ホーム
アセット
マイ作品
Models
ボイスライブラリ
開発者
ブログ
日本語
料金
ログイン
Models/Speech/Seed Audio

ByteDance: Seed Audio

  • Voice acting
  • Emotion
API referenceUse in AI音声生成

A voice-acting model; its tool page is called AI Voice. It performs a line with emotion rather than reading text aloud.

Billed per second at 0.5 credits with a 1-credit floor, so short lines cost very little.

Strengths

  • Expressive emotion and tone
  • Per-second billing keeps short lines cheap

Limitations

  • 120 seconds per request
  • No multi-speaker dialogue

Capabilities

CapabilityValue
Text to speech–No
Multi-speaker
–No
EmotionYes
Streaming–No
Voice actingYes
Voice clone–No

Specs and limits

ParameterValue
Max duration120s

How it is billed

0.5 积分 / 秒，最低 1 积分

Standard pricesCredits
60 秒30
每秒0.5

Figures come from the same estimator the generation form calls before you spend anything.

Alternatives

  • LFlowSpeechFor long reads, multi-speaker dialogue, or streaming.

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/listenhub-voice/generate" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"text": "A gentle rain falls on a quiet street at midnight.","durationHint": 20}'
  • API reference
  • SDK & CLI
  • Agent Skills

Similar models

  • LFlowSpeech
  • LVoice Clone