToSpeechRequest {
|
|
|
42
42
|
/**
|
|
43
43
|
* Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
|
|
44
44
|
*
|
|
45
|
-
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3
|
|
45
|
+
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3 and will cause a validation error if provided.
|
|
46
46
|
*/
|
|
47
47
|
pitch?: number;
|
|
48
48
|
/**
|
|
@@ -50,21 +50,19 @@ export interface TextToSpeechRequest {
|
|
|
50
50
|
*
|
|
51
51
|
* **Model-specific ranges:**
|
|
52
52
|
* - **bulbul:v2:** 0.3 to 3.0
|
|
53
|
-
* - **bulbul:v3
|
|
53
|
+
* - **bulbul:v3:** 0.5 to 2.0
|
|
54
54
|
*/
|
|
55
55
|
pace?: number;
|
|
56
56
|
/**
|
|
57
57
|
* Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
|
|
58
58
|
*
|
|
59
|
-
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3
|
|
59
|
+
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3 and will cause a validation error if provided.
|
|
60
60
|
*/
|
|
61
61
|
loudness?: number;
|
|
62
62
|
/**
|
|
63
|
-
* Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
|
|
63
|
+
* Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
64
64
|
*
|
|
65
|
-
* **
|
|
66
|
-
* - **bulbul:v2:** Default is 22050 Hz
|
|
67
|
-
* - **bulbul:v3-beta:** Default is 24000 Hz
|
|
65
|
+
* **Default:** 24000 Hz
|
|
68
66
|
*/
|
|
69
67
|
speech_sample_rate?: SarvamAI.SpeechSampleRate;
|
|
70
68
|
/**
|
|
@@ -72,7 +70,7 @@ export interface TextToSpeechRequest {
|
|
|
72
70
|
*
|
|
73
71
|
* **Model-specific behavior:**
|
|
74
72
|
* - **bulbul:v2:** Default is false
|
|
75
|
-
* - **bulbul:v3
|
|
73
|
+
* - **bulbul:v3:** Automatically enabled (true) and cannot be disabled
|
|
76
74
|
*/
|
|
77
75
|
enable_preprocessing?: boolean;
|
|
78
76
|
/**
|
|
@@ -80,7 +78,7 @@ export interface TextToSpeechRequest {
|
|
|
80
78
|
*
|
|
81
79
|
* **Available models:**
|
|
82
80
|
* - **bulbul:v2:** Default model with pitch, loudness controls
|
|
83
|
-
* - **bulbul:v3
|
|
81
|
+
* - **bulbul:v3:** Newer model with improved quality
|
|
84
82
|
*/
|
|
85
83
|
model?: SarvamAI.TextToSpeechModel;
|
|
86
84
|
/** Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics. */
|
|
@@ -88,7 +86,7 @@ export interface TextToSpeechRequest {
|
|
|
88
86
|
/**
|
|
89
87
|
* Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
|
|
90
88
|
*
|
|
91
|
-
* **Note:** This parameter is only supported for bulbul:v3
|
|
89
|
+
* **Note:** This parameter is only supported for bulbul:v3. It has no effect on bulbul:v2.
|
|
92
90
|
*/
|
|
93
91
|
temperature?: number;
|
|
94
92
|
}
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
/**
|
|
2
2
|
* Text to speech model to use.
|
|
3
3
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
4
|
-
* - **bulbul:v3
|
|
4
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
5
5
|
*/
|
|
6
6
|
export declare const TextToSpeechStreamingModel: {
|
|
7
7
|
readonly BulbulV2: "bulbul:v2";
|
|
8
|
-
readonly
|
|
8
|
+
readonly BulbulV3: "bulbul:v3";
|
|
9
9
|
};
|
|
10
10
|
export type TextToSpeechStreamingModel = (typeof TextToSpeechStreamingModel)[keyof typeof TextToSpeechStreamingModel];
|
|
@@ -5,9 +5,9 @@ exports.TextToSpeechStreamingModel = void 0;
|
|
|
5
5
|
/**
|
|
6
6
|
* Text to speech model to use.
|
|
7
7
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
8
|
-
* - **bulbul:v3
|
|
8
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
9
9
|
*/
|
|
10
10
|
exports.TextToSpeechStreamingModel = {
|
|
11
11
|
BulbulV2: "bulbul:v2",
|
|
12
|
-
|
|
12
|
+
BulbulV3: "bulbul:v3",
|
|
13
13
|
};
|
|
@@ -6,7 +6,7 @@
|
|
|
6
6
|
*
|
|
7
7
|
* **Model-Specific Notes:**
|
|
8
8
|
* - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
|
|
9
|
-
* - **bulbul:v3
|
|
9
|
+
* - **bulbul:v3:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Default sample rate: 24000 Hz. Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
10
10
|
*/
|
|
11
11
|
export interface ConfigureConnection {
|
|
12
12
|
type: "config";
|
|
@@ -17,17 +17,17 @@ export declare namespace ConfigureConnection {
|
|
|
17
17
|
/**
|
|
18
18
|
* Specifies the model to use for text-to-speech conversion.
