Seed Audio 1.0

Text-to-speech with voice cloning and prosody control

Try Seed Audio 1.0 in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: bytedance-seed-audio-1-0

ByteDance Seed Audio 1.0 is a text-to-speech and audio generation model. It synthesizes natural speech from a text prompt with control over voice, output format, sample rate, speed, volume, and pitch. It supports voice cloning from up to three reference audio clips, or from a single reference image.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Minimal

cURL

curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seed-audio-1-0",
  "prompt": "<prompt>",
  "input": "Welcome to Oxen"
}'

Basic parameters

cURL

curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seed-audio-1-0",
  "prompt": "<prompt>",
  "audio_urls": [
    "https://example.com/audio.mp3"
  ],
  "image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "input": "Welcome to Oxen"
}'

All parameters

cURL

curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seed-audio-1-0",
  "prompt": "<prompt>",
  "audio_urls": [
    "https://example.com/audio.mp3"
  ],
  "image_url": "https://hub.oxen.ai/api/repos/elau/assets/file/main/bloxy/bloxy_cropped_512x512.png",
  "output_format": "mp3",
  "sample_rate": 24000,
  "speed": 1.0,
  "volume": 1.0,
  "pitch": 0,
  "input": "Welcome to Oxen"
}'

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/bytedance-seed-audio-1-0

Request parameters

Required parameters

Field	Type	Default	Description
prompt	string	—	Prompt or text to synthesize. Reference audio inputs by order with @Audio1, @Audio2, @Audio3.

Optional parameters

Field	Type	Default	Description
audio_urls	array<string>	—	Up to 3 reference audio URLs for voice cloning (max 30s and 10MB each). Reference them in the prompt as @Audio1, @Audio2, @Audio3. Supported formats: wav, mp3, pcm, ogg_opus.
image_url	string	—	Optional single reference image URL (jpeg, png, or webp, max 10MB). Incompatible with audio references. Format: uri.
output_format	string	"mp3"	Output audio file format. One of: wav, mp3, pcm, ogg_opus.
sample_rate	integer	24000	Output sample rate in Hz. One of: 8000, 16000, 24000, 32000, 44100, 48000.
speed	number	1.0	Speech tempo multiplier (typical range 0.5-2.0). Range: 0.5 – 2.0.
volume	number	1.0	Audio amplitude multiplier (typical range 0.5-2.0). Range: 0.5 – 2.0.
pitch	integer	0	Pitch shift in semitones (range -12 to 12; 0 leaves the pitch unchanged). Range: -12 – 12.