Integrations / PlayHT (direct)
PlayHT (direct)
PlayHT text-to-speech API (api.play.ht) called directly from customer code. TENG-2205: there is no telara-observability SDK wrapper for PlayHT, and unlike the LLM providers there is no OpenAI-compatible fallback either — a generic chat-completion wrapper cannot be pointed at a TTS synthesize call. This connector only receives data if the customer's own code emits an OTel span or log record per synthesize request carrying the attributes below; an uninstrumented integration reports nothing, not zero. PlayHT meters usage by CHARACTERS submitted for synthesis (its plans are priced by monthly character/word volume), not tokens, so gen_ai.usage.* token attributes do not apply and are intentionally absent here — an always-zero input_tokens field would look like real data and isn't. Cost is NOT derived: PlayHT's public pricing is a tiered monthly character allowance, not a flat per-character $ rate, so no model_price_table is set. Dollar figures only appear if the customer's instrumentation independently emits a cost_usd attribute; absent that, this connector reports character and audio-second counts only.
What Telara does
Capability matrix
Before you connect
Prerequisites
Vendor setup
Get the credential
In Telara
Connect in Telara
This connector does not take a vendor key in Settings → Integrations. Run `telara otlp` (or point the vendor’s OpenTelemetry exporter at the endpoint that command prints) so usage arrives as telemetry.
Telara has not published the exact form fields for this method yet. Complete whatever the Connect dialog shows.
Spend
What gets measured
Resolution: Per request.
Attribution: Matched to people by email.
How far back vendor history goes is not published uniformly for this connector.
- characterscount — Characters submitted for synthesis on this call — PlayHT's actual billing unit. Not a standard OTel GenAI attribute (no convention exists for TTS input length); the customer's manual instrumentation must set it, e.g. len(text) at the call site.
- generationscount — Count of synthesize calls (one span/log per TTS request).
- audio_secondsseconds — Duration of the synthesized audio returned, in seconds. Secondary signal alongside characters for teams that reason in playback minutes rather than input length; populated only if the customer's instrumentation reads it back from the response.
Sync
Freshness & sync
Spend connectors refresh on the vendor pull cadence declared in the catalog. Indexing lag is not published for this connector.
Data handling
Permissions & data handling
Telara has not published a permission list for this connector yet. Treat the vendor consent screen as the source of truth until this page lists scopes.
This catalog entry does not declare extra semantic-search exclusions.
After connect
Verify it worked
This connector does not declare a credential probe yet. A saved connection means Telara stored the credential, not that the vendor accepted it.
Honesty