Eleven Turbo v2.5
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.
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_turbo_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_turbo_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_turbo_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
Turbo V2.5
A fast, cost-efficient text-to-speech model for natural and expressive voice generation.
Turbo V2.5 is an ElevenLabs text-to-speech model available on WaveSpeed AI. It is designed for teams that need strong voice quality, fast turnaround, and predictable cost, making it well suited for production-grade audio generation. With no cold starts and ready-to-use inference performance, it fits both real-time and batch content workflows.
🚀 Key Features
- Natural, expressive speech: Produces clear pronunciation, smooth pacing, and humanlike prosody for polished voice output.
- Fast generation with no cold start: Delivers responsive performance for high-throughput production pipelines.
- Rich voice selection: Supports a broad set of
voice_idoptions, making it easy to match different brands, characters, or content styles. - Fine-grained voice control: Tune
similarityandstabilityto balance speaker likeness, clarity, and consistency. - Improved English normalization:
use_speaker_boosthelps with English numbers, dates, times, and measurement-heavy scripts. - Affordable pricing: Low per-character cost makes it practical for both prototyping and scaled deployment.
🛠️ Technical Specifications
| Item | Details |
|---|---|
| Model architecture | Text-to-speech(TTS) |
| Model name | Turbo V2.5 |
| Input format | Text(string) |
| Output format | Audio |
| Maximum input length | 10,000 characters |
| Tokenization rule | Each character counts as 1 token |
| Voice selection | Set via voice_id such as Alice, Callum, Gigi, and others |
| Similarity control | similarity: 0.0–1.0; higher values increase target voice likeness but may introduce artifacts |
| Stability control | stability: 0.0–1.0; higher values generally improve delivery consistency |
| English enhancement | use_speaker_boost: improves normalization and reading of English numbers and units |
| Pause control | Insert <#x#> between words to control pauses from 0.01 to 99.99 seconds |
| Latency | Fast inference suitable for production workflows |
| Cold start | None |
| Language support | Multilingual voice support, with strong English reading performance |
Sample prompts
Note: This is a text-to-speech model, so the examples below are sample input scripts.
Welcome to our advanced text-to-speech system! Experience high-quality voice synthesis with natural pronunciation and clear articulation.Today we shipped 12,450 units in Q3, with delivery scheduled at 8:30 AM on October 15th.Please wait <#1.2#> your verification code is 4829 <#0.8#> and will expire in five minutes.
💰 Pricing
| Item | Price |
|---|---|
| Text-to-speech | $0.05 per 1,000 characters |
💡 Best Use Cases
- Voiceovers and narration: Ideal for explainer videos, tutorials, podcasts, and branded media.
- Business audio automation: Useful for alerts, announcements, customer messaging, and information playback.
- Finance and data-heavy scripts: Especially effective for content with numbers, dates, times, and measurements.
- Multi-voice digital content: Great for teams producing character-driven or brand-specific audio at scale.
🔗 Related Models
- Elevenlabs Turbo V2: An earlier Turbo-series option for users comparing speed, quality, and cost.
- Elevenlabs Voice Changer: A complementary model for voice transformation workflows.
Related models
Eleven v3
The most expressive model. Supports 70+ languages. Requires more prompt engineering than our previous models.
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
Eleven Flash v2.5
Our ultra low latency model in 32 languages. Ideal for conversational use cases.