curl --request POST \
--url https://api.omnimux.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer sk-...' \
--header 'Content-Type: multipart/form-data' \
--form 'file=@audio.mp3' \
--form 'model=doubao-asr-bigmodel'
{
"text": "Transcribed text output from Doubao ASR speech recognition model."
}
curl --request POST \
--url https://api.omnimux.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer sk-...' \
--header 'Content-Type: multipart/form-data' \
--form 'file=@audio.mp3' \
--form 'model=doubao-asr-bigmodel'
{
"text": "Transcribed text output from Doubao ASR speech recognition model."
}
Doubao Speech Recognition
Doubao Speech Recognition
VolcEngine / Doubao speech recognition · model doubao-asr-bigmodel, seedasr-auc, bigasr-auc
curl --request POST \
--url https://api.omnimux.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer sk-...' \
--header 'Content-Type: multipart/form-data' \
--form 'file=@audio.mp3' \
--form 'model=doubao-asr-bigmodel'
{
"text": "Transcribed text output from Doubao ASR speech recognition model."
}
POST
/
v1
/
audio
/
transcriptions
curl --request POST \
--url https://api.omnimux.ai/v1/audio/transcriptions \
--header 'Authorization: Bearer sk-...' \
--header 'Content-Type: multipart/form-data' \
--form 'file=@audio.mp3' \
--form 'model=doubao-asr-bigmodel'
{
"text": "Transcribed text output from Doubao ASR speech recognition model."
}
- Endpoint:
POST /v1/audio/transcriptions - Protocol: OpenAI-compatible Audio Transcriptions endpoint
- Supports recorded audio file speech-to-text transcription
Identity
| Field | Value |
|---|---|
| Series | Audio series |
| Brand | VolcEngine / Doubao |
| model | doubao-asr-bigmodel, seedasr-auc, bigasr-auc |
Endpoint
| Method | Path |
|---|---|
POST | /v1/audio/transcriptions |
https://api.omnimux.ai
Authorizations
| Name | In | Type | Required | Description |
|---|---|---|---|---|
Authorization | header | string | yes | Bearer sk-... (API key) |
Body (multipart/form-data)
| Field | Type | Required | Description |
|---|---|---|---|
file | file | yes | The audio file object to transcribe (supports wav, mp3, ogg, m4a, etc.) |
model | string | yes | One of doubao-asr-bigmodel, seedasr-auc, bigasr-auc |
language | string | no | The language of the input audio in ISO-639-1 format (e.g. en, zh) |
response_format | string | no | Format of output (json, text). Default json |
Response
200
{
"text": "Transcribed text output from Doubao ASR speech recognition model."
}