Get TTS Generation

Retrieve a single stored text-to-speech generation.

GET /v1/speak/samples/{id}

Get TTS Generation

cURL

curl --request GET \
  --url https://api.bland.ai/v1/speak/samples/{id} \
  --header 'authorization: <authorization>'

Metadata response

{
  "data": {
    "id": "a3f8c2d1-4b5e-6789-0abc-def012345678",
    "org_id": "9e1d2c3b-4a5f-6780-bcde-f01234567890",
    "user_id": "5c6d7e8f-9012-3456-789a-bcdef0123456",
    "text": "Hello, this is a test of the text-to-speech system.",
    "voice_id": "2b3c4d5e-6f70-8901-2345-6789abcdef01",
    "output_format": "pcm_44100",
    "audio_data": "base64-encoded-audio-data",
    "latency_ms": 1261,
    "cost": 0.011,
    "created_at": "2026-03-16T01:44:56.673Z"
  },
  "errors": null
}

Headers

authorization · string · required

Your API key for authentication.

Path Parameters

id · string · required

The ID of the generation to retrieve.

Query Parameters

format · string

Pass audio to receive the raw WAV binary instead of the metadata JSON.

Response

Without ?format=audio, returns the generation metadata:

id · string

Unique identifier for the generation.

org_id · string

The organization that created the generation.

user_id · string

The user that created the generation.

text · string

The text that was synthesized.

voice_id · string

The voice used for synthesis.

output_format · string

The audio format of the generation (e.g. pcm_44100).

audio_data · string

Base64-encoded audio data. Only present in the JSON response (not when using ?format=audio).

latency_ms · number

Time in milliseconds from request to first audio.

cost · number

Cost in USD for this generation.

created_at · string

ISO 8601 timestamp of when the generation was created.

With ?format=audio, returns a raw WAV audio binary (same as the original POST /v1/speak response).

Metadata response

{
  "data": {
    "id": "a3f8c2d1-4b5e-6789-0abc-def012345678",
    "org_id": "9e1d2c3b-4a5f-6780-bcde-f01234567890",
    "user_id": "5c6d7e8f-9012-3456-789a-bcdef0123456",
    "text": "Hello, this is a test of the text-to-speech system.",
    "voice_id": "2b3c4d5e-6f70-8901-2345-6789abcdef01",
    "output_format": "pcm_44100",
    "audio_data": "base64-encoded-audio-data",
    "latency_ms": 1261,
    "cost": 0.011,
    "created_at": "2026-03-16T01:44:56.673Z"
  },
  "errors": null
}

---

Docs for agents: llms.txt