Skip to main content
Glama
Sign In

Nexscope

by io.github.nexscope
OverviewDiscussionsAdmin

Twitch Clip Transcript

social_twitch_clip_transcript
Read-only

Gets a transcript from a public Twitch clip. Checks native captions first; returned native captions cost 1 credit. Set use_ai_as_fallback=true to opt into paid AI only when captions are unavailable. No transcript costs 0 credits. transcript_source is native, ai, or null. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Completed lookups cost at least 10 Nexscope credits. Actual cost depends on the operation and requested options. Repeated requests may purchase data again. Twitch Clip Transcript API View Pricing Get native captions from a Twitch clip. Enable use_ai_as_fallback for AI when captions are unavailable. Native captions or AI up to 2 minutes: 1 credit. Paid AI mode: 10 credits/minute, rounded up, even for short videos. No transcript: 0 credits. Gets a transcript from a public Twitch clip. Checks native captions first; returned native captions cost 1 credit. Set use_ai_as_fallback=true to opt into paid AI only when captions are unavailable. No transcript costs 0 credits. transcript_source is native, ai, or null. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Use paid AI only when native captions are unavailable. Defaults to false. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Current official page: returned native captions or successful default AI up to 120 seconds cost 1; no transcript 0. AI fallback is separately enabled. With literal allow_long_transcription=true, all successful AI, including short, costs 10 per started minute; empty AI/errors have no AI fee.

Input Schema

NameRequiredDescriptionDefault
urlYesTwitch clip URL
use_ai_as_fallbackNoUse paid AI only when native captions are unavailable. Defaults to false. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.
allow_long_transcriptionNoPaid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/openWorld/non-destructive, so the description carries the pricing, latency and failure behavior — 1 credit for native captions, 0 for no transcript, 10 credits per started minute under paid mode, synchronous calls needing 30+ seconds, and timeouts on long videos. That is genuinely useful context an agent cannot get from annotations. It loses a point because the flag semantics are muddled (allow_long_transcription is variously 'opt into paid AI' and 'does not enable transcription or AI fallback by itself'), and the credit costs sit in tension with the readOnlyHint framing of a zero-side-effect read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The same credit-policy paragraph is pasted five or more times, including leaked marketing/UI text ('Twitch Clip Transcript API View Pricing Get native captions...'). The actual signal — caption-first, AI fallback opt-in, 120-second cap, 10-credits-per-minute paid mode — is buried under duplication and is not front-loaded beyond the first sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does supply the key return semantics an agent needs: transcript_source is native, ai, or null, and a null/empty result costs nothing. It also warns about latency and timeouts. What it omits is the shape of a successful payload (transcript text field, language, duration), which matters given the absent output schema, and the contradictory flag framing leaves residual ambiguity about how to actually trigger paid long transcription.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters (url, use_ai_as_fallback, allow_long_transcription) are already documented in the schema with the same pricing text. The description adds no parameter meaning beyond what the schema provides — it largely repeats it verbatim. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource: 'Gets a transcript from a public Twitch clip.' That is unambiguous and lets an agent distinguish it from social_twitch_clip or social_kick_clip. However, it never differentiates itself from the many other *_transcript siblings (YouTube, TikTok, Rumble, Kick clip transcripts), so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives operational guidance about the two flags: native captions are always tried first, use_ai_as_fallback opts into paid AI only when captions are unavailable, and allow_long_transcription is required for clips over 120 seconds. That is real when-to-use guidance for the options, but there is no guidance on when to call this tool versus alternatives (e.g., social_twitch_clip for metadata, or the Kick/Rumble transcript tools) and no when-not-to-use exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Nexscope toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources