Gemini TTS 2.5 Pro Serverless API

Human-like speech synthesis with rich expressive emotional depth.

~43.51s
POST /v2/gemini-2.5-pro-tts · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "gemini-2.5-pro-tts",
 9    text="Narrate softly: I hope you find peace and joy.",
10    voice_1="Kore",
11    temperature=0.4,
12)
13print(result["status"])                      # COMPLETED
14print(result.get("output"))                  # model output (e.g. media URL)
15print(result["metrics"]["inference_time"])   # server compute seconds
16
17# --- Or submit + poll manually (track request_id, control the cadence) ---
18from segmind import SegmindClient, InferenceFailed, InferenceTimeout
19
20client = SegmindClient()                      # reads SEGMIND_API_KEY
21payload = {
22    "text": "Narrate softly: I hope you find peace and joy.",
23    "voice_1": "Kore",
24    "temperature": 0.4,
25}
26job = client.submit_async("gemini-2.5-pro-tts", **payload)
27print(job.request_id)                         # available immediately
28try:
29    result = job.wait(timeout=600, interval=1.0)
30except InferenceTimeout as e:
31    print("still running:", e.request_id)
32except InferenceFailed as e:
33    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/gemini-2.5-pro-tts

Parameters

textrequired
string

Input text for voice synthesis. Use styles like: 'soft, calm' or 'excited narration'.

Default: "Narrate softly: I hope you find peace and joy."
temperatureoptional
number

Adjusts speech variance. Use 0.2 for stable narration or 0.7 for dynamic expression.

Default: 0.4Range: 0 - 2
voice_1optional
string

Select a unique voice for Speaker 1. Ideal for character roles or distinct narrator styles.

Default: "Kore"
Allowed values (30 total):
"Zephyr""Puck""Charon""Kore""Fenrir""Leda""Orus""Aoede""Callirrhoe""Autonoe"+20 more
voice_2optional
string

Choose a second speaker voice for dialogues. Use contrasting voices for role distinction.

Default: null
Allowed values (30 total):
"Zephyr""Puck""Charon""Kore""Fenrir""Leda""Orus""Aoede""Callirrhoe""Autonoe"+20 more

Response Type

Returns: Audio

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/gemini-2.5-pro-tts

    Submitreturns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Polluntil COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out