|
|
19
19
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
20
|
-
* - **bulbul:v3
|
|
20
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
21
21
|
*/
|
|
22
22
|
model?: Data.Model;
|
|
23
|
-
/** The language
|
|
23
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
24
24
|
target_language_code: Data.TargetLanguageCode;
|
|
25
25
|
/**
|
|
26
26
|
* The speaker voice to be used for the output audio.
|
|
27
27
|
*
|
|
28
28
|
* **Model Compatibility:**
|
|
29
29
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
30
|
-
* - **bulbul:v3
|
|
30
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
31
31
|
*
|
|
32
32
|
* **Note:** Speaker selection must match the chosen model version.
|
|
33
33
|
*/
|
|
@@ -37,7 +37,7 @@ export declare namespace ConfigureConnection {
|
|
|
37
37
|
* while higher values make it sharper. The suitable range is between -0.75
|
|
38
38
|
* and 0.75. Default is 0.0.
|
|
39
39
|
*
|
|
40
|
-
* **Note:** NOT supported for bulbul:v3
|
|
40
|
+
* **Note:** NOT supported for bulbul:v3. Will be ignored if provided.
|
|
41
41
|
*/
|
|
42
42
|
pitch?: number;
|
|
43
43
|
/**
|
|
@@ -46,7 +46,7 @@ export declare namespace ConfigureConnection {
|
|
|
46
46
|
*
|
|
47
47
|
* **Model-specific ranges:**
|
|
48
48
|
* - **bulbul:v2:** 0.3 to 3.0
|
|
49
|
-
* - **bulbul:v3
|
|
49
|
+
* - **bulbul:v3:** 0.5 to 2.0
|
|
50
50
|
*/
|
|
51
51
|
pace?: number;
|
|
52
52
|
/**
|
|
@@ -54,7 +54,7 @@ export declare namespace ConfigureConnection {
|
|
|
54
54
|
* while higher values make it louder. The suitable range is between 0.3
|
|
55
55
|
* and 3.0. Default is 1.0.
|
|
56
56
|
*
|
|
57
|
-
* **Note:** NOT supported for bulbul:v3
|
|
57
|
+
* **Note:** NOT supported for bulbul:v3. Will be ignored if provided.
|
|
58
58
|
*/
|
|
59
59
|
loudness?: number;
|
|
60
60
|
/**
|
|
@@ -62,16 +62,14 @@ export declare namespace ConfigureConnection {
|
|
|
62
62
|
* focused and deterministic, while higher values make it more random.
|
|
63
63
|
* The suitable range is between 0.01 and 1.0. Default is 0.6.
|
|
64
64
|
*
|
|
65
|
-
* **Note:** Only supported for bulbul:v3
|
|
65
|
+
* **Note:** Only supported for bulbul:v3. Will be ignored for bulbul:v2.
|
|
66
66
|
*/
|
|
67
67
|
temperature?: number;
|
|
68
68
|
/**
|
|
69
69
|
* Specifies the sample rate of the output audio. Supported values are
|
|
70
|
-
* 8000, 16000, 22050, 24000 Hz.
|
|
70
|
+
* 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
71
71
|
*
|
|
72
|
-
* **
|
|
73
|
-
* - **bulbul:v2:** 22050 Hz
|
|
74
|
-
* - **bulbul:v3-beta:** 24000 Hz
|
|
72
|
+
* **Default:** 24000 Hz
|
|
75
73
|
*/
|
|
76
74
|
speech_sample_rate?: number;
|
|
77
75
|
/**
|
|
@@ -79,9 +77,7 @@ export declare namespace ConfigureConnection {
|
|
|
79
77
|
* (e.g., numbers, dates) is performed. Set to true for better handling
|
|
80
78
|
* of mixed-language text.
|
|
81
79
|
*
|
|
82
|
-
* **
|
|
83
|
-
* - **bulbul:v2:** false (optional)
|
|
84
|
-
* - **bulbul:v3-beta:** Always enabled (cannot be disabled)
|
|
80
|
+
* **Note:** Only supported for bulbul:v2. Not applicable for bulbul:v3.
|
|
85
81
|
*/
|
|
86
82
|
enable_preprocessing?: boolean;
|
|
87
83
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
@@ -97,14 +93,14 @@ export declare namespace ConfigureConnection {
|
|
|
97
93
|
/**
|
|
98
94
|
* Specifies the model to use for text-to-speech conversion.
|
|
99
95
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
100
|
-
* - **bulbul:v3
|
|
96
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
101
97
|
*/
|
|
102
98
|
const Model: {
|
|
103
99
|
readonly BulbulV2: "bulbul:v2";
|
|
104
|
-
readonly
|
|
100
|
+
readonly BulbulV3: "bulbul:v3";
|
|
105
101
|
};
|
|
106
102
|
type Model = (typeof Model)[keyof typeof Model];
|
|
107
|
-
/** The language
|
|
103
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
108
104
|
const TargetLanguageCode: {
|
|
109
105
|
readonly BnIn: "bn-IN";
|
|
110
106
|
readonly EnIn: "en-IN";
|
|
@@ -124,7 +120,7 @@ export declare namespace ConfigureConnection {
|
|
|
124
120
|
*
|
|
125
121
|
* **Model Compatibility:**
|
|
126
122
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
127
|
-
* - **bulbul:v3
|
|
123
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
128
124
|
*
|
|
129
125
|
* **Note:** Speaker selection must match the chosen model version.
