Audio Generation

Generate audio

POST /api/v1/audio/generate

Scope: audio:generate

Turn text into an MP3. The request returns immediately with an id. Poll Get generation until the job is completed or failed.

Audio generation requires at least one credit purchase on the account. Signup credits are not enough. See Purchase required.

Request body

Generic fields stay at the top level. Settings unique to ElevenLabs go in provider_options.

Field	Type	Required	Description
`text`	string	Yes	Text to speak, 1–5,000 characters. Eleven v3 audio tags may be included inline.
`provider`	string	Yes	Currently `elevenlabs`
`output_format`	string	No	Currently `mp3`; defaults to `mp3`
`provider_options`	object	Yes	Provider-specific settings (see below)

`provider_options` (ElevenLabs)

Field	Type	Required	Description
`voice_id`	string	Yes	ElevenLabs voice ID
`model`	string	No	Currently `eleven_v3`
`stability`	string	No	`creative`, `natural`, or `robust` (default: `natural`)
`language_code`	string	No	Two-letter ISO 639-1 code (`en`, `he`, …)
`seed`	integer	No	Best-effort deterministic seed. Identical output is not guaranteed.
`text_normalization`	string	No	`auto`, `on`, or `off` (default: `auto`)

Cost is based on text length: 1 credit per 400 characters, rounded up, minimum 1. Charged when the job starts. Failed jobs are refunded. The start response includes credits_used and remaining_credits.

Examples: 1 character costs 1 credit. 400 characters cost 1. 401 characters cost 2.

Eleven v3 text

Put delivery direction in text:

Audio tags such as [whispers], [excited], or [sighs]
Ellipses, punctuation, capitalization, and line breaks for pauses, rhythm, and emphasis
Do not use SSML <break> tags; Eleven v3 does not support them
Pick a voice whose natural character matches the delivery. Tag behavior varies by voice

One voice per request. For more than one speaker, generate a separate job per voice.

Example

curl -X POST https://powerpost.ai/api/v1/audio/generate \
  -H "x-api-key: pp_live_sk_YOUR_KEY" \
  -H "X-Workspace-Id: YOUR_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "[warmly] Welcome to PowerPost.",
    "provider": "elevenlabs",
    "output_format": "mp3",
    "provider_options": {
      "model": "eleven_v3",
      "voice_id": "YOUR_VOICE_ID",
      "stability": "natural",
      "language_code": "en"
    }
  }'

Response

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "processing",
  "status_url": "/api/v1/audio/generations/22222222-2222-4222-8222-222222222222",
  "created_at": "2026-09-04T18:30:00Z",
  "credits_used": 1,
  "remaining_credits": 46
}

Field	Type	Description
`audio_generation_id`	string	Id to poll for this job
`status`	string	Always `processing` on a successful start
`status_url`	string	Relative URL to poll for results
`created_at`	string	ISO 8601 timestamp
`credits_used`	number	Credits deducted
`remaining_credits`	number	Balance after deduction

Errors

Code	Description
400	Invalid request body
401	Invalid API key
402	Insufficient credits (`INSUFFICIENT_CREDITS`)
402	Purchase required (`MEDIA_REQUIRES_PURCHASE`)
403	API key is missing the `audio:generate` scope
429	Rate limit exceeded

Get generation

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

Scope: audio:read

Poll every 2–5 seconds until status is completed or failed.

Path parameters

Parameter	Type	Description
`id`	string	The audio generation id

Example

curl https://powerpost.ai/api/v1/audio/generations/22222222-2222-4222-8222-222222222222 \
  -H "x-api-key: pp_live_sk_YOUR_KEY" \
  -H "X-Workspace-Id: YOUR_WORKSPACE_ID"

Response (processing)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "processing",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": null,
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:01Z",
  "audio": null
}

Response (completed)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "completed",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": null,
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:08Z",
  "audio": {
    "audio_id": "33333333-3333-4333-8333-333333333333",
    "media_id": "33333333-3333-4333-8333-333333333333",
    "url": "https://temporary-signed-url.example/audio.mp3",
    "file_name": "33333333-3333-4333-8333-333333333333.mp3",
    "file_size": 123456,
    "mime_type": "audio/mpeg",
    "duration": 4.2
  }
}

