Generate speech with bytedance/seed-audio-1.0

Authorization

BearerAuth

AuthorizationBearer <token>

API key is required to authorize requests. Create a key in the Atlas Cloud dashboard.

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*"bytedance/seed-audio-1.0"

Model name.

Value in

"bytedance/seed-audio-1.0"

text*string

Prompt or text to synthesize into audio. For audio-reference generation, cite the provider-specific audio reference placeholders supported by the upstream service.

references?array<||||>

Optional reference resources. Omit for text-only generation. Add up to 3 audio/speaker references or 1 image reference. Each item must choose exactly one source.

Itemsitems <= 3

format?string

Output audio format.

Value in

"mp3"
"wav"
"pcm"
"ogg_opus"

sample_rate?integer

Output sample rate.

Default24000

Value in

8000
16000
24000
32000
44100
48000

pitch_rate?integer

Pitch adjustment. Range [-12, 12], default 0.

Range-12 <= value <= 12

Default0

speech_rate?integer

Speech speed adjustment. Range [-50, 100], where 100 means 2.0x and -50 means 0.5x.

Range-50 <= value <= 100

Default0

loudness_rate?integer

Loudness adjustment. Range [-50, 100], where 100 means 2.0x loudness and -50 means 0.5x.

Range-50 <= value <= 100

Default0

Response Body

`application/json`

curl -X POST "https://example.com/api/v1/model/generateAudio" \  -H "Content-Type: application/json" \  -d '{    "model": "bytedance/seed-audio-1.0",    "text": "A phone vibrates first, then a calm male voice says: Welcome to Seed Audio."  }'

{  "created_at": "2019-08-24T14:15:22Z",  "id": "string",  "model": "string",  "outputs": [    "string"  ],  "status": "string",  "urls": {}}

Generate speech with bytedance/seed-audio-1.0

Authorization

Request Body

Response Body

200application/json

`application/json`