-
Notifications
You must be signed in to change notification settings - Fork 4.7k
Expand file tree
/
Copy pathspeech_create_params.py
More file actions
68 lines (46 loc) · 2.09 KB
/
speech_create_params.py
File metadata and controls
68 lines (46 loc) · 2.09 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
from __future__ import annotations
from typing import Union
from typing_extensions import Literal, Required, TypeAlias, TypedDict
from .speech_model import SpeechModel
__all__ = ["SpeechCreateParams", "Voice", "VoiceID"]
class SpeechCreateParams(TypedDict, total=False):
input: Required[str]
"""The text to generate audio for. The maximum length is 4096 characters."""
model: Required[Union[str, SpeechModel]]
"""
One of the available [TTS models](https://platform.openai.com/docs/models#tts):
`tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
"""
voice: Required[Voice]
"""The voice to use when generating the audio.
Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`,
`fable`, `onyx`, `nova`, `sage`, `shimmer`, `verse`, `marin`, and `cedar`. You
may also provide a custom voice object with an `id`, for example
`{ "id": "voice_1234" }`. Previews of the voices are available in the
[Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
"""
instructions: str
"""Control the voice of your generated audio with additional instructions.
Does not work with `tts-1` or `tts-1-hd`.
"""
response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"]
"""The format to audio in.
Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`.
"""
speed: float
"""The speed of the generated audio.
Select a value from `0.25` to `4.0`. `1.0` is the default.
"""
stream_format: Literal["sse", "audio"]
"""The format to stream the audio in.
Supported formats are `sse` and `audio`. `sse` is not supported for `tts-1` or
`tts-1-hd`.
"""
class VoiceID(TypedDict, total=False):
"""Custom voice reference."""
id: Required[str]
"""The custom voice ID, e.g. `voice_1234`."""
Voice: TypeAlias = Union[
str, Literal["alloy", "ash", "ballad", "coral", "echo", "sage", "shimmer", "verse", "marin", "cedar"], VoiceID
]