Capabilities
Explore what Murf Falcon 2 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Murf AI
- Product
- Text-to-Speech
- Release Date
- Jun 16, 2026
- Data Policy
- Not specified
- Region
- Global
- Input
- Text
- Output
- Audio
Playground
Try Murf Falcon 2 by Murf AI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Murf Falcon 2.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Murf AI | Not specified | Audio | $8.50 / 1M characters | — | murf/falcon-2:murf |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 3000 |
| Formats | mp3, ogg, flac, wav, pcm, ulaw, alaw |
Provider Notes
Falcon 2 is Murf's $0.01/1K-character low-latency model and supports streaming HTTP plus multiplexed WebSockets. Gen2 is $0.03/1K characters and adds the Synthesize Speech endpoint, word durations, requested audio duration, variation, and zero-retention Base64 output; Murf decommissioned Gen2 streaming on 2026-10-05, so Gen2 is served through Synthesize Speech only. Both models support MP3, FLAC, WAV, Ogg, PCM, μ-law, A-law, regional hosts, voice styles, rate, pitch and locale; only Falcon 2 works on AudioLab's speech WebSocket. Murf's US-East WebSocket currently falls back to Gen2 even when Falcon 2 is selected, so AudioLab pins implicit/global Falcon 2 WebSocket sessions to Murf's US-West host; an explicitly selected residency region remains unchanged. Murf's native WebSocket voice field is camelCase voiceId; AudioLab also accepts voice_id as an input alias and serializes the native form upstream. Provider errors terminate the stream and release every credit reserve. Requests are capped at 3,000 characters per HTTP request or WebSocket context; use the live Murf voice catalog because model voice/style/locale availability differs.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "murf/falcon-2",
"input": "Make every word count.",
"voice": "Gordon",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | murf/falcon-2 — Required model identifier. |
transport | View Accepted Values |
region | View Accepted Values |
format (native JSON) | View Accepted Values |
channel_type | View Accepted Values |
sample_rate | View Accepted Values |
locale | View Accepted Values |
pitch / rate / style | View Accepted Values |
variation (Gen2) | View Accepted Values |
audio_duration (Gen2 generate) | View Accepted Values |
encode_as_base64 (Gen2 generate) | View Accepted Values |
word_durations_as_original_text (Gen2 generate) | View Accepted Values |
voice_config.voiceId / context_id / end / clear (WebSocket) | View Accepted Values |
min_buffer_size / max_buffer_delay_in_ms (WebSocket) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 3000 |
| Formats | mp3, ogg, flac, wav, pcm, ulaw, alaw |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Murf Gen2Murf AI | Not specified | $25.50 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
| audio8DeepInfra | Not specified | $4.25 / 1M characters | — |
