Gemini 3.8 Flash TTS Serverless API

Direct expressive text-to-speech with two-speaker dialogue, 130+ languages.

PlaygroundAPI
Pricing
~7.74s
POST /v2/gemini-3.8-flash-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-3.8-flash-tts",
 9    text="It's fifteen seconds from the final whistle, and it's still Rovers one, City one. <short pause> Mateo Rinaldi picks it up on the halfway line... he's past one man, past two — can he finish it from here? <gasp> He shoots... and it's IN! Rinaldi wins it at the death, and the whole Olimpico is on its feet!",
10    voice_1="Fenrir",
11    style="live stadium football commentator, tense and hushed at first, then erupting into euphoric excitement on the goal",
12    temperature=1.1,
13)
14print(result["status"])                      # COMPLETED
15print(result.get("output"))                  # model output (e.g. media URL)
16print(result["metrics"]["inference_time"])   # server compute seconds
17
18# --- Or submit + poll manually (track request_id, control the cadence) ---
19from segmind import SegmindClient, InferenceFailed, InferenceTimeout
20
21client = SegmindClient()                      # reads SEGMIND_API_KEY
22payload = {
23    "text": "It's fifteen seconds from the final whistle, and it's still Rovers one, City one. <short pause> Mateo Rinaldi picks it up on the halfway line... he's past one man, past two — can he finish it from here? <gasp> He shoots... and it's IN! Rinaldi wins it at the death, and the whole Olimpico is on its feet!",
24    "voice_1": "Fenrir",
25    "style": "live stadium football commentator, tense and hushed at first, then erupting into euphoric excitement on the goal",
26    "temperature": 1.1,
27}
28job = client.submit_async("gemini-3.8-flash-tts", **payload)
29print(job.request_id)                         # available immediately
30try:
31    result = job.wait(timeout=600, interval=1.0)
32except InferenceTimeout as e:
33    print("still running:", e.request_id)
34except InferenceFailed as e:
35    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/gemini-3.8-flash-tts

Parameters

textrequired
string

Transcript to speak, read verbatim; required. Add inline cues like <laughs>, <sigh> or <short pause>. For two speakers, start each turn with its voice name, e.g. 'Kore: Hi!' then 'Puck: Hello!'.

Default: "It's fifteen seconds from the final whistle, and it's still Rovers one, City one. <short pause> Mateo Rinaldi picks it up on the halfway line... he's past one man, past two — can he finish it from here? <gasp> He shoots... and it's IN! Rinaldi wins it at the death, and the whole Olimpico is on its feet!"
styleoptional
string

Plain-English delivery direction applied to every line. Use for emotion, pacing or accent, e.g. 'whispered urgently' or 'cheerful, upbeat'.

temperatureoptional
number

Expressiveness from 0 to 2. Use 0.2-0.5 for steady narration, 0.8-1.4 for emotional, animated delivery.

Default: 0.4Range: 0 - 2
voice_1optional
string

Primary speaker, one of 30 studio voices. Pick the timbre that fits your character; it also leads two-speaker scenes.

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

Optional second speaker for two-person dialogue (max two). Choose a different voice and start each of that speaker's lines with this voice name.

Allowed values (30 total):
"Kore""Puck""Charon""Zephyr""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-3.8-flash-tts

    Submit — returns request_id, status_url, response_url

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

    Poll — until COMPLETED or FAILED

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

    Result — final response body

Status states

QUEUED— Accepted, waiting for a worker
PROCESSING— Running on a worker
COMPLETED— Done — result body is ready
FAILED— Errored (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