Run text-to-speech behind a managed API
Serve open text-to-speech models like Parler or Zonos from an autoscaling endpoint that returns hosted audio URLs. Beam manages the GPUs and only bills while speech is being generated.
Scalable voice AI infrastructure
Run open models on your own endpoint with flat compute pricing.
Any open TTS model
Parler and Zonos have step-by-step guides, and anything that runs in PyTorch deploys the same way.
Explore docsHosted audio outputs
Save generated audio with Output and return a public URL straight from the endpoint, so you don't wire up storage buckets.
Explore docsWarm models per container
on_start loads the model once per container, so generation starts immediately on every request.
Explore docsKeep-warm for voice apps
Hold containers hot with keep_warm_seconds when response time matters, and scale to zero the rest of the time.
Explore docsAutoscale with traffic
Beam adds containers as requests grow and removes them when traffic stops, so idle GPUs don't show up on your bill.
Explore docsPer-second pricing
Pay for seconds of GPU generation instead of per character, per voice, or by usage tier.
Explore docsShip a voice API in three steps
Define the endpoint
Load your TTS model in on_start and declare the GPU and Python packages inline.
Deploy it
beam deploy returns an authenticated HTTPS URL backed by autoscaling GPUs.
POST text, get audio
The endpoint returns a hosted URL for the generated file.
$ beam deploy app.py:speak
=> Deployed 🎉
=> https://parler-tts-abc123.app.beam.cloud
$ curl -X POST https://parler-tts-abc123.app.beam.cloud \
-H 'Authorization: Bearer YOUR_TOKEN' \
-d '{"prompt": "Welcome! Your order has shipped."}'
{"url": "https://app.beam.cloud/output/id/3f2a..."}Frequently asked questions
Which TTS models can I run?
Beam has guides for Parler-TTS and Zonos, and any open text-to-speech model that runs in PyTorch deploys the same way, including your own fine-tuned voices.
How is audio returned?
Save the file with Output and return a hosted public URL, or base64-encode the audio into the JSON response.
How do I keep latency down for real-time apps?
Combine on_start model loading with keep_warm_seconds so containers stay hot between requests. Cold boots on Beam take seconds, not minutes.
What does it cost when nobody is talking?
Nothing. Endpoints scale to zero when idle and billing is per-second while audio is being generated.
Can I batch-generate narration for long documents?
Yes. Run the same function as a task queue or fan it out with .map() to synthesize many segments in parallel.
Related use cases
Run Whisper transcription behind your own API
On-demand Whisper transcription behind an autoscaling API.
InferenceDeploy open-source LLMs
Serve open-source LLMs behind an autoscaling, OpenAI-compatible API.
SandboxesGive your AI agents a safe place to run code
Isolated sandboxes for agent-generated code, booting in seconds.
Give your agents their own machines
Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.