> ## Documentation Index > Fetch the complete documentation index at: https://platform.stepfun.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Audio Models Find the right model for voice agents, translation, transcription, speech generation, and music creation. This page summarizes what each model does; see the individual model pages for specs and quick-start code. Try them in [Voice Studio](https://audio.stepfun.ai/). Language support: * TTS and ASR — Chinese, English, Japanese, Korean, French, Spanish * Realtime — Chinese, English > Note: All languages except Chinese and English are in preview. More languages are on the way. ## Choose a model | Model | Description | Input → Output | Details | | - | - | - | - | | `stepaudio-3-tts` | Natural, context-aware speech with low-latency streaming | Text → Audio | [StepAudio 3 TTS](/docs/en/guides/models/stepaudio-3-tts) | | `stepaudio-3-asr-max` | Context-aware speech recognition via HTTP or SSE | Audio → Text | [StepAudio 3 ASR](/docs/en/guides/models/stepaudio-3-asr) | | `stepaudio-3-realtime-preview` | Full-duplex voice interaction with adaptive reasoning | Audio or text → Audio + text | [StepAudio 3 Realtime](/docs/en/guides/models/stepaudio-3-realtime) | | `stepaudio-3-gen-preview` | Unified generation of speech, sound effects, ambience, and background music | Text → Audio | [StepAudio 3 Gen](/docs/en/guides/models/stepaudio-3-gen) | | `stepaudio-3-music-preview` | Music generation from text, lyrics, and audio | Text, audio → Music | [StepAudio 3 Music](/docs/en/guides/models/stepaudio-3-music) | | `stepaudio-2.5-chat` | Understands speech (including tone and emotion) and responds in text through an OpenAI-compatible Chat Completion API | Audio or text → Text | [StepAudio 2.5 Chat](/docs/en/guides/models/stepaudio-2.5-chat) | | `stepaudio-2.5-realtime` | Real-time speech-to-speech conversation over a WebSocket Realtime API | Audio or text → Audio + text | [StepAudio 2.5 Realtime](/docs/en/guides/models/stepaudio-2.5-realtime) | | `stepaudio-2.5-tts` | Contextual text-to-speech with natural-language control over delivery and zero-shot voice cloning | Text → Audio | [StepAudio 2.5 TTS](/docs/en/guides/models/stepaudio-2.5-tts) | | `stepaudio-2.5-asr` | Speech recognition (one-shot, HTTP + SSE) | Audio → Text | [StepAudio 2.5 ASR](/docs/en/guides/models/stepaudio-2.5-asr) | | `stepaudio-2.5-asr-stream` | Real-time bidirectional streaming speech recognition | Audio → Text | [StepAudio 2.5 ASR](/docs/en/guides/models/stepaudio-2.5-asr) | ## StepAudio 3 TTS Generate natural, expressive speech—including laughter, hesitation, and self-correction—with low-latency streaming and fine-grained control over context. [Learn more about StepAudio 3 TTS](/docs/en/guides/models/stepaudio-3-tts). ## StepAudio 3 ASR Context-aware transcription for proper names, specialized terminology, dialects, Chinese–English code-switching, and challenging audio such as whispers and singing. [Learn more about StepAudio 3 ASR](/docs/en/guides/models/stepaudio-3-asr). ## StepAudio 3 Realtime Full-duplex real-time voice: build natural, real-time voice agents that handle interruptions, take turns smoothly, reason while speaking, and call tools. [Learn more about StepAudio 3 Realtime](/docs/en/guides/models/stepaudio-3-realtime). ## StepAudio 3 Gen Create speech, singing, sound effects, ambience, and background music in a single clip from a natural-language prompt. [Learn more about StepAudio 3 Gen](/docs/en/guides/models/stepaudio-3-gen). ## StepAudio 3 Music Turn lyrics, style prompts, or dry vocals into complete songs, instrumentals, covers, and soundtracks. [Learn more about StepAudio 3 Music](/docs/en/guides/models/stepaudio-3-music). ## StepAudio 2.5 Chat An end-to-end speech-understanding model served through an OpenAI-compatible Chat Completion API. It accepts audio or text input and returns a text response, interpreting not just the words but also vocal cues such as intonation, hesitation, and laughter. * **Paralinguistic understanding**: captures a speaker's emotional state and intent from vocal cues a text transcript would miss. * **Unified text and audio input**: typed and spoken turns share the same endpoint, so one conversation can mix both. * For spoken replies, pass the text output to a text-to-speech model such as StepAudio 2.5 TTS. Common use cases: voice assistants and conversational agents, call and meeting analysis, and voice message triage. ## StepAudio 2.5 Realtime An end-to-end speech-to-speech model served over a WebSocket Realtime API. It takes streaming audio or text and responds with streaming audio and a matching text transcript—no separate transcription or synthesis step—keeping latency low enough for natural back-and-forth conversation. * **Paralinguistic understanding**: interprets vocal cues such as intonation, pacing, and hesitation in addition to the spoken words. * **Natural turn-taking**: server-side voice activity detection (VAD) lets the model reply at the right moment and be interrupted mid-response. * **System voices**: a set of English system voices selectable per session; see the [voices list](/docs/en/guides/models/stepaudio-2.5-realtime#voices). Common use cases: voice agents for customer support, live hands-free assistants, and interactive phone and IVR systems. ## StepAudio 2.5 TTS A text-to-speech model that brings context understanding into the entire generation pipeline. Instead of matching preset tags, you describe the delivery you want in natural language, at two levels: * **Global context** sets the overall mood, scene, and character relationships for an entire passage. * **Inline context** fine-tunes how individual words and phrases are delivered. It supports layered, mixed delivery intents, such as "restrained sadness, no sobbing, with a slight tremble". The model renders pauses, stress, rhythm, and tonal transitions accordingly, producing speech with natural breathing, dynamic emphasis, and emotional arcs. **Zero-shot voice cloning**: about 3 seconds of reference audio is enough to clone a voice precisely, and cloned voices keep full global and inline context control, with no fixed voice library or preset characters required. Common use cases: audiobooks, dubbing, ad narration, emotional storytelling, and other content that demands high vocal expressiveness. ## StepAudio 2.5 ASR A new-generation speech recognition model built on a 4B-parameter Multi-Token Prediction (MTP) architecture, maintaining SOTA transcription accuracy while sharply reducing latency. Supports Chinese and English recognition with ITN text normalization. It offers two access methods: * **One-shot recognition (`stepaudio-2.5-asr`)**: submit audio over HTTP + SSE and receive the transcription streamed back incrementally. * **Real-time bidirectional streaming (`stepaudio-2.5-asr-stream`)**: stream audio over WebSocket and receive incremental and final results with per-word timing; supports server-side VAD. * Suitable for live captions, voice input, meeting transcription, and back-end batch processing. ## Usage limits * **Text-to-speech input**: up to 1,000 characters per request. * **Text-to-speech output formats**: `wav`, `mp3`, `flac`, `opus`, `pcm`; the default is `mp3`. * **StepAudio 3 Gen input limits**: the `instruction` and `roles` fields are capped at 500 characters and `scripts` at 1,000 characters; exceeding a limit returns HTTP 400. * **StepAudio 3 Gen delivery**: currently supports HTTP `audio` / `sse` return; bidirectional WebSocket streaming is not supported. ## Next steps Human-level, low-latency text-to-speech. Context-aware recognition on a large language model foundation. Full-duplex real-time voice with adaptive reasoning and Voice Agent. Unified audio generation—voice, SFX, ambience, and music. Generate songs, instrumentals, covers, and scoring from dry vocals. Explore the end-to-end speech-understanding model with audio and text input. Explore the end-to-end speech-to-speech model with real-time conversation over WebSocket. Explore the contextual TTS model with dual-level context control and zero-shot voice cloning. Explore the new-generation 4B MTP ASR model with one-shot SSE and real-time bidirectional streaming. Get started with speech generation, voice cloning, and automatic speech recognition. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.