ElevenLabs: Eleven Flash v2.5
One API key. Live prices. Ready-to-run code.
Eleven Flash v2.5 is ElevenLabs' ultra-low-latency multilingual text-to-speech model designed for real-time voice agents, conversational AI, interactive applications, telephony, and large-scale speech generation.
Served on OneInfer by ElevenLabs. Use it with the same API key and pay-as-you-go wallet as every other model in the catalog.
elevenlabs/eleven-flash-v2.5Call Eleven Flash v2.5 in 4 steps
Create a key in the Console. The same key works for every model on OneInfer.
- Context
- 2K
- Input
- text
- Output
- audio
- Tool calling
- Not listed
About this model
Eleven Flash v2.5 is ElevenLabs' ultra-low-latency multilingual text-to-speech model designed for real-time voice agents, conversational AI, interactive applications, telephony, and large-scale speech generation. It generates high-quality natural speech with approximately 75 ms model inference latency while supporting 32 languages and up to 40,000 characters per request. The model balances speech quality, speed, and cost for latency-sensitive production workloads and supports streaming generation, voice cloning, multilingual voice consistency, and multiple audio output formats. It is particularly suited for AI calling agents, customer support systems, chatbots, games, IVR applications, and other real-time experiences where fast time-to-speech is critical.
Input modalities
text
Accepted as model input
Providers
Available routing options for this model through OneInfer.
- Available
- Text to speech
- $40.000 / 1M characters
- Routing
- OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Text to speechTTS | $40.000 / 1M characters |
Performance and benchmarks
Independent evaluations and live cluster operational metrics
We haven’t measured this model yet.
API guide
Generate your access token
Use your API key to generate the JWT access token required by the Models API.
Add the JWT token
Copy the generated JWT token and replace
JWT_TOKENin the example below.Check your credits
If your balance is too low, before calling the model.
Run the API example
Choose your preferred language, copy the example, and send your first model request.
curl -X POST https://api.oneinfer.ai/v1/ula/generate-audio \ -H "Authorization: Bearer YOUR_JWT_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "elevenlabs/eleven-flash-v2.5", "prompt": "OneInfer makes AI inference simple.", "stream": false, "voice_id": "English_expressive_narrator", "format": "mp3" }'
Community reviews and ratings
Visitor and developer evaluations of ElevenLabs: Eleven Flash v2.5's real-world intelligence, code accuracy, and speed
Top community tags
No community reviews yet
Be the first to share developer feedback on ElevenLabs: Eleven Flash v2.5's latency, code accuracy, and reliability in production.