Response (failed)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "failed",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": {
    "code": "AUDIO_GENERATION_FAILED",
    "message": "Audio generation failed"
  },
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:08Z",
  "audio": null
}

Response fields

Field	Type	Description
`audio_generation_id`	string	Audio generation id
`status`	string	`processing`, `completed`, or `failed`
`provider`	string	Speech provider
`model`	string	Model used for this job
`error`	object \| null	Present when `status` is `failed`
`created_at`	string	ISO 8601 timestamp
`updated_at`	string	ISO 8601 timestamp
`audio`	object \| null	Output file when `status` is `completed`

Audio object

Field	Type	Description
`audio_id`	string	Generated audio asset id. Same value as `media_id`.
`media_id`	string	Workspace media library id.
`url`	string \| null	Signed MP3 URL, valid for 1 hour
`file_name`	string	Stored file name
`file_size`	number	Size in bytes
`mime_type`	string	`audio/mpeg`
`duration`	number \| null	Length in seconds, when known

Status values

Status	Description
`processing`	Speech is being generated
`completed`	MP3 is ready
`failed`	Generation failed; credits are refunded

audio.url is signed and expires after 1 hour. Keep audio_generation_id and call this endpoint again for a fresh URL. Completed audio is also stored in the workspace media library as media_type: audio. You cannot pass media_id on posts yet; no publish destination accepts a raw MP3. Use Video audio to mix it into a publishable MP4. If the media item is deleted, the generation remains in history and audio becomes null, matching image and video generations.

Errors

Code	Description
401	Invalid API key
403	API key is missing the `audio:read` scope
404	Audio generation not found
429	Rate limit exceeded

Generate audio

POST /api/v1/audio/generate

Scope: audio:generate

Turn text into an MP3. The request returns immediately with an id. Poll Get generation until the job is completed or failed.

Audio generation requires at least one credit purchase on the account. Signup credits are not enough. See Purchase required.

Request body

Generic fields stay at the top level. Settings unique to ElevenLabs go in provider_options.

Field	Type	Required	Description
`text`	string	Yes	Text to speak, 1–5,000 characters. Eleven v3 audio tags may be included inline.
`provider`	string	Yes	Currently `elevenlabs`
`output_format`	string	No	Currently `mp3`; defaults to `mp3`
`provider_options`	object	Yes	Provider-specific settings (see below)

`provider_options` (ElevenLabs)

Field	Type	Required	Description
`voice_id`	string	Yes	ElevenLabs voice ID
`model`	string	No	Currently `eleven_v3`
`stability`	string	No	`creative`, `natural`, or `robust` (default: `natural`)
`language_code`	string	No	Two-letter ISO 639-1 code (`en`, `he`, …)
`seed`	integer	No	Best-effort deterministic seed. Identical output is not guaranteed.
`text_normalization`	string	No	`auto`, `on`, or `off` (default: `auto`)

Credits

Examples: 1 character costs 1 credit. 400 characters cost 1. 401 characters cost 2.

Eleven v3 text

Put delivery direction in text:

Audio tags such as [whispers], [excited], or [sighs]
Ellipses, punctuation, capitalization, and line breaks for pauses, rhythm, and emphasis
Do not use SSML <break> tags; Eleven v3 does not support them
Pick a voice whose natural character matches the delivery. Tag behavior varies by voice

One voice per request. For more than one speaker, generate a separate job per voice.

