{"uid":"cap_MavKoxs0_uuht1_JuJSYq","slug":"venice-ai-text-to-speech-a6fb4d10","name":"Venice AI Text-to-Speech","description":"Text-to-speech.","url":"https://api.venice.ai/api/v1/audio/speech?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","example":{"input":"Hello, welcome to Venice Voice.","model":"tts-xai-v1","speed":1,"voice":"af_sky","streaming":false,"response_format":"mp3"},"required":["input"],"properties":{"input":{"type":"string","example":"Hello, this is a test of the text to speech system.","maxLength":4096,"minLength":1,"description":"The text to generate audio for. The maximum length is 4096 characters."},"model":{"enum":["tts-kokoro","tts-qwen3-0-6b","tts-qwen3-1-7b","tts-xai-v1","tts-inworld-1-5-max","tts-chatterbox-hd","tts-orpheus","tts-elevenlabs-turbo-v2-5","tts-minimax-speech-02-hd","tts-gemini-3-1-flash"],"type":"string","default":"tts-kokoro","example":"tts-xai-v1","description":"The model ID of a Venice TTS model."},"speed":{"type":"number","default":1,"example":1,"maximum":4,"minimum":0.25,"description":"The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default."},"top_p":{"type":"number","example":1,"maximum":1,"minimum":0,"description":"Nucleus sampling parameter. Supported by models advertising `supportsTopPParam` (currently Qwen 3 TTS). Ignored by other models."},"voice":{"anyOf":[{"enum":["af_alloy","af_aoede","af_bella","af_heart","af_jadzia","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_lily","bm_daniel","bm_fable","bm_george","bm_lewis","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang","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","ef_dora","em_alex","em_santa","Vivian","Serena","Ono_Anna","Sohee","Uncle_Fu","Dylan","Eric","Ryan","Aiden","eve","ara","rex","sal","leo","Craig","Ashley","Olivia","Sarah","Elizabeth","Priya","Alex","Edward","Theodore","Ronald","Mark","Hades","Luna","Pixie","Aurora","Britney","Siobhan","Vicky","Blade","Carl","Cliff","Richard","Rico","tara","leah","jess","mia","zoe","dan","zac","Rachel","Aria","Laura","Charlotte","Alice","Matilda","Jessica","Lily","Roger","Charlie","George","Callum","River","Liam","Will","Chris","Brian","Daniel","Bill","WiseWoman","FriendlyPerson","InspirationalGirl","CalmWoman","LivelyGirl","LovelyGirl","SweetGirl","ExuberantGirl","DeepVoiceMan","CasualGuy","PatientMan","YoungKnight","DeterminedMan","ImposingManner","ElegantMan","Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Pulcherrima","Puck","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"type":"string"},{"type":"string","pattern":"^vv_[A-Za-z0-9_-]+$"}],"default":"af_sky","example":"af_sky","description":"The voice to use when generating the audio. Voices are model-specific: Kokoro (e.g. af_sky, af_bella, am_adam), Qwen 3 (e.g. Vivian, Serena, Dylan), xAI (eve, ara, rex, sal, leo), Orpheus (tara, leah, jess, leo, dan, mia, zac, zoe), Inworld (Craig, Ashley, ...), Chatterbox (Aurora, Blade, ...), ElevenLabs Turbo (Rachel, Aria, ...), MiniMax (WiseWoman, DeepVoiceMan, ...). You can also pass a cloned-voice handle (`vv_<id>`) returned by POST /v1/audio/voices to synthesize in a previously cloned voice; the handle must be paired with the same model used to create it. Using an incompatible voice returns a 400 error. Call GET /models/{id} to list voices for a specific model."},"prompt":{"type":"string","example":"Very happy.","maxLength":500,"description":"A style prompt to control the emotion and delivery of the speech. Supported by models advertising `supportsPromptParam` (currently Qwen 3 TTS). Ignored by other models. Examples: \"Very happy.\", \"Sad and slow.\", \"Excited and energetic.\""},"language":{"type":"string","example":"English","maxLength":32,"minLength":2,"description":"Optional language hint. Accepted values are model-specific: Qwen 3 accepts full names (English, Chinese, ...); xAI/ElevenLabs accept ISO 639-1 codes (en, ja, ...); MiniMax accepts full names. Unsupported values are silently ignored. Omit to let the model auto-detect."},"streaming":{"type":"boolean","default":false,"example":true,"description":"Should the content stream back sentence by sentence or be processed and returned as a complete audio file."},"temperature":{"type":"number","example":0.9,"maximum":2,"minimum":0,"description":"Sampling temperature for speech generation. Higher values produce more varied output. Supported by models advertising `supportsTemperatureParam` (Qwen 3, Orpheus, Chatterbox HD). Ignored by other models."},"response_format":{"enum":["mp3","opus","aac","flac","wav","pcm"],"type":"string","default":"mp3","example":"mp3","description":"The format to audio in."}},"description":"Request to generate audio from text.","additionalProperties":false},"responseSchema":{"type":"string","format":"binary"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"10","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$10/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_td40WI_6rrFET6hgctkXZ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"10","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts text (up to 4096 characters) into audio using a choice of TTS models and voices, returning binary audio in the requested format.","exampleAgentPrompt":"Read this aloud using the Venice TTS model tts-xai-v1 with the af_sky voice at normal speed and give me back an mp3: 'Welcome to our platform. We are thrilled to have you here today.'","exampleUseCases":null,"resultDescription":"A binary audio file (e.g. mp3, wav) containing the synthesized speech of the input text, ready for playback or storage.","failureModes":["Input text exceeds 4096 characters — returns 400 with validation error","Invalid or unsupported model ID — returns 400","Invalid voice name or cloned voice handle not found — returns 400","Insufficient balance for x402 wallet auth — returns 402 Payment Required with top-up instructions","Unauthenticated request — returns 401","Model does not support the selected voice or voice_cloning capability — returns 400 or ignores parameter","Speed out of range (below 0.25 or above 4.0) — returns 400"],"whenToPreferThis":"Choose this endpoint when you need to synthesize speech from text with fine-grained control over voice, model, speed, and format — especially if you want to use Venice AI's range of open and proprietary TTS models, leverage voice cloning via a pre-uploaded audio handle, or authenticate via x402 crypto wallet payments. Prefer over generic TTS APIs when Venice-specific models (e.g. tts-chatterbox-hd, tts-orpheus) or multilingual voices are required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:46:58.111Z","isFirstParty":false,"canonicalSlug":"venice-ai-text-to-speech-a6fb4d10"}