@mastra/voice-murf 0.12.0 → 0.12.1

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.
@@ -1,83 +0,0 @@
1
- # Voice API Reference
2
-
3
- > API reference for voice - 1 entries
4
-
5
-
6
- ---
7
-
8
- ## Reference: Murf
9
-
10
- > Documentation for the Murf voice implementation, providing text-to-speech capabilities.
11
-
12
- The Murf voice implementation in Mastra provides text-to-speech (TTS) capabilities using Murf's AI voice service. It supports multiple voices across different languages.
13
-
14
- ## Usage Example
15
-
16
- ```typescript
17
- import { MurfVoice } from "@mastra/voice-murf";
18
-
19
- // Initialize with default configuration (uses MURF_API_KEY environment variable)
20
- const voice = new MurfVoice();
21
-
22
- // Initialize with custom configuration
23
- const voice = new MurfVoice({
24
- speechModel: {
25
- name: "GEN2",
26
- apiKey: "your-api-key",
27
- properties: {
28
- format: "MP3",
29
- rate: 1.0,
30
- pitch: 1.0,
31
- sampleRate: 48000,
32
- channelType: "STEREO",
33
- },
34
- },
35
- speaker: "en-US-cooper",
36
- });
37
-
38
- // Text-to-Speech with default settings
39
- const audioStream = await voice.speak("Hello, world!");
40
-
41
- // Text-to-Speech with custom properties
42
- const audioStream = await voice.speak("Hello, world!", {
43
- speaker: "en-UK-hazel",
44
- properties: {
45
- format: "WAV",
46
- rate: 1.2,
47
- style: "casual",
48
- },
49
- });
50
-
51
- // Get available voices
52
- const voices = await voice.getSpeakers();
53
- ```
54
-
55
- ## Constructor Parameters
56
-
57
- ### MurfConfig
58
-
59
- ### Speech Properties
60
-
61
- ## Methods
62
-
63
- ### speak()
64
-
65
- Converts text to speech using Murf's API.
66
-
67
- Returns: `Promise<NodeJS.ReadableStream>`
68
-
69
- ### getSpeakers()
70
-
71
- Returns an array of available voice options, where each node contains:
72
-
73
- ### listen()
74
-
75
- This method is not supported by Murf and will throw an error. Murf does not provide speech-to-text functionality.
76
-
77
- ## Important Notes
78
-
79
- 1. A Murf API key is required. Set it via the `MURF_API_KEY` environment variable or pass it in the constructor.
80
- 2. The service uses GEN2 as the default model version.
81
- 3. Speech properties can be set at the constructor level and overridden per request.
82
- 4. The service supports extensive audio customization through properties like format, sample rate, and channel type.
83
- 5. Speech-to-text functionality is not supported.