Creative x402 offerings

AI chat completions API - pay per request with USDC on Solana

AI chat completions API - pay per request with USDC on Solana

OpenAI-compatible text embeddings for retrieval and semantic search.

OpenAI-compatible chat completions for Qwen chat/reasoning/code models.

Synthesize speech (MP3/WAV/OGG) from text or SSML.

OpenAI-compatible chat completions for Qwen-MT translation.

Generate content with Gemini 2.0 Flash (text + multimodal).

OpenAI-compatible chat completions for Qwen OCR (image-to-text).

Generates images from trending sounds and audio-inspired prompts.

Audio transcription and speech to text: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds.

Transcribe audio to text with the gpt-transcribe model - the same model as /api/transcribe with a longer cap. Provide a URL to an audio file and get back the transcript; add diarize:true for speaker labels, word timestamps and a language confidence score (the scribe-v2 model). No API key needed; pay per call via x402. Max 10 minutes of audio, 25 MB file size.

Use when an agent is handed audio and needs text it can work with: Whisper large v3 turbo - pass an https URL (mp3, wav, flac, m4a, ogg, up to 10 MB) or base64 audio in a POST. Returns the text, the detected language with its probability, the duration, and timed segments; add words=true for word-level timestamps. Around 100 languages. You are only charged if the transcript is delivered. No API key, no account.

Speech-to-text (OpenAI-compatible /v1/audio/transcriptions, multipart). Whisper large-v3-turbo, 100 languages, verbose_json with segment timestamps + duration. wav/mp3 up to 5 min / 12 MB. $0.003 USDC per minute (Telnyx list rate, zero margin), metered per second via the upto scheme (min $0.002 network floor ≈ 40s), or flat $0.015 exact.

OpenAI's transcription wire on the ten-minute tier: POST multipart/form-data with a `file` part. Same model as /v1/audio/transcriptions with a longer cap, for a recording a four-minute route refuses.

Assesses how suitable an image is for use as a spokesperson or presenter.

Submit a Stable Diffusion 3.5 Large image generation request

Submit a MiniMax Video 01 generation request

Submit a FLUX Pro 1.1 Ultra image generation request

Submit a Recraft V3 image generation request

Submit a Stable Video generation request

Submit a Fast SDXL image generation request

Submit a FLUX Schnell image generation request

Submit a FLUX Dev image generation request

Generates a 1024x1024 image from a text description and returns a ready-to-use image URL - illustrations, thumbnails and visual assets on demand