{ "openapi": "3.1.0", "info": { "title": "AudioDojo — Chutes API", "description": "One chute, 12 models, 13 endpoints — covering text-to-speech, voice cloning, voice design, transcription, denoising, source separation, speaker verification, VAD, and language detection. Including Kokoro-82M, Qwen3-TTS 1.7B, Whisper large-v3-turbo, NVIDIA Canary-Qwen 2.5B, and...", "version": "33685e32-b209-5b82-8079-d43326fb1319", "contact": { "name": "Chutes", "url": "https://chutes.ai" }, "x-chutes": { "chuteId": "d6c66e0a-3e04-595b-825c-f3a65e50b2c7", "slug": "vonkaiser-audiodojo", "modelName": "AudioDojo", "standardTemplate": null, "openaiCompatible": false, "confidentialCompute": true, "modelPage": "https://chutes.ai/app/chute/vonkaiser-audiodojo", "llmsTxt": "https://chutes.ai/app/chute/vonkaiser-audiodojo/llms.txt", "pricing": { "usdPerHour": 1.8 } } }, "servers": [ { "url": "https://vonkaiser-audiodojo.chutes.ai" } ], "security": [ { "bearerAuth": [] } ], "components": { "securitySchemes": { "bearerAuth": { "type": "http", "scheme": "bearer", "description": "Chutes API key. Send as `Authorization: Bearer $CHUTES_API_KEY`." } } }, "paths": { "/speak": { "post": { "operationId": "speak", "summary": "POST /speak", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "text": { "type": "string" }, "speed": { "type": "number", "description": "Voice output speed.", "default": 1, "minimum": 0.1, "maximum": 3 }, "voice": { "type": "string", "description": "Voice selection for text-to-speech", "enum": [ "af_heart", "af_alloy", "af_aoede", "af_bella", "af_jessica", "af_kore", "af_nicole", "af_nova", "af_river", "af_sarah", "af_sky", "am_adam", "am_echo", "am_eric", "am_fenrir", "am_liam", "am_michael", "am_onyx", "am_puck", "am_santa", "bf_alice", "bf_emma", "bf_isabella", "bf_lily", "bm_daniel", "bm_fable", "bm_george", "bm_lewis", "ef_dora", "em_alex", "em_santa", "ff_siwis", "hf_alpha", "hf_beta", "hm_omega", "hm_psi", "if_sara", "im_nicola", "jf_alpha", "jf_gongitsune", "jf_nezumi", "jf_tebukuro", "jm_kumo", "pf_dora", "pm_alex", "pm_santa", "zf_xiaobei", "zf_xiaoni", "zf_xiaoxiao", "zf_xiaoyi", "zm_yunjian", "zm_yunxi", "zm_yunxia", "zm_yunyang" ], "default": "af_heart" } }, "required": [ "text" ] }, "example": { "text": "Your text here", "speed": 1, "voice": "af_heart" } } } } } }, "/tts/kokoro": { "post": { "operationId": "tts_kokoro", "summary": "POST /tts/kokoro", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "text": { "type": "string" }, "speed": { "type": "number", "description": "Playback speed multiplier (0.1–3.0).", "default": 1, "minimum": 0.1, "maximum": 3 }, "voice": { "type": "string", "description": "Built-in voice ID. See KokoroVoice enum for the full list.", "enum": [ "af_heart", "af_alloy", "af_aoede", "af_bella", "af_jessica", "af_kore", "af_nicole", "af_nova", "af_river", "af_sarah", "af_sky", "am_adam", "am_echo", "am_eric", "am_fenrir", "am_liam", "am_michael", "am_onyx", "am_puck", "am_santa", "bf_alice", "bf_emma", "bf_isabella", "bf_lily", "bm_daniel", "bm_fable", "bm_george", "bm_lewis", "ef_dora", "em_alex", "em_santa", "ff_siwis", "hf_alpha", "hf_beta", "hm_omega", "hm_psi", "if_sara", "im_nicola", "jf_alpha", "jf_gongitsune", "jf_nezumi", "jf_tebukuro", "jm_kumo", "pf_dora", "pm_alex", "pm_santa", "zf_xiaobei", "zf_xiaoni", "zf_xiaoxiao", "zf_xiaoyi", "zm_yunjian", "zm_yunxi", "zm_yunxia", "zm_yunyang" ], "default": "af_heart" } }, "required": [ "text" ] }, "example": { "text": "Your text here", "speed": 1, "voice": "af_heart" } } } } } }, "/tts/qwen3clone": { "post": { "operationId": "tts_qwen3_clone", "summary": "POST /tts/qwen3clone", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "text": { "type": "string" }, "language": { "type": "string", "description": "Target language name (e.g. 'English', 'Chinese').", "default": "English" }, "ref_text": { "type": "string", "description": "Transcript of the reference audio. If omitted, Whisper auto-transcribes it.", "default": "" }, "trim_sample": { "type": "boolean", "description": "If True, automatically trim ref audio to the first 6s. If False and the audio exceeds 6s, the request is rejected with an error.", "default": false }, "auto_denoise": { "type": "boolean", "description": "If True, run MetricGAN+ speech enhancement on the reference audio before cloning. Improves clone quality when the reference recording is noisy.", "default": false }, "high_fidelity": { "type": "boolean", "description": "Controls the voice cloning mode. False (default): speaker-embedding-only mode (xvec). The model extracts a speaker embedding from the reference audio and conditions generation purely on that vector — clean output with no risk of reference audio bleed-through. Recommended for most use cases. True: in-context learning (ICL) mode. The reference audio is prepended as acoustic context so the model can mimic fine-grained prosody and timbre directly. Higher voice similarity is possible, but the last word or syllable of your reference clip may bleed into the start of the generated output if the reference does not end on a clean silence.", "default": false }, "ref_audio_b64": { "type": "string", "description": "Base64-encoded reference audio for voice cloning (max 6s)." } }, "required": [ "text", "ref_audio_b64" ] }, "example": { "text": "Your text here", "language": "English", "ref_text": "", "trim_sample": false, "auto_denoise": false, "high_fidelity": false, "ref_audio_b64": "" } } } } } }, "/tts/qwen3custom": { "post": { "operationId": "tts_qwen3_custom", "summary": "POST /tts/qwen3custom", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "text": { "type": "string" }, "speaker": { "type": "string", "description": "Preset speaker identity: Vivian, Serena, Uncle Fu, Dylan, Eric, Ryan, Aiden, Ono Anna, Sohee. Defaults to Ryan.", "default": null }, "instruct": { "type": "string", "description": "Free-text delivery style, e.g. 