Voice APIvoice.ai ↗
Access Voice.ai queue wait times, TTS demo voices, and pricing plans via 3 endpoints. Get real-time tool status and voice metadata for audio workflow automation.
What is the Voice API?
The Voice.ai API covers 3 endpoints that expose queue wait times for audio processing tools, available text-to-speech demo voices, and current pricing plan details. The get_queue_wait_times endpoint returns per-tool estimated wait times in seconds alongside human-readable descriptions, letting you poll service load before dispatching audio jobs. The list_tts_voices endpoint returns voice IDs, names, and avatar URLs for all voices in the public TTS demo.
curl -X GET 'https://api.parse.bot/scraper/d7b6424e-cdb7-4533-8215-80495d6daef6/get_queue_wait_times?tool=vocal-remover' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace voice-ai-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
from parse_apis.voice_ai_tools_api import VoiceAI, Tool, BillingCycle
client = VoiceAI()
# Get queue wait times for all tools
queue = client.queuestatuses.get()
print(queue.tools, queue.tool_descriptions)
# Get wait time for a specific tool
demucs_queue = client.queuestatuses.get(tool=Tool.DEMUCS)
print(demucs_queue.tools)
# Get monthly pricing plans
pricing = client.pricinginfos.get(billing_cycle=BillingCycle.MONTH)
print(pricing.billing_cycle)
for plan in pricing.plans:
print(plan.name, plan.price_display, plan.credits_per_month, plan.is_most_popular)
# List available TTS voices
catalog = client.voicecatalogs.get()
print(catalog.total, catalog.max_text_length)
for voice in catalog.voices:
print(voice.id, voice.name, voice.avatar_url)
Get current estimated queue wait times (in seconds) for Voice.ai audio processing tools. Returns wait times for all tools by default, or for a specific tool when the tool parameter is provided. Tools include vocal-remover, echo-remover, demucs (stem splitter), audio-converter, and denoiser. Wait times are polled from the live queue and reflect real-time load.
| Param | Type | Description |
|---|---|---|
| tool | string | Filter to a specific audio tool. |
{
"type": "object",
"fields": {
"tools": "object mapping tool name to wait time in seconds",
"tool_descriptions": "object mapping tool name to human-readable description"
},
"sample": {
"data": {
"tools": {
"demucs": 38,
"denoiser": 0,
"echo-remover": 0,
"vocal-remover": 0,
"audio-converter": 0
},
"tool_descriptions": {
"demucs": "Stem splitter - separate audio into individual stems",
"denoiser": "Remove background noise from audio",
"echo-remover": "Remove echo from audio recordings",
"vocal-remover": "Remove vocals from audio tracks",
"audio-converter": "Convert audio between formats"
}
},
"status": "success"
}
}About the Voice API
Audio Tool Queue Times
The get_queue_wait_times endpoint returns a tools object mapping each tool name to its current estimated queue wait time in seconds, plus a tool_descriptions object with a human-readable description for each. By default it returns data for all four supported tools: vocal-remover, echo-remover, demucs, and audio-converter. Pass the optional tool parameter with exactly one of those values to narrow the response to a single tool — useful when you only care about a specific processing step.
Text-to-Speech Demo Voices
The list_tts_voices endpoint requires no inputs and returns three fields: total (integer count of available voices), voices (an array of objects each containing id, name, and avatar_url), and max_text_length (the maximum character count accepted by the TTS demo). This gives you a complete inventory of selectable voices without needing to interact with the Voice.ai interface directly.
Pricing Plans
The get_pricing_plans endpoint accepts an optional billing_cycle parameter (month or year) and returns a plans array with full pricing and feature details per plan, plus a billing_cycle field confirming which period the returned data covers. This is useful for displaying up-to-date plan comparisons or alerting when plan structures change.
The Voice API is a managed, monitored endpoint for voice.ai — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when voice.ai changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official voice.ai API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Poll
get_queue_wait_timesbefore submitting a batch job to estimate turnaround for vocal-remover or demucs processing. - Build a dashboard that surfaces real-time queue depth across all four Voice.ai audio tools.
- Enumerate all TTS demo voices via
list_tts_voicesto populate a voice-selection UI with accurate IDs and avatar images. - Track
max_text_lengthfromlist_tts_voicesto validate user input before sending to the TTS demo. - Monitor pricing plan changes over time by scheduling periodic calls to
get_pricing_plansand diffing results. - Compare monthly vs. yearly plan features by calling
get_pricing_planswith bothbilling_cyclevalues and presenting the diff to users.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does Voice.ai have an official developer API?+
What does the `tool` parameter in `get_queue_wait_times` accept?+
vocal-remover, echo-remover, demucs, or audio-converter. When omitted, the endpoint returns wait times and descriptions for all four tools in a single response.Does the API return actual audio output or TTS-generated files?+
Can I retrieve historical queue wait times or trend data?+
What fields come back for each voice in `list_tts_voices`?+
voices array includes id, name, and avatar_url. The response also includes total (count of voices) and max_text_length (the character limit for TTS demo input).