|
|
130
126
|
*/
|
|
@@ -161,6 +157,20 @@ export declare namespace ConfigureConnection {
|
|
|
161
157
|
readonly Advait: "advait";
|
|
162
158
|
readonly Amelia: "amelia";
|
|
163
159
|
readonly Sophia: "sophia";
|
|
160
|
+
readonly Anand: "anand";
|
|
161
|
+
readonly Tanya: "tanya";
|
|
162
|
+
readonly Tarun: "tarun";
|
|
163
|
+
readonly Sunny: "sunny";
|
|
164
|
+
readonly Mani: "mani";
|
|
165
|
+
readonly Gokul: "gokul";
|
|
166
|
+
readonly Vijay: "vijay";
|
|
167
|
+
readonly Shruti: "shruti";
|
|
168
|
+
readonly Suhani: "suhani";
|
|
169
|
+
readonly Mohit: "mohit";
|
|
170
|
+
readonly Kavitha: "kavitha";
|
|
171
|
+
readonly Rehan: "rehan";
|
|
172
|
+
readonly Soham: "soham";
|
|
173
|
+
readonly Rupali: "rupali";
|
|
164
174
|
};
|
|
165
175
|
type Speaker = (typeof Speaker)[keyof typeof Speaker];
|
|
166
176
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
@@ -9,13 +9,13 @@ var ConfigureConnection;
|
|
|
9
9
|
/**
|
|
10
10
|
* Specifies the model to use for text-to-speech conversion.
|
|
11
11
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
12
|
-
* - **bulbul:v3
|
|
12
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
13
13
|
*/
|
|
14
14
|
Data.Model = {
|
|
15
15
|
BulbulV2: "bulbul:v2",
|
|
16
|
-
|
|
16
|
+
BulbulV3: "bulbul:v3",
|
|
17
17
|
};
|
|
18
|
-
/** The language
|
|
18
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
19
19
|
Data.TargetLanguageCode = {
|
|
20
20
|
BnIn: "bn-IN",
|
|
21
21
|
EnIn: "en-IN",
|
|
@@ -34,7 +34,7 @@ var ConfigureConnection;
|
|
|
34
34
|
*
|
|
35
35
|
* **Model Compatibility:**
|
|
36
36
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
37
|
-
* - **bulbul:v3
|
|
37
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
38
38
|
*
|
|
39
39
|
* **Note:** Speaker selection must match the chosen model version.
|
|
40
40
|
*/
|
|
@@ -71,6 +71,20 @@ var ConfigureConnection;
|
|
|
71
71
|
Advait: "advait",
|
|
72
72
|
Amelia: "amelia",
|
|
73
73
|
Sophia: "sophia",
|
|
74
|
+
Anand: "anand",
|
|
75
|
+
Tanya: "tanya",
|
|
76
|
+
Tarun: "tarun",
|
|
77
|
+
Sunny: "sunny",
|
|
78
|
+
Mani: "mani",
|
|
79
|
+
Gokul: "gokul",
|
|
80
|
+
Vijay: "vijay",
|
|
81
|
+
Shruti: "shruti",
|
|
82
|
+
Suhani: "suhani",
|
|
83
|
+
Mohit: "mohit",
|
|
84
|
+
Kavitha: "kavitha",
|
|
85
|
+
Rehan: "rehan",
|
|
86
|
+
Soham: "soham",
|
|
87
|
+
Rupali: "rupali",
|
|
74
88
|
};
|
|
75
89
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
76
90
|
Data.OutputAudioCodec = {
|
|
@@ -31,5 +31,19 @@ export declare const TextToSpeechSpeaker: {
|
|
|
31
31
|
readonly Advait: "advait";
|
|
32
32
|
readonly Amelia: "amelia";
|
|
33
33
|
readonly Sophia: "sophia";
|
|
34
|
+
readonly Anand: "anand";
|
|
35
|
+
readonly Tanya: "tanya";
|
|
36
|
+
readonly Tarun: "tarun";
|
|
37
|
+
readonly Sunny: "sunny";
|
|
38
|
+
readonly Mani: "mani";
|
|
39
|
+
readonly Gokul: "gokul";
|
|
40
|
+
readonly Vijay: "vijay";
|
|
41
|
+
readonly Shruti: "shruti";
|
|
42
|
+
readonly Suhani: "suhani";
|
|
43
|
+
readonly Mohit: "mohit";
|
|
44
|
+
readonly Kavitha: "kavitha";
|
|
45
|
+
readonly Rehan: "rehan";
|
|
46
|
+
readonly Soham: "soham";
|
|
47
|
+
readonly Rupali: "rupali";
|
|
34
48
|
};
|
|
35
49
|
export type TextToSpeechSpeaker = (typeof TextToSpeechSpeaker)[keyof typeof TextToSpeechSpeaker];
|
|
@@ -35,4 +35,18 @@ exports.TextToSpeechSpeaker = {
|
|
|
35
35
|
Advait: "advait",
|
|
36
36
|
Amelia: "amelia",
|
|
37
37
|
Sophia: "sophia",
|
|
38
|
+
Anand: "anand",
|
|
39
|
+
Tanya: "tanya",
|
|
40
|
+
Tarun: "tarun",
|
|
41
|
+
Sunny: "sunny",
|
|
42
|
+
Mani: "mani",
|
|
43
|
+
Gokul: "gokul",
|
|
44
|
+
Vijay: "vijay",
|
|
45
|
+
Shruti: "shruti",
|
|
46
|
+
Suhani: "suhani",
|
|
47
|
+
Mohit: "mohit",
|
|
48
|
+
Kavitha: "kavitha",
|
|
49
|
+
Rehan: "rehan",
|
|
50
|
+
Soham: "soham",
|
|
51
|
+
Rupali: "rupali",
|
|
38
52
|
};
|
package/dist/cjs/version.d.ts
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
export declare const SDK_VERSION = "1.1.
