speech-to-text

POST

https://api.chatfire.cn/elevenlabs/v1/speech-to-text

最后修改时间：2025-07-15 10:17:04

责任人：未设置

详情参考 https://elevenlabs.io/docs/api-reference/speech-to-text/convert

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Body 参数multipart/form-data

file

必需

model_id

enum<string>

必需

枚举值:

scribe_v1

language_code

string | null

可选

与音频文件语言对应的 ISO-639-1 或 ISO-639-3 语言代码。如果事先知道，有时可以提高转录性能。默认为 null，在这种情况下会自动预测语言。

tag_audio_events

string

可选

num_speakers

string

可选

timestamps_granularity

string

可选

diarize

string

可选

diarization_threshold

string

可选

additional_formats[0][format]

string

可选

additional_formats[0][include_speakers]

string

可选

additional_formats[0][max_characters_per_line]

string

可选

additional_formats[0][segment_on_silence_longer_than_s]

string

可选

additional_formats[0][max_segment_duration_s]

string

可选

additional_formats[0][max_segment_chars]

string

可选

additional_formats[1][format]

string

可选

additional_formats[1][include_speakers]

string

可选

additional_formats[1][include_timestamps]

string

可选

file_format

string

可选

cloud_storage_url

string

可选

webhook

string

可选

temperature

string

可选

seed

string

可选

示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.chatfire.cn/elevenlabs/v1/speech-to-text' \
--form 'file=@""' \
--form 'model_id=""' \
--form 'language_code=""' \
--form 'tag_audio_events=""' \
--form 'num_speakers=""' \
--form 'timestamps_granularity=""' \
--form 'diarize=""' \
--form 'diarization_threshold=""' \
--form 'additional_formats[0][format]=""' \
--form 'additional_formats[0][include_speakers]=""' \
--form 'additional_formats[0][max_characters_per_line]=""' \
--form 'additional_formats[0][segment_on_silence_longer_than_s]=""' \
--form 'additional_formats[0][max_segment_duration_s]=""' \
--form 'additional_formats[0][max_segment_chars]=""' \
--form 'additional_formats[1][format]=""' \
--form 'additional_formats[1][include_speakers]=""' \
--form 'additional_formats[1][include_timestamps]=""' \
--form 'file_format=""' \
--form 'cloud_storage_url=""' \
--form 'webhook=""' \
--form 'temperature=""' \
--form 'seed=""'

返回响应

🟢200成功

application/json

Body

audio_base64

string

必需

alignment

object

必需

characters

array[string]

必需

character_start_times_seconds

array [oneOf]

必需

character_end_times_seconds

array[number]

必需

normalized_alignment

object

必需

characters

array[string]

必需

character_start_times_seconds

array [oneOf]

必需

character_end_times_seconds

array[number]

必需

示例

{
    "language_code": "zho",
    "language_probability": 1.0,
    "text": "你好啊！",
    "words": [
        {
            "text": "你",
            "start": 0.119,
            "end": 0.319,
            "type": "word",
            "speaker_id": null,
            "logprob": 0.0,
            "characters": null
        },
        {
            "text": "好",
            "start": 0.319,
            "end": 0.459,
            "type": "word",
            "speaker_id": null,
            "logprob": 0.0,
            "characters": null
        },
        {
            "text": "啊",
            "start": 0.459,
            "end": 0.579,
            "type": "word",
            "speaker_id": null,
            "logprob": 0.0,
            "characters": null
        },
        {
            "text": "！",
            "start": 0.579,
            "end": 0.639,
            "type": "word",
            "speaker_id": null,
            "logprob": 0.0,
            "characters": null
        }
    ],
    "additional_formats": null
}

修改于 2025-07-15 10:17:04

text-to-speech-with-timestamps

Fal.ai