Audio Generation

POST /v1/audio/generations

Create an async audio generation job. Returns 202 Accepted with the job ID.

Request

curl https://ghostmind.optdmsa.com/v1/audio/generations \
  -H "Authorization: Bearer sk-gm-..." \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, world!",
    "voice": "ar-MA-Standard-A",
    "response_format": "wav",
    "provider": "google_ai_studio_savio_tts"
  }'

Parameters

Field	Type	Required	Description
input	string	Yes	Text to synthesize (max 10,000 chars)
voice	string	Yes	Voice identifier
model	string	No	Model name
language	string	No	Language code
response_format	string	No	Output format (default: wav)
provider	string	No	Provider override
provider_options	object	No	Provider-specific options

Response (202)

{
  "id": "job-uuid",
  "status": "queued",
  "provider": "google_ai_studio_savio_tts",
  "voice": "ar-MA-Standard-A"
}

GET /v1/audio/generations/{id}

Get job status.

Response

{
  "id": "job-uuid",
  "status": "completed",
  "provider": "google_ai_studio_savio_tts",
  "voice": "ar-MA-Standard-A",
  "output_mime_type": "audio/wav",
  "output_size_bytes": 102400,
  "duration_ms": 2500,
  "content_url": "/v1/audio/generations/job-uuid/content"
}

Job Statuses

Status	Description
created	Job created
validated	Request validated
queued	Job queued for processing
processing	Audio is being generated
completed	Audio is ready for download
failed	Generation failed
cancelled	Job was cancelled

GET /v1/audio/generations/{id}/content

Download the generated audio. Supports Range requests for partial content.

curl https://ghostmind.optdmsa.com/v1/audio/generations/{id}/content \
  -H "Authorization: Bearer sk-gm-..." \
  -o audio.wav

POST /v1/audio/generations/{id}/cancel

Cancel a queued or processing job.

POST /v1/audio/generations/{id}/retry

Retry a failed job. Creates a new job with the same parameters.

GET /v1/audio/generations

List jobs in the workspace. Supports status, limit, and offset query parameters.

GET /v1/audio/providers

List available TTS providers.

GET /v1/audio/providers/{provider}/voices

List available voices for a provider. Supports dialect and gender filters.

Next Steps

• Speech Generation Guide — User guide
• Async Audio Jobs — Developer guide
• Google Savio — Provider details