|
|
1
|
+
export declare const SDK_VERSION = "1.1.3-alpha.1";
|
package/dist/cjs/version.js
CHANGED
package/dist/esm/BaseClient.mjs
CHANGED
|
@@ -6,8 +6,8 @@ export function normalizeClientOptions(options) {
|
|
|
6
6
|
const headers = mergeHeaders({
|
|
7
7
|
"X-Fern-Language": "JavaScript",
|
|
8
8
|
"X-Fern-SDK-Name": "sarvamai",
|
|
9
|
-
"X-Fern-SDK-Version": "1.1.
|
|
10
|
-
"User-Agent": "sarvamai/1.1.
|
|
9
|
+
"X-Fern-SDK-Version": "1.1.3-alpha.1",
|
|
10
|
+
"User-Agent": "sarvamai/1.1.3-alpha.1",
|
|
11
11
|
"X-Fern-Runtime": core.RUNTIME.type,
|
|
12
12
|
"X-Fern-Runtime-Version": core.RUNTIME.version,
|
|
13
13
|
}, options === null || options === void 0 ? void 0 : options.headers);
|
|
@@ -16,14 +16,14 @@ export declare class TextToSpeechClient {
|
|
|
16
16
|
*
|
|
17
17
|
* **Available Models:**
|
|
18
18
|
* - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
|
|
19
|
-
* - **bulbul:v3
|
|
19
|
+
* - **bulbul:v3**: Newer model with improved quality
|
|
20
20
|
*
|
|
21
|
-
* **Important Notes for bulbul:v3
|
|
21
|
+
* **Important Notes for bulbul:v3:**
|
|
22
22
|
* - Pitch and loudness parameters are NOT supported
|
|
23
23
|
* - Pace must be between 0.5 and 2.0
|
|
24
24
|
* - Preprocessing is automatically enabled
|
|
25
25
|
* - Default sample rate is 24000 Hz
|
|
26
|
-
* -
|
|
26
|
+
* - Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz
|
|
27
27
|
*
|
|
28
28
|
* @param {SarvamAI.TextToSpeechRequest} request
|
|
29
29
|
* @param {TextToSpeechClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -23,14 +23,14 @@ export class TextToSpeechClient {
|
|
|
23
23
|
*
|
|
24
24
|
* **Available Models:**
|
|
25
25
|
* - **bulbul:v2** (default): Supports pitch, loudness, and pace controls
|
|
26
|
-
* - **bulbul:v3
|
|
26
|
+
* - **bulbul:v3**: Newer model with improved quality
|
|
27
27
|
*
|
|
28
|
-
* **Important Notes for bulbul:v3
|
|
28
|
+
* **Important Notes for bulbul:v3:**
|
|
29
29
|
* - Pitch and loudness parameters are NOT supported
|
|
30
30
|
* - Pace must be between 0.5 and 2.0
|
|
31
31
|
* - Preprocessing is automatically enabled
|
|
32
32
|
* - Default sample rate is 24000 Hz
|
|
33
|
-
* -
|
|
33
|
+
* - Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz
|
|
34
34
|
*
|
|
35
35
|
* @param {SarvamAI.TextToSpeechRequest} request
|
|
36
36
|
* @param {TextToSpeechClient.RequestOptions} requestOptions - Request-specific configuration.
|
|
@@ -15,26 +15,26 @@ export interface TextToSpeechRequest {
|
|
|
15
15
|
*
|
|
16
16
|
* **Model-specific limits:**
|
|
17
17
|
* - **bulbul:v2:** Max 1500 characters
|
|
18
|
-
* - **bulbul:v3
|
|
18
|
+
* - **bulbul:v3:** Max 2500 characters
|
|
19
19
|
*
|
|
20
20
|
* **Important Note:**
|
|
21
21
|
* - For numbers larger than 4 digits, use commas (e.g., '10,000' instead of '10000')
|
|
22
22
|
* - This ensures proper pronunciation as a whole number
|
|
23
23
|
*/
|
|
24
24
|
text: string;
|
|
25
|
-
/** The language
|
|
25
|
+
/** The language code in BCP-47 format. This parameter is primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
26
26
|
target_language_code: SarvamAI.TextToSpeechLanguage;
|
|
27
27
|
/**
|
|
28
28
|
* The speaker voice to be used for the output audio.
