StepFun

Frontier multimodal reasoning with a 1M token context, image and video input, parallel tool calling, and strict JSON schema output.

StepFun multimodal reasoning model with image and video input, tool calling, adjustable reasoning effort, and 256K context.

Agent-optimized Step 3.5 Flash variant with low and high reasoning effort modes.

StepFun text reasoning model for agents, coding, tool calling, and long-context analysis.

Audio and text conversation model that reasons before answering, with function calling and JSON output.

StepFun audio and text conversation model with text output and paralinguistic understanding.

Human-level speech synthesis across six languages, with 12 system voices, natural-language delivery direction, and streaming playback.

Contextual StepFun text-to-speech model with natural-language voice direction and expressive delivery.

Generates dialogue, sound effects, ambience, and background music together in one clip from a written scene.

Writes complete songs from a style description, with vocals, arrangement, and mixing, or instrumentals and covers.

Context-aware transcription for proper nouns, technical terms, dialects, and difficult audio including whispers, fast speech, and singing.

Live transcription over a socket, returning partial results as the speaker talks, with voice activity detection marking each sentence.

StepFun streaming speech recognition model for Chinese and English audio transcription.

Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.

Speech in, speech out, over one socket, with paralinguistic understanding of tone and pacing.

StepFun image generation and image editing model for text-to-image and single-image edits.

StepFun text-to-speech model with official voices, custom cloned voices, and voice tag controls.