'Very happy', 'calm husky', 'whispering'. Leave blank for neutral.", "default": null }, "language": { "type": "string", "description": "Target language name.", "default": "English" } }, "required": [ "text" ] }, "example": { "text": "Your text here", "language": "English" } } } } } }, "/tts/qwen3design": { "post": { "operationId": "tts_qwen3_design", "summary": "POST /tts/qwen3design", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "text": { "type": "string" }, "instruct": { "type": "string", "description": "Voice description, e.g. 'A warm, confident male narrator with a slight British accent'." }, "language": { "type": "string", "description": "Target language name.", "default": "English" } }, "required": [ "text", "instruct" ] }, "example": { "text": "Your text here", "instruct": "example-string", "language": "English" } } } } } }, "/stt/whisper": { "post": { "operationId": "stt_whisper", "summary": "POST /stt/whisper", "responses": { "200": { "description": "Successful response.", "content": { "application/json": { "schema": { "type": "object", "additionalProperties": true } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "language": { "type": "string", "description": "BCP-47 language code, e.g. 'en', 'fr', 'zh'. Auto-detected if omitted.", "default": null }, "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." }, "return_timestamps": { "type": "boolean", "description": "Include word-level timestamp chunks in the response.", "default": true } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "", "return_timestamps": true } } } } } }, "/stt/canary": { "post": { "operationId": "stt_canary", "summary": "POST /stt/canary", "responses": { "200": { "description": "Successful response.", "content": { "application/json": { "schema": { "type": "object", "additionalProperties": true } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file." }, "max_new_tokens": { "type": "integer", "description": "Maximum tokens to generate for the transcript.", "default": 256, "minimum": 16, "maximum": 4096 } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "", "max_new_tokens": 256 } } } } } }, "/stt/parakeet": { "post": { "operationId": "stt_parakeet", "summary": "POST /stt/parakeet", "responses": { "200": { "description": "Successful response.", "content": { "application/json": { "schema": { "type": "object", "additionalProperties": true } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file." }, "timestamps": { "type": "boolean", "description": "Include word and segment timestamps in the response.", "default": true } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "", "timestamps": true } } } } } }, "/audio/vad": { "post": { "operationId": "audio_vad", "summary": "POST /audio/vad", "responses": { "200": { "description": "Binary media payload.", "content": { "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "" } } } } } }, "/audio/diarize": { "post": { "operationId": "audio_diarize", "summary": "POST /audio/diarize", "responses": { "200": { "description": "Binary media payload.", "content": { "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "" } } } } } }, "/audio/verifyspeaker": { "post": { "operationId": "audio_verify_speaker", "summary": "POST /audio/verifyspeaker", "responses": { "200": { "description": "Binary media payload.", "content": { "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_a_b64": { "type": "string", "description": "Base64-encoded first audio clip." }, "audio_b_b64": { "type": "string", "description": "Base64-encoded second audio clip." } }, "required": [ "audio_a_b64", "audio_b_b64" ] }, "example": { "audio_a_b64": "", "audio_b_b64": "" } } } } } }, "/audio/denoise": { "post": { "operationId": "audio_denoise", "summary": "POST /audio/denoise", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "" } } } } } }, "/audio/separate": { "post": { "operationId": "audio_separate", "summary": "POST /audio/separate", "responses": { "200": { "description": "Binary media payload.", "content": { "audio/wav": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "" } } } } } }, "/audio/detectlanguage": { "post": { "operationId": "audio_detect_language", "summary": "POST /audio/detectlanguage", "responses": { "200": { "description": "Binary media payload.", "content": { "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } } }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "audio_b64": { "type": "string", "description": "Base64-encoded audio file (any common format)." } }, "required": [ "audio_b64" ] }, "example": { "audio_b64": "" } } } } } } } }