|
|
29
29
|
*
|
|
30
|
-
* **Default:** Anushka (for bulbul:v2),
|
|
30
|
+
* **Default:** Anushka (for bulbul:v2), Shubh (for bulbul:v3)
|
|
31
31
|
*
|
|
32
32
|
* **Model Compatibility (Speakers compatible with respective model):**
|
|
33
33
|
* - **bulbul:v2:**
|
|
34
34
|
* - Female: Anushka, Manisha, Vidya, Arya
|
|
35
35
|
* - Male: Abhilash, Karun, Hitesh
|
|
36
|
-
* - **bulbul:v3
|
|
37
|
-
* - Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan,
|
|
36
|
+
* - **bulbul:v3:**
|
|
37
|
+
* - Shubh (default), Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Ashutosh, Advait, Amelia, Sophia, Anand, Tanya, Tarun, Sunny, Mani, Gokul, Vijay, Shruti, Suhani, Mohit, Kavitha, Rehan, Soham, Rupali
|
|
38
38
|
*
|
|
39
39
|
* **Note:** Speaker selection must match the chosen model version.
|
|
40
40
|
*/
|
|
@@ -42,7 +42,7 @@ export interface TextToSpeechRequest {
|
|
|
42
42
|
/**
|
|
43
43
|
* Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0.
|
|
44
44
|
*
|
|
45
|
-
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3
|
|
45
|
+
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3 and will cause a validation error if provided.
|
|
46
46
|
*/
|
|
47
47
|
pitch?: number;
|
|
48
48
|
/**
|
|
@@ -50,21 +50,19 @@ export interface TextToSpeechRequest {
|
|
|
50
50
|
*
|
|
51
51
|
* **Model-specific ranges:**
|
|
52
52
|
* - **bulbul:v2:** 0.3 to 3.0
|
|
53
|
-
* - **bulbul:v3
|
|
53
|
+
* - **bulbul:v3:** 0.5 to 2.0
|
|
54
54
|
*/
|
|
55
55
|
pace?: number;
|
|
56
56
|
/**
|
|
57
57
|
* Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0.
|
|
58
58
|
*
|
|
59
|
-
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3
|
|
59
|
+
* **Note:** This parameter is only supported for bulbul:v2. It is NOT supported for bulbul:v3 and will cause a validation error if provided.
|
|
60
60
|
*/
|
|
61
61
|
loudness?: number;
|
|
62
62
|
/**
|
|
63
|
-
* Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz.
|
|
63
|
+
* Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
64
64
|
*
|
|
65
|
-
* **
|
|
66
|
-
* - **bulbul:v2:** Default is 22050 Hz
|
|
67
|
-
* - **bulbul:v3-beta:** Default is 24000 Hz
|
|
65
|
+
* **Default:** 24000 Hz
|
|
68
66
|
*/
|
|
69
67
|
speech_sample_rate?: SarvamAI.SpeechSampleRate;
|
|
70
68
|
/**
|
|
@@ -72,7 +70,7 @@ export interface TextToSpeechRequest {
|
|
|
72
70
|
*
|
|
73
71
|
* **Model-specific behavior:**
|
|
74
72
|
* - **bulbul:v2:** Default is false
|
|
75
|
-
* - **bulbul:v3
|
|
73
|
+
* - **bulbul:v3:** Automatically enabled (true) and cannot be disabled
|
|
76
74
|
*/
|
|
77
75
|
enable_preprocessing?: boolean;
|
|
78
76
|
/**
|
|
@@ -80,7 +78,7 @@ export interface TextToSpeechRequest {
|
|
|
80
78
|
*
|
|
81
79
|
* **Available models:**
|
|
82
80
|
* - **bulbul:v2:** Default model with pitch, loudness controls
|
|
83
|
-
* - **bulbul:v3
|
|
81
|
+
* - **bulbul:v3:** Newer model with improved quality
|
|
84
82
|
*/
|
|
85
83
|
model?: SarvamAI.TextToSpeechModel;
|
|
86
84
|
/** Specifies the audio codec for the output audio file. Different codecs offer various compression and quality characteristics. */
|
|
@@ -88,7 +86,7 @@ export interface TextToSpeechRequest {
|
|
|
88
86
|
/**
|
|
89
87
|
* Controls the randomness of the output. Lower values make the output more focused and deterministic, while higher values make it more random. The suitable range is between 0.01 and 1.0. Default is 0.6.
|
|
90
88
|
*
|
|
91
|
-
* **Note:** This parameter is only supported for bulbul:v3
|
|
89
|
+
* **Note:** This parameter is only supported for bulbul:v3. It has no effect on bulbul:v2.
|
|
92
90
|
*/
|
|
93
91
|
temperature?: number;
|
|
94
92
|
}
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
/**
|
|
2
2
|
* Text to speech model to use.
