Eleven Flash v2.5
eleven_flash_v2_5
Our ultra low latency model in 32 languages. Ideal for conversational use cases.
Examples
Parameters
| Name | Type | Default | Constraints | Description |
|---|---|---|---|---|
| voice_id *声音id | text | — | — | |
| language_codeISO 639-1语言code | text | — | — | |
| similarity_boostSimilarity Boost | slider | 0.75 | 0 ~ 1 · step 0.05 | |
| stabilityStability | slider | 0.5 | 0 ~ 1 · step 0.05 |
Output fields
| Field | Type | Description |
|---|---|---|
| audio_url | string |
API
Call this model through one unified REST API. Get a key on the API Keys page.
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/eleven_flash_v2_5" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"Python
import time, requests
API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}
# 1) Submit
resp = requests.post(
"https://www.namifusion.com/api/v1/marketplace/run/eleven_flash_v2_5",
headers=HEADERS,
json={
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
},
)
resp.raise_for_status() # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()
# 2) Poll until a terminal state (completed / failed / cancelled).
# This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
if time.time() > deadline:
raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
time.sleep(3)
poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
poll.raise_for_status()
task = poll.json()
print(task["status"], task.get("output"))JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };
// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/eleven_flash_v2_5", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"voice_id": "JBFqnCBsd6RMkjVDRZzb",
"language_code": "en",
"similarity_boost": 0.8,
"stability": 0.55
}
}),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();
// 2) Poll until a terminal state (completed / failed / cancelled).
// This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
await new Promise((r) => setTimeout(r, 3000));
const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
task = await poll.json();
}
console.log(task.status, task.output);Documentation
Flash V2.5
Fast, affordable text-to-speech with no cold starts and natural voice quality.
Flash V2.5 is an ElevenLabs text-to-speech model available on WaveSpeed AI for developers and teams that need reliable, production-ready speech generation. It combines low latency, natural pronunciation, multilingual voice options, and fine-grained voice control, making it a strong choice for narration, voiceovers, and scalable audio content pipelines.
🚀 Key Features
- No cold starts: Well suited for real-time and high-frequency workloads where responsiveness matters.
- Natural-sounding speech: Produces clear pronunciation, smooth pacing, and expressive delivery for polished audio output.
- Rich voice library: Supports a broad set of built-in multilingual voices as well as custom
voice_idvalues. - Fine voice control: Adjust
similarityandstabilityto balance speaker likeness, clarity, and delivery consistency. - English normalization support:
use_speaker_boostimproves reading quality for numbers, dates, times, and measurements in English. - Cost-efficient scaling: Transparent per-character pricing makes it practical for batch generation and commercial content workflows.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model Name | Flash V2.5 |
| Model ID | elevenlabs/flash-v2.5 |
| Model Type | Text-to-Speech(TTS) |
| Input | Text |
| Output | Audio |
| Output Format | MP3 |
| Maximum Input Length | 10,000 characters |
| Billing Unit | Charged per character; price is shown per 1,000 characters |
| voice_id | Default: Alice; supports built-in and custom voice IDs |
| similarity | 0.0–1.0, default 1.0; controls voice similarity and enhancement strength |
| stability | 0.0–1.0, default 0.5; controls consistency of delivery |
| use_speaker_boost | Boolean, default true; improves English text normalization for numbers and units |
| Pause Control | Use <#x#> between words to insert pauses from 0.01 to 99.99 seconds |
| Latency | Optimized for fast generation with no cold starts; actual inference time depends on text length and load |
| Language Support | Multilingual voice support, with strong English number and date reading performance |
Sample Prompts
Note: This is a text-to-speech model, so the examples below are sample input scripts rather than image prompts.
Welcome to our product demo. Today we'll walk through the key features, pricing, and setup in under two minutes.Your appointment is scheduled for 3:45 PM on September 18th. Please arrive 10 minutes early.The package weighs 2.5 kilograms and will arrive in 3 to 5 business days.<#0.5#>Thank you for your order.
💰 Pricing
| Item | Price |
|---|---|
| Generated speech per 1,000 characters | $0.05 |
💡 Best Use Cases
- Marketing and branded content: Create voiceovers for ads, product explainers, and social media content.
- Education and training: Generate narration for courses, tutorials, language learning, and knowledge content.
- Customer support and assistants: Power automated announcements, reminders, and voice-based user experiences.
- Media and publishing: Produce podcasts, audiobooks, summaries, and localized spoken content at scale.
🔗 Related Models
- Elevenlabs Flash V2: An earlier model in the Flash series for teams maintaining existing workflows.
- Elevenlabs Multilingual V1: A related option focused on multilingual speech generation and localization scenarios.
Related models
Eleven v3
The most expressive model. Supports 70+ languages. Requires more prompt engineering than our previous models.
Eleven Turbo v2.5
Our high quality, low latency model in 32 languages. Best for developer use cases where speed matters and you need non-English languages.
Eleven Multilingual v2
Our most life-like, emotionally rich mode in 29 languages. Best for voice overs, audiobooks, post-production, or any other content creation needs