模型概览
模型规格
- 上下文
- 暂未提供
- 最大输出
- 暂未提供
- 架构
- audio->transcription
- 分词器
- Other
- 知识截止时间
- 暂未提供
- 内容审核
- 否
能力与模态
输入 → 输出
输入
audio
输出
transcription
API
支持的 API 参数
可用提供方
1 提供方
Deepgram
unknown- 上下文
- 暂未提供
- 最大输出
- 暂未提供
- 输入
- $4300.00
- 输出
- 免费
- 缓存读取
- 暂未提供
- 缓存写入
- 暂未提供
Deepgram Nova-3 general-purpose speech-to-text model with monolingual and multilingual transcription support.
Flux TTS is a text-to-speech model from Deepgram. It is suited for natural, expressive English speech synthesis across Deepgram's Flux voice catalog.
Aura-2 is a multilingual text-to-speech model from Deepgram. It supports Deepgram’s canonical Aura-2 voice catalog for speech synthesis across multiple languages.