|
|
3
3
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
4
|
-
* - **bulbul:v3
|
|
4
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
5
5
|
*/
|
|
6
6
|
export declare const TextToSpeechStreamingModel: {
|
|
7
7
|
readonly BulbulV2: "bulbul:v2";
|
|
8
|
-
readonly
|
|
8
|
+
readonly BulbulV3: "bulbul:v3";
|
|
9
9
|
};
|
|
10
10
|
export type TextToSpeechStreamingModel = (typeof TextToSpeechStreamingModel)[keyof typeof TextToSpeechStreamingModel];
|
|
@@ -2,9 +2,9 @@
|
|
|
2
2
|
/**
|
|
3
3
|
* Text to speech model to use.
|
|
4
4
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
5
|
-
* - **bulbul:v3
|
|
5
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
6
6
|
*/
|
|
7
7
|
export const TextToSpeechStreamingModel = {
|
|
8
8
|
BulbulV2: "bulbul:v2",
|
|
9
|
-
|
|
9
|
+
BulbulV3: "bulbul:v3",
|
|
10
10
|
};
|
|
@@ -6,7 +6,7 @@
|
|
|
6
6
|
*
|
|
7
7
|
* **Model-Specific Notes:**
|
|
8
8
|
* - **bulbul:v2:** Supports pitch, loudness, pace (0.3-3.0). Default sample rate: 22050 Hz.
|
|
9
|
-
* - **bulbul:v3
|
|
9
|
+
* - **bulbul:v3:** Does NOT support pitch/loudness. Pace range: 0.5-2.0. Default sample rate: 24000 Hz. Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
10
10
|
*/
|
|
11
11
|
export interface ConfigureConnection {
|
|
12
12
|
type: "config";
|
|
@@ -17,17 +17,17 @@ export declare namespace ConfigureConnection {
|
|
|
17
17
|
/**
|
|
18
18
|
* Specifies the model to use for text-to-speech conversion.
|
|
19
19
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
20
|
-
* - **bulbul:v3
|
|
20
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
21
21
|
*/
|
|
22
22
|
model?: Data.Model;
|
|
23
|
-
/** The language
|
|
23
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
24
24
|
target_language_code: Data.TargetLanguageCode;
|
|
25
25
|
/**
|
|
26
26
|
* The speaker voice to be used for the output audio.
|
|
27
27
|
*
|
|
28
28
|
* **Model Compatibility:**
|
|
29
29
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
30
|
-
* - **bulbul:v3
|
|
30
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
31
31
|
*
|
|
32
32
|
* **Note:** Speaker selection must match the chosen model version.
|
|
33
33
|
*/
|
|
@@ -37,7 +37,7 @@ export declare namespace ConfigureConnection {
|
|
|
37
37
|
* while higher values make it sharper. The suitable range is between -0.75
|
|
38
38
|
* and 0.75. Default is 0.0.
|
|
39
39
|
*
|
|
40
|
-
* **Note:** NOT supported for bulbul:v3
|
|
40
|
+
* **Note:** NOT supported for bulbul:v3. Will be ignored if provided.
|
|
41
41
|
*/
|
|
42
42
|
pitch?: number;
|
|
43
43
|
/**
|
|
@@ -46,7 +46,7 @@ export declare namespace ConfigureConnection {
|
|
|
46
46
|
*
|
|
47
47
|
* **Model-specific ranges:**
|
|
48
48
|
* - **bulbul:v2:** 0.3 to 3.0
|
|
49
|
-
* - **bulbul:v3
|
|
49
|
+
* - **bulbul:v3:** 0.5 to 2.0
|
|
50
50
|
*/
|
|
51
51
|
pace?: number;
|
|
52
52
|
/**
|
|
@@ -54,7 +54,7 @@ export declare namespace ConfigureConnection {
|
|
|
54
54
|
* while higher values make it louder. The suitable range is between 0.3
|
|
55
55
|
* and 3.0. Default is 1.0.
|
|
56
56
|
*
|
|
57
|
-
* **Note:** NOT supported for bulbul:v3
|
|
57
|
+
* **Note:** NOT supported for bulbul:v3. Will be ignored if provided.
|
|
58
58
|
*/
|
|
59
59
|
loudness?: number;
|
|
60
60
|
/**
|
|
@@ -62,16 +62,14 @@ export declare namespace ConfigureConnection {
|
|
|
62
62
|
* focused and deterministic, while higher values make it more random.
|
|
63
63
|
* The suitable range is between 0.01 and 1.0. Default is 0.6.
|
|
64
64
|
*
|
|
65
|
-
* **Note:** Only supported for bulbul:v3
|
|
65
|
+
* **Note:** Only supported for bulbul:v3. Will be ignored for bulbul:v2.
|
|
66
66
|
*/
|
|
67
67
|
temperature?: number;
|
|
68
68
|
/**
|
|
69
69
|
* Specifies the sample rate of the output audio. Supported values are
|
|
70
|
-
* 8000, 16000, 22050, 24000 Hz.
|
|
70
|
+
* 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz.
|
|
71
71
|
*
|
|
72
|
-
* **
|
|
73
|
-
* - **bulbul:v2:** 22050 Hz
|
|
74
|
-
* - **bulbul:v3-beta:** 24000 Hz
|
|
72
|
+
* **Default:** 24000 Hz
|
|
75
73
|
*/
|
|
76
74
|
speech_sample_rate?: number;
|
|
77
75
|
/**
|
|
@@ -79,9 +77,7 @@ export declare namespace ConfigureConnection {
|
|
|
79
77
|
* (e.g., numbers, dates) is performed. Set to true for better handling
|
|
80
78
|
* of mixed-language text.
