AI voice and music | Speech, transcription and sound - Pure Tokens

Use available models in the Pure Tokens audio workspace for speech, transcription, sound and music creation; check capabilities and pay for actual usage.

Turn text into speech

Enter text and choose an available voice model and voice to create narration or voiceovers for your content.

Transcribe recordings and make music

Switch between transcription, voice generation and music creation by task. Check the workspace for supported inputs, formats and models.

Explore audio in one workspace

See available audio capabilities in the workspace. To call these models from an Agent, follow the Pure Tokens Skill installation guide.

Pure Tokens 让每种想法,找到合适的模型 A model for every idea
正在打开你的 AI 工作台 Preparing your AI workspace
连接稍慢,准备好后会自动进入 Connection is slow. We'll open it when ready.
重新加载 Reload page