Create a Mistral account at elevenlabs.io, generate your API key, store it securely, then integrate with Bifrost for virtual keys, budgets, and cost governance. Complete setup in minutes.
Bifrost supports ElevenLabs voice APIs for centralized authentication, budgets, and observability.
| Property | Details |
|---|---|
| Description | ElevenLabs provides realistic text-to-speech, voice cloning, and speech-to-text APIs. |
| Provider route on Bifrost | elevenlabs/<model> |
| Provider doc | ElevenLabs |
| API endpoint for provider | https://api.elevenlabs.io/v1 |
| Supported endpoints | /v1/models, /v1/audio/speech, /v1/audio/transcriptions |
ElevenLabs documentation and account links.
Before you begin, you will need:
[ QUICK START ]
Use the ElevenLabs website.
Go to elevenlabs.io and sign up with email or SSO.
Click your profile icon, then open Profile + API key (or API Keys in the dashboard).
Copy the key immediately.
Generate a new API key, name it, and copy the value. Store it as an environment variable.
export ELEVENLABS_API_KEY="..."
Use the xi-api-key header or Bearer auth per ElevenLabs docs.
ElevenLabs accepts xi-api-key on REST endpoints:
$ curl "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM" -H "xi-api-key: $ELEVENLABS_API_KEY" -H "Content-Type: application/json" -d '{"text": "Hello from ElevenLabs!", "model_id": "eleven_multilingual_v2"}' --output speech.mp3
[ MODELS ]
| Model | API ID | Best for |
|---|---|---|
| Eleven Multilingual v2 | eleven_multilingual_v2 | High-quality multilingual TTS. |
| Eleven Turbo v2.5 | eleven_turbo_v2_5 | Low-latency TTS for real-time apps. |
| Eleven Flash v2.5 | eleven_flash_v2_5 | Fastest TTS with good quality. |
| Eleven v3 | eleven_v3 | Latest expressive speech generation. |
| Scribe v1 | scribe_v1 | Speech-to-text transcription. |
Models and availability change over time. See the ElevenLabs' models documentation for the latest list and pricing.
[ TROUBLESHOOTING ]
| Error | Likely Cause | What to Do |
|---|---|---|
401 Unauthorized | Invalid or missing API key. | Verify your API key is correct. Generate a new key if needed. |
400 Bad Request | Invalid request format or unsupported model. | Check request format and confirm model ID is valid. |
429 Rate Limited | Rate limit exceeded for your plan. | Upgrade your plan or implement exponential backoff. Use Bifrost for intelligent load distribution. |
502/503 Service Error | Temporary Mistral service unavailability. | Retry after a delay. Check Mistral status page. Configure failover with Bifrost. |
[ PRODUCTION-READY ]
Bifrost is a drop-in replacement for ElevenLabs SDKs: keep your client code and change the base URL to your gateway. Bifrost handles cost tracking, virtual keys, budgets, and failover automatically.
Run the Bifrost gateway and configure your Mistral credentials in the Web UI.
$ npx -y @maximhq/bifrost
✓ Bifrost started ├─ HTTP server listening on http://localhost:8080 ├─ Web UI available at http://localhost:8080 └─ Configure providers and virtual keys in the dashboard
Update your OpenAI SDK client to route through the Bifrost gateway.
import OpenAI client = OpenAI( api_key="sk-bf-your-virtual-key", base_url="http://localhost:8080/openai" ) response = client.audio.speech.create( model="eleven_multilingual_v2", voice="21m00Tcm4TlvDq8ikWAM", input="Hello from Bifrost!", response_format="mp3", ) # response is a streamable HttpxBinaryResponseContent audio = response.read() print(len(audio)) # Or save directly to a file response.stream_to_file("output.mp3")
x-bf-vk or Authorization: Bearer sk-bf-* per the Bifrost documentation.[ WHAT'S NEXT ]
You have your API key. Add governance, guardrails, and MCP controls for production.
[ BIFROST FEATURES ]
Everything you need to run AI in production, from free open source to enterprise-grade features.
01 Governance
SAML support for SSO and Role-based access control and policy enforcement for team collaboration.
02 Adaptive Load Balancing
Automatically optimizes traffic distribution across provider keys and models based on real-time performance metrics.
03 Cluster Mode
High availability deployment with automatic failover and load balancing. Peer-to-peer clustering where every instance is equal.
04 Alerts
Real-time notifications for budget limits, failures, and performance issues on Email, Slack, PagerDuty, Teams, Webhook and more.
05 Log Exports
Export and analyze request logs, traces, and telemetry data from Bifrost with enterprise-grade data export capabilities for compliance, monitoring, and analytics.
06 Audit Logs
Comprehensive logging and audit trails for compliance and debugging.
07 Vault Support
Secure API key management with HashiCorp Vault, AWS Secrets Manager, Google Secret Manager, and Azure Key Vault integration.
08 VPC Deployment
Deploy Bifrost within your private cloud infrastructure with VPC isolation, custom networking, and enhanced security controls.
09 Guardrails
Automatically detect and block unsafe model outputs with real-time policy enforcement and content moderation across all agents.
[ SHIP RELIABLE AI ]
Change just one line of code. Works with OpenAI, Anthropic, Vercel AI SDK, LangChain, and more.
[ FAQ ]
Yes. The free tier includes monthly character credits for testing text-to-speech.
Pass your API key in the xi-api-key header on https://api.elevenlabs.io/v1 requests.
Yes. ElevenLabs supports instant and professional voice cloning, see their voice API documentation.
TTS endpoints typically return MP3 or PCM depending on parameters. Check the API reference for options.
Add ElevenLabs in the Bifrost dashboard and route through http://localhost:8080/elevenlabs.
Usage is billed by characters converted to speech. Monitor usage in the ElevenLabs dashboard or via Bifrost.