|
|
81
79
|
*
|
|
82
|
-
* **
|
|
83
|
-
* - **bulbul:v2:** false (optional)
|
|
84
|
-
* - **bulbul:v3-beta:** Always enabled (cannot be disabled)
|
|
80
|
+
* **Note:** Only supported for bulbul:v2. Not applicable for bulbul:v3.
|
|
85
81
|
*/
|
|
86
82
|
enable_preprocessing?: boolean;
|
|
87
83
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
@@ -97,14 +93,14 @@ export declare namespace ConfigureConnection {
|
|
|
97
93
|
/**
|
|
98
94
|
* Specifies the model to use for text-to-speech conversion.
|
|
99
95
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
100
|
-
* - **bulbul:v3
|
|
96
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
101
97
|
*/
|
|
102
98
|
const Model: {
|
|
103
99
|
readonly BulbulV2: "bulbul:v2";
|
|
104
|
-
readonly
|
|
100
|
+
readonly BulbulV3: "bulbul:v3";
|
|
105
101
|
};
|
|
106
102
|
type Model = (typeof Model)[keyof typeof Model];
|
|
107
|
-
/** The language
|
|
103
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
108
104
|
const TargetLanguageCode: {
|
|
109
105
|
readonly BnIn: "bn-IN";
|
|
110
106
|
readonly EnIn: "en-IN";
|
|
@@ -124,7 +120,7 @@ export declare namespace ConfigureConnection {
|
|
|
124
120
|
*
|
|
125
121
|
* **Model Compatibility:**
|
|
126
122
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
127
|
-
* - **bulbul:v3
|
|
123
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
128
124
|
*
|
|
129
125
|
* **Note:** Speaker selection must match the chosen model version.
|
|
130
126
|
*/
|
|
@@ -161,6 +157,20 @@ export declare namespace ConfigureConnection {
|
|
|
161
157
|
readonly Advait: "advait";
|
|
162
158
|
readonly Amelia: "amelia";
|
|
163
159
|
readonly Sophia: "sophia";
|
|
160
|
+
readonly Anand: "anand";
|
|
161
|
+
readonly Tanya: "tanya";
|
|
162
|
+
readonly Tarun: "tarun";
|
|
163
|
+
readonly Sunny: "sunny";
|
|
164
|
+
readonly Mani: "mani";
|
|
165
|
+
readonly Gokul: "gokul";
|
|
166
|
+
readonly Vijay: "vijay";
|
|
167
|
+
readonly Shruti: "shruti";
|
|
168
|
+
readonly Suhani: "suhani";
|
|
169
|
+
readonly Mohit: "mohit";
|
|
170
|
+
readonly Kavitha: "kavitha";
|
|
171
|
+
readonly Rehan: "rehan";
|
|
172
|
+
readonly Soham: "soham";
|
|
173
|
+
readonly Rupali: "rupali";
|
|
164
174
|
};
|
|
165
175
|
type Speaker = (typeof Speaker)[keyof typeof Speaker];
|
|
166
176
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
@@ -6,13 +6,13 @@ export var ConfigureConnection;
|
|
|
6
6
|
/**
|
|
7
7
|
* Specifies the model to use for text-to-speech conversion.
|
|
8
8
|
* - **bulbul:v2** (default): Standard TTS model with pitch/loudness support
|
|
9
|
-
* - **bulbul:v3
|
|
9
|
+
* - **bulbul:v3**: Advanced model with improved quality (no pitch/loudness)
|
|
10
10
|
*/
|
|
11
11
|
Data.Model = {
|
|
12
12
|
BulbulV2: "bulbul:v2",
|
|
13
|
-
|
|
13
|
+
BulbulV3: "bulbul:v3",
|
|
14
14
|
};
|
|
15
|
-
/** The language
|
|
15
|
+
/** The language code in BCP-47 format. Primarily used by the pre-TTS text normalization model to handle language-specific text processing such as number formatting, abbreviations, and special characters. */
|
|
16
16
|
Data.TargetLanguageCode = {
|
|
17
17
|
BnIn: "bn-IN",
|
|
18
18
|
EnIn: "en-IN",
|
|
@@ -31,7 +31,7 @@ export var ConfigureConnection;
|
|
|
31
31
|
*
|
|
32
32
|
* **Model Compatibility:**
|
|
33
33
|
* - **bulbul:v2:** anushka (default), abhilash, manisha, vidya, arya, karun, hitesh
|
|
34
|
-
* - **bulbul:v3
|
|
34
|
+
* - **bulbul:v3:** shubh (default), aditya, ritu, priya, neha, rahul, pooja, rohan, simran, kavya, amit, dev, ishita, shreya, ratan, varun, manan, sumit, roopa, kabir, aayan, ashutosh, advait, amelia, sophia, anand, tanya, tarun, sunny, mani, gokul, vijay, shruti, suhani, mohit, kavitha, rehan, soham, rupali
|
|
35
35
|
*
|
|
36
36
|
* **Note:** Speaker selection must match the chosen model version.
