Knowledge base

Tìm nhanh trong tài liệu Zora

Audio API

Create speech, transcribe audio, dub audio, generate sound effects, change voices, or isolate speech through the Zora API. Audio endpoints are asynchronous and require a paid Zora API key or PAYG credit.

PAYG audio usage is charged in VND by completed task usage. Provider credit fields and provider balances are not returned in public Zora responses.

POST/v1/audio/speech
POST/v1/audio/transcriptions
POST/v1/audio/dubbing
POST/v1/audio/sound-effects
POST/v1/audio/voice-changer
POST/v1/audio/voice-isolate
GET/v1/audio/tasks/{task_id}

Supported Models

ModelUse
whisper-large-v3Higher-accuracy transcription and translation
whisper-large-v3-turboLower-latency transcription
eleven_v3Expressive text-to-speech with inline audio tag control
eleven_multilingual_v2Multilingual text-to-speech
eleven_flash_v2_5Low-latency text-to-speech
eleven_turbo_v2_5Balanced quality and latency text-to-speech
eleven_multilingual_sts_v2Speech-to-speech voice changing
eleven_text_to_sound_v2Prompt-based sound effect generation

Text To Speech

curl
curl https://api.zora.io.vn/v1/audio/speech \ -H "Authorization: Bearer YOUR_ZORA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "voice_id": "21m00Tcm4TlvDq8ikWAM", "text": "The first move is what sets everything in motion.", "model_id": "eleven_v3", "with_transcript": false }'

Speech To Text

curl
curl https://api.zora.io.vn/v1/audio/transcriptions \ -H "Authorization: Bearer YOUR_ZORA_API_KEY" \ -F file="@audio.mp3" \ -F tag_audio_events=true

Task Polling

Creation endpoints return a task_id. Poll the task endpoint until status is done, then read Zora output URLs from metadata. Output URLs use /v1/audio/files/{token}and require the same Zora API key to download.

curl
curl https://api.zora.io.vn/v1/audio/tasks/task_uuid_here \ -H "Authorization: Bearer YOUR_ZORA_API_KEY"

Common Fields

FieldRequiredDescription
voice_idTTS/voice changerTarget voice ID. Use GET /v1/audio/voices to list voices.
textTTS/sound effectsInput text or sound effect prompt.
fileUpload routesAudio file upload for transcription, dubbing, voice changing, or isolation.
receive_urlNoOptional webhook URL for task completion.
target_langDubbingTarget language for dubbed audio.