Example

curl -X POST https://powerpost.ai/api/v1/audio/generate \
  -H "x-api-key: pp_live_sk_YOUR_KEY" \
  -H "X-Workspace-Id: YOUR_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "[warmly] Welcome to PowerPost.",
    "provider": "elevenlabs",
    "output_format": "mp3",
    "provider_options": {
      "model": "eleven_v3",
      "voice_id": "YOUR_VOICE_ID",
      "stability": "natural",
      "language_code": "en"
    }
  }'

Response

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "processing",
  "status_url": "/api/v1/audio/generations/22222222-2222-4222-8222-222222222222",
  "created_at": "2026-09-04T18:30:00Z",
  "credits_used": 1,
  "remaining_credits": 46
}

Field	Type	Description
`audio_generation_id`	string	Id to poll for this job
`status`	string	Always `processing` on a successful start
`status_url`	string	Relative URL to poll for results
`created_at`	string	ISO 8601 timestamp
`credits_used`	number	Credits deducted
`remaining_credits`	number	Balance after deduction

Errors

Code	Description
400	Invalid request body
401	Invalid API key
402	Insufficient credits (`INSUFFICIENT_CREDITS`)
402	Purchase required (`MEDIA_REQUIRES_PURCHASE`)
403	API key is missing the `audio:generate` scope
429	Rate limit exceeded

Get generation

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

Scope: audio:read

Poll every 2–5 seconds until status is completed or failed.

Path parameters

Parameter	Type	Description
`id`	string	The audio generation id

Example

curl https://powerpost.ai/api/v1/audio/generations/22222222-2222-4222-8222-222222222222 \
  -H "x-api-key: pp_live_sk_YOUR_KEY" \
  -H "X-Workspace-Id: YOUR_WORKSPACE_ID"

Response (processing)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "processing",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": null,
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:01Z",
  "audio": null
}

Response (completed)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "completed",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": null,
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:08Z",
  "audio": {
    "audio_id": "33333333-3333-4333-8333-333333333333",
    "media_id": "33333333-3333-4333-8333-333333333333",
    "url": "https://temporary-signed-url.example/audio.mp3",
    "file_name": "33333333-3333-4333-8333-333333333333.mp3",
    "file_size": 123456,
    "mime_type": "audio/mpeg",
    "duration": 4.2
  }
}

Response (failed)

{
  "audio_generation_id": "22222222-2222-4222-8222-222222222222",
  "status": "failed",
  "provider": "elevenlabs",
  "model": "eleven_v3",
  "error": {
    "code": "AUDIO_GENERATION_FAILED",
    "message": "Audio generation failed"
  },
  "created_at": "2026-09-04T18:30:00Z",
  "updated_at": "2026-09-04T18:30:08Z",
  "audio": null
}

Response fields

Field	Type	Description
`audio_generation_id`	string	Audio generation id
`status`	string	`processing`, `completed`, or `failed`
`provider`	string	Speech provider
`model`	string	Model used for this job
`error`	object \| null	Present when `status` is `failed`
`created_at`	string	ISO 8601 timestamp
`updated_at`	string	ISO 8601 timestamp
`audio`	object \| null	Output file when `status` is `completed`

Audio object

Field	Type	Description
`audio_id`	string	Generated audio asset id. Same value as `media_id`.
`media_id`	string	Workspace media library id.
`url`	string \| null	Signed MP3 URL, valid for 1 hour
`file_name`	string	Stored file name
`file_size`	number	Size in bytes
`mime_type`	string	`audio/mpeg`
`duration`	number \| null	Length in seconds, when known

Status values

Status	Description
`processing`	Speech is being generated
`completed`	MP3 is ready
`failed`	Generation failed; credits are refunded

Errors

Code	Description
401	Invalid API key
403	API key is missing the `audio:read` scope
404	Audio generation not found
429	Rate limit exceeded

Audio Generation

Generate audio

Request body

`provider_options` (ElevenLabs)

Credits

Eleven v3 text

Example

Response

Errors

Get generation

Path parameters

Example

Response (processing)

Response (completed)

Response (failed)

Response fields

Audio object

Status values

Errors

On this page

Audio Generation

Generate audio

Request body

`provider_options` (ElevenLabs)

Credits

Eleven v3 text

Example

Response

Errors

Get generation

Path parameters

Example

Response (processing)

Response (completed)

Response (failed)

Response fields

Audio object

Status values

Errors

On this page