|
|
37
37
|
*/
|
|
@@ -68,6 +68,20 @@ export var ConfigureConnection;
|
|
|
68
68
|
Advait: "advait",
|
|
69
69
|
Amelia: "amelia",
|
|
70
70
|
Sophia: "sophia",
|
|
71
|
+
Anand: "anand",
|
|
72
|
+
Tanya: "tanya",
|
|
73
|
+
Tarun: "tarun",
|
|
74
|
+
Sunny: "sunny",
|
|
75
|
+
Mani: "mani",
|
|
76
|
+
Gokul: "gokul",
|
|
77
|
+
Vijay: "vijay",
|
|
78
|
+
Shruti: "shruti",
|
|
79
|
+
Suhani: "suhani",
|
|
80
|
+
Mohit: "mohit",
|
|
81
|
+
Kavitha: "kavitha",
|
|
82
|
+
Rehan: "rehan",
|
|
83
|
+
Soham: "soham",
|
|
84
|
+
Rupali: "rupali",
|
|
71
85
|
};
|
|
72
86
|
/** Audio codec (currently supports MP3 only, optimized for real-time playback) */
|
|
73
87
|
Data.OutputAudioCodec = {
|
|
@@ -31,5 +31,19 @@ export declare const TextToSpeechSpeaker: {
|
|
|
31
31
|
readonly Advait: "advait";
|
|
32
32
|
readonly Amelia: "amelia";
|
|
33
33
|
readonly Sophia: "sophia";
|
|
34
|
+
readonly Anand: "anand";
|
|
35
|
+
readonly Tanya: "tanya";
|
|
36
|
+
readonly Tarun: "tarun";
|
|
37
|
+
readonly Sunny: "sunny";
|
|
38
|
+
readonly Mani: "mani";
|
|
39
|
+
readonly Gokul: "gokul";
|
|
40
|
+
readonly Vijay: "vijay";
|
|
41
|
+
readonly Shruti: "shruti";
|
|
42
|
+
readonly Suhani: "suhani";
|
|
43
|
+
readonly Mohit: "mohit";
|
|
44
|
+
readonly Kavitha: "kavitha";
|
|
45
|
+
readonly Rehan: "rehan";
|
|
46
|
+
readonly Soham: "soham";
|
|
47
|
+
readonly Rupali: "rupali";
|
|
34
48
|
};
|
|
35
49
|
export type TextToSpeechSpeaker = (typeof TextToSpeechSpeaker)[keyof typeof TextToSpeechSpeaker];
|
|
@@ -32,4 +32,18 @@ export const TextToSpeechSpeaker = {
|
|
|
32
32
|
Advait: "advait",
|
|
33
33
|
Amelia: "amelia",
|
|
34
34
|
Sophia: "sophia",
|
|
35
|
+
Anand: "anand",
|
|
36
|
+
Tanya: "tanya",
|
|
37
|
+
Tarun: "tarun",
|
|
38
|
+
Sunny: "sunny",
|
|
39
|
+
Mani: "mani",
|
|
40
|
+
Gokul: "gokul",
|
|
41
|
+
Vijay: "vijay",
|
|
42
|
+
Shruti: "shruti",
|
|
43
|
+
Suhani: "suhani",
|
|
44
|
+
Mohit: "mohit",
|
|
45
|
+
Kavitha: "kavitha",
|
|
46
|
+
Rehan: "rehan",
|
|
47
|
+
Soham: "soham",
|
|
48
|
+
Rupali: "rupali",
|
|
35
49
|
};
|
package/dist/esm/version.d.mts
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
export declare const SDK_VERSION = "1.1.
|
|
1
|
+
export declare const SDK_VERSION = "1.1.3-alpha.1";
|
package/dist/esm/version.mjs
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
export const SDK_VERSION = "1.1.
|
|
1
|
+
export const SDK_VERSION = "1.1.3-alpha.1";
|
package/package.json
CHANGED
package/reference.md
CHANGED
|
@@ -423,14 +423,14 @@ Convert text into spoken audio. The output is a wave file encoded as a base64 st
|
|
|
423
423
|
|
|
424
424
|
**Available Models:**
|
|
425
425
|
- **bulbul:v2** (default): Supports pitch, loudness, and pace controls
|
|
426
|
-
- **bulbul:v3
|
|
426
|
+
- **bulbul:v3**: Newer model with improved quality
|
|
427
427
|
|
|
428
|
-
**Important Notes for bulbul:v3
|
|
428
|
+
**Important Notes for bulbul:v3:**
|
|
429
429
|
- Pitch and loudness parameters are NOT supported
|
|
430
430
|
- Pace must be between 0.5 and 2.0
|
|
431
431
|
- Preprocessing is automatically enabled
|
|
432
432
|
- Default sample rate is 24000 Hz
|
|
433
|
-
-
|
|
433
|
+
- Supports sample rates: 8000, 16000, 22050, 24000, 32000, 44100, 48000 Hz
|
|
434
434
|
</dd>
|
|
435
435
|
</dl>
|
|
436
